1
|
Neuhaus H, Nguyen A, Grossmann J. A novel colonoscope with a wider field of view of 230° - first in human case. Endoscopy 2025; 57:E157-E158. [PMID: 39933749 PMCID: PMC11813659 DOI: 10.1055/a-2524-5900] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/13/2025]
Affiliation(s)
- Horst Neuhaus
- Department of Gastroenterology, RKM740 Interdisciplinary Care Clinic, Düsseldorf, Germany
| | - Anh Nguyen
- Department of Gastroenterology, RKM740 Interdisciplinary Care Clinic, Düsseldorf, Germany
| | - Johannes Grossmann
- Department of Gastroenterology, RKM740 Interdisciplinary Care Clinic, Düsseldorf, Germany
| |
Collapse
|
2
|
Nascimento de Lima P, Maerzluft C, Ozik J, Collier N, Rutter CM. Stress-Testing US Colorectal Cancer Screening Guidelines: Decennial Colonoscopy from Age 45 is Robust to Natural History Uncertainty and Colonoscopy Sensitivity Assumptions. Med Decis Making 2025; 45:557-568. [PMID: 40302197 DOI: 10.1177/0272989x251334373] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/01/2025]
Abstract
PurposeThe 2023 American College of Physicians (ACP) guidelines for colorectal cancer (CRC) screening are at odds with the United States Preventive Task Force (USPSTF) guidelines, with the former recommending screening starting at age 50 y and the latter at age 45 y. This article "stress tests" CRC colonoscopy screening strategies to investigate their robustness to uncertainties stemming from the natural history of disease and sensitivity of colonoscopy.MethodsThis study uses the CRC-SPIN microsimulation model to project the life-years gained (LYG) under several colonoscopy CRC screening strategies. The model was extended to include birth cohort effects on adenoma risk. We estimated natural history parameters under 2 different assumptions about the youngest age of adenoma initiation. For each, we generated 500 parameter sets to reflect uncertainty in the natural history parameters. We simulated 26 colonoscopy screening strategies and examined 4 different colonoscopy sensitivity assumptions, encompassing the range of sensitivities consistent with prior tandem colonoscopy studies. Across this set of scenarios, we identify efficient screening strategies and report posterior credible intervals for benefits of screening (LYG), burden (number of colonoscopies), and incremental burden-effectiveness ratios.ResultsProjected absolute screening benefits varied widely based on assumptions, but strategies starting at age 45 y were consistently in the efficiency frontier. Strategies in which screening starts at age 50 y with 10-y intervals were never efficient, saving fewer life-years than starting screening at age 45 y and performing colonoscopies every 15 y while requiring more colonoscopies per person.ConclusionsDecennial colonoscopy screening initiation at age 45 y remained a robust recommendation. Colonoscopy screening with a 10-y interval starting at age 50 y did not result in an efficient use of colonoscopies in any of the scenarios evaluated.HighlightsColorectal cancer colonoscopy screening strategies initiated at age 45 y were projected to yield more life-years gained while requiring the least number of colonoscopies across different model assumptions about disease natural history and colonoscopy sensitivity.Colonoscopy screening starting at age 50 y with a 10-y interval consistently underperformed strategies that started at age 45 y.
Collapse
Affiliation(s)
| | - Christopher Maerzluft
- Hutchinson Institute for Cancer Outcomes Research, Fred Hutchinson Cancer Center, Seattle, WA, USA
| | - Jonathan Ozik
- Decision and Infrastructure Sciences, Argonne National Laborator, Argonne, IL, USA
| | - Nicholson Collier
- Decision and Infrastructure Sciences, Argonne National Laborator, Argonne, IL, USA
| | - Carolyn M Rutter
- Hutchinson Institute for Cancer Outcomes Research, Fred Hutchinson Cancer Center, Seattle, WA, USA
| |
Collapse
|
3
|
Sergeev D, Heisser T, Hoffmeister M, Brenner H. Potential for enhancing efficacy of screening colonoscopy by lowering starting ages and extending screening intervals: A modelling study for Germany. Int J Cancer 2025; 156:2303-2310. [PMID: 39751766 PMCID: PMC12008824 DOI: 10.1002/ijc.35322] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2024] [Revised: 12/05/2024] [Accepted: 12/16/2024] [Indexed: 01/04/2025]
Abstract
Studies aimed to evaluate the expected impact of alternative screening strategies are essential for optimizing colorectal cancer (CRC) screening offers, but such studies are lacking in Germany, where two screening colonoscopies (CS) 10 years apart are offered for men from age 50 and women from age 55. Our aim was to explore whether and to what extent the efficacy of utilizing two CS could be enhanced by alternative starting ages and screening intervals. We modeled the expected numbers of CRC cases, CRC deaths, years of potential life lost (YPLL), and disability-adjusted life years (DALYs) due to CRC in hypothetical cohorts of 100,000 men and women aged 45-85 using COSIMO, a validated Markov-based multi-state simulation model. Modeled strategies included combinations of starting ages (45/50/55/60) and CS (10/15/20 years). For men, CRC deaths could be slightly reduced by extending the interval to 15 years, with a second CS at 65. YPLL and DALYs would be reduced by decreasing starting age to 45 when combined with a 15-year screening interval. For women, use of two CS at ages 50 and 65 would reduce all CRC burden parameters compared to the current earliest-use offer at 55 and 65 years. Our results suggest that lowering the starting age of screening colonoscopy to 45 for men and 50 for women, combined with extending the CS screening interval to 15 years would have the potential to enable significant reductions in years of potential life lost, and disability-adjusted life years compared to current screening offers in Germany.
Collapse
Affiliation(s)
- Dmitry Sergeev
- Division of Clinical Epidemiology and Aging ResearchGerman Cancer Research Center (DKFZ)HeidelbergGermany
- Medical Faculty Heidelberg, Heidelberg UniversityHeidelbergGermany
| | - Thomas Heisser
- Division of Clinical Epidemiology and Aging ResearchGerman Cancer Research Center (DKFZ)HeidelbergGermany
| | - Michael Hoffmeister
- Division of Clinical Epidemiology and Aging ResearchGerman Cancer Research Center (DKFZ)HeidelbergGermany
| | - Hermann Brenner
- Division of Clinical Epidemiology and Aging ResearchGerman Cancer Research Center (DKFZ)HeidelbergGermany
- German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ)HeidelbergGermany
| |
Collapse
|
4
|
Aleissa MA, Luca M, Singh JP, Chitragari G, Drelichman ER, Mittal VK, Bhullar JS. Current status of artificial intelligence colonoscopy on improving adenoma detection rate based on systematic review of multiple metanalysis. Artif Intell Gastroenterol 2025; 6:106149. [DOI: 10.35712/aig.v6.i1.106149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/17/2025] [Revised: 03/23/2025] [Accepted: 05/08/2025] [Indexed: 06/06/2025] Open
Abstract
BACKGROUND Colorectal cancer (CRC) can be prevented by screening and early detection. Colonoscopy is used for screening, and adenoma detection rate (ADR) is used as a key quality indicator of sufficient colonoscopy. However, ADR can vary significantly among endoscopists, leading to missed polyps or cancer. Artificial intelligence (AI) has shown promise in improving ADR by assisting in real-time polyp identification or diagnosis. While multiple randomized controlled trials (RCTs) and metanalyses highlight the benefits of AI in increasing detection rates and reducing missed polyps, concerns remain about its real-world applicability, impact on procedure time, and cost-effectiveness.
AIM To explore the current status of AI assistance colonoscopy in adenoma detection and improving quality of colonoscopy.
METHODS This systematic review followed PRISMA guidelines, both PubMed and Web of Science databases were used for articles search. Metanalyses and systematic reviews that assessed AI's role during colonoscopy. English article only published between January 2000 and January 2025 were included. Articles related to non-adenoma indications were excluded. Data extraction was independently performed by two researchers for accuracy and consistency.
RESULTS 22 articles met the inclusion criteria, with significant heterogeneity (I2 = 28%-91%) observed in multiple studies. The number of studies per metanalysis ranged from 5 to 33, with higher heterogeneity in analyses involving more than 18 RCTs. AI demonstrated improvement in ADR, with an approximate 20% increase across multiple studies. However, its effectiveness in detecting flat or serrated adenomas remains unproven. Endoscopists with low ADR benefit more from AI-colonoscopies, while expert endoscopists outperformed AI in ADR, adenoma miss rate, and the identification of advanced lesions. No significant change in withdrawal time was observed when comparing AI-assisted colonoscopy to conventional endoscopy.
CONCLUSION While AI-assisted colonoscopy has been shown to improve procedural quality, particularly for junior endoscopists and those with lower ADR, its performance decreases when compared to expert endoscopists in real-time clinical practice. This is especially evident in non-randomized studies, where AI demonstrates limited real-world benefits despite its benefit in controlled settings. Furthermore, no meta-analyses have specifically examined AI's impact on the learning experience of fellows and residents. Some experts caution that reliance on AI may prevent trainees from developing essential observational skills, potentially leading to less thorough examinations. Further research is needed to determine the actual benefits of AI-colonoscopy, particularly its role in cancer prevention. As technology advances, improved outcomes are expected, especially in detecting small, flat, and lesions at difficult anatomical locations.
Collapse
Affiliation(s)
- Maryam A Aleissa
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfeild, MI 48075, United States
- Collage of Medicine, Princess Nourah bint Abdulrhman University, Riyadh 84428, Saudi Arabia
| | - Micheal Luca
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfield, MI 48075, United States
| | - Jai P Singh
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfield, MI 48075, United States
| | - Gautham Chitragari
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfield, MI 48075, United States
| | - Ernesto R Drelichman
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfield, MI 48075, United States
| | - Vijay K Mittal
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfield, MI 48075, United States
| | - Jasneet S Bhullar
- Department of Surgery, Henry Ford Providence Hospital, Michigan State University College of Human Medicine, Southfield, MI 48075, United States
| |
Collapse
|
5
|
Hagen R, Srivastava A, Anderson JC. The serrated pathway and colorectal cancer: what the gastroenterologist should know. Expert Rev Gastroenterol Hepatol 2025:1-14. [PMID: 40409278 DOI: 10.1080/17474124.2025.2509797] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/20/2025] [Revised: 04/28/2025] [Accepted: 05/19/2025] [Indexed: 05/25/2025]
Abstract
INTRODUCTION Serrated polyps can progress to colorectal cancer (CRC), through a pathway that is distinct from the conventional adenoma-carcinoma sequence. This pathway includes hyperplastic polyps (HPs), sessile serrated polyps (SSPs), and traditional serrated adenomas (TSAs). AREAS COVERED Our review includes the histology and pathological challenges, carcinogenesis, risk factors, detection, emerging technologies, resection, and surveillance. EXPERT OPINION Serrated polyp management presents many detection, diagnosis, resection, and surveillance challenges. Missed serrated polyps contribute to preventable CRCs. A new SSP detection rate benchmark will guide endoscopists with a goal when improving detection. Furthermore, new SSP-specific surveillance strategies may also aid in reducing CRC burden. Histologic differentiation remains a challenge, underscoring the need for standardized pathology practices and exploring novel ways to stratify risk independent of histology, given interobserver variation. Moreover, the clinical significance of proximal HPs requires further clarification. Which HPs < 1 cm require closer surveillance intervals? Molecular profiling may help identify markers that separate proximal low risk from high-risk HP. The best approach for resection of serrated polyps also needs to be clarified. There is also a lack of robust longitudinal outcome data to guide surveillance recommendations since current guidelines are based on low quality of evidence.
Collapse
Affiliation(s)
- Rachael Hagen
- Department of Medicine, University of Connecticut, Farmington, CT, USA
| | - Amitabh Srivastava
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Joseph C Anderson
- Department of Medicine, University of Connecticut, Farmington, CT, USA
- Division of Gastroenterology and Hepatology, Department of Medicine, Geisel School of Medicine at Dartmouth, Hanover, NH, USA
- Division of Gastroenterology and Hepatology, Department of Medicine, White River Junction VAMC, White River Junction, VT, USA
| |
Collapse
|
6
|
Jukic I, Vukovic J. Bowel Preparation for Colonoscopy in Patients with Diabetes Mellitus-A Gap We Have to Bridge: A Review. J Clin Med 2025; 14:3336. [PMID: 40429332 PMCID: PMC12111914 DOI: 10.3390/jcm14103336] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2025] [Revised: 04/27/2025] [Accepted: 05/09/2025] [Indexed: 05/29/2025] Open
Abstract
Colonoscopy is an essential diagnostic and therapeutic tool in gastroenterology, significantly impacting colorectal cancer (CRC) detection and management. Effective bowel preparation is critical for optimal visualization, directly influencing colonoscopy accuracy and patient outcomes. However, diabetic patients frequently encounter challenges achieving adequate bowel preparation, primarily due to gastroparesis, autonomic neuropathy, altered colonic motility, fluid-electrolyte imbalances, and complexities related to antihyperglycemic medication adjustments. This review aims to evaluate the current literature on bowel preparation efficacy in diabetic patients undergoing colonoscopy, assess existing guidelines from leading gastroenterological societies, and highlight the necessity for detailed, diabetes-specific recommendations. We conducted a comprehensive PubMed search identifying 20 pertinent studies, including randomized controlled trials, meta-analyses, multicenter studies, cohort studies, and reviews. The findings consistently indicate diabetes as an independent predictor of inadequate bowel preparation. Furthermore, an evaluation of guidelines from the European Society of Gastrointestinal Endoscopy (ESGE), the US Multi-Society Task Force, and the Canadian Association of Gastroenterology revealed either absent or insufficiently detailed diabetes-specific recommendations. Given the rising global prevalence of diabetes and CRC, inadequate bowel preparation significantly impacts the quality of colonoscopy, adenoma detection rates, patient safety, and healthcare costs. This review underscores the urgent need for additional research focusing on tailored bowel preparation strategies for diabetic patients. Ultimately, the implementation of standardized, evidence-based protocols designed explicitly for this high-risk group is essential to enhance diagnostic efficacy, improve patient outcomes, and reduce CRC-related morbidity and mortality.
Collapse
Affiliation(s)
- Ivana Jukic
- Department of Gastroenterology and Hepatology, University Hospital Split, Spinciceva 1, 21000 Split, Croatia;
- University Department of Health Studie, University of Split, 21000 Split, Croatia
| | - Jonatan Vukovic
- Department of Gastroenterology and Hepatology, University Hospital Split, Spinciceva 1, 21000 Split, Croatia;
- Department of Internal Medicine, School of Medicine, University of Split, 21000 Split, Croatia
| |
Collapse
|
7
|
Xu Z, Li Y, Su P, Zhong Z, Zeng Z, Chen M, Chen D, Lan C. Artificial intelligence system improves the quality of digestive endoscopy: A prospective pretest and post-test single-center clinical trial. Dig Liver Dis 2025:S1590-8658(25)00739-X. [PMID: 40345942 DOI: 10.1016/j.dld.2025.04.029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/18/2024] [Revised: 03/10/2025] [Accepted: 04/15/2025] [Indexed: 05/11/2025]
Abstract
BACKGROUND With the assistance of ENDOANGEL, a study was conducted at Hainan General Hospital to evaluate the effect of artificial intelligence (AI) system on the detection of gastrointestinal precancerous lesions. METHODS The prospective, randomized, pretest and post-test, single-center clinical trial compared the detection rates of gastric precancerous lesions and intestinal adenomas between baseline and post-intervention phase among traditional digestive endoscopy (control groups i and ii, and experimental group i) and AI-assisted endoscopy (experimental group ii). Additionally, the effect of AI on the detection rate of different seniority physicians was analyzed. RESULTS AI assistance significantly increased the detection rates of intestinal metaplasia (experimental group ii vs control group ii: 14.23 % vs 9.15 %, P = 0.013), atrophy (experimental group ii vs control group ii: 22.76 % vs 17.28 %, P = 0.031) and intestinal adenomas (experimental group ii vs control group ii: 48.52 % vs 24.58 %, P < 0.001). The improvement was particularly notable among junior doctors, with significant enhancements in the detection rates of intestinal metaplasia (experimental group ii vs control group ii: 14.39 % vs 9.09 %, P = 0.008), atrophy (experimental group ii vs control group ii: 22.04 % vs 15.31 %, P = 0.004), and intestinal adenomas (experimental group ii vs control group ii: 45.18 % vs 29.27 %, P = 0.002). CONCLUSIONS AI systems have the potential to significantly improve the detection rates of precancerous conditions, particularly among less experienced endoscopists. This advancement can lead to more accurate and appropriate follow-up and review strategies for patients, ultimately reducing the risk of missed early cancer diagnoses.
Collapse
Affiliation(s)
- Zewen Xu
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China
| | - Yongrong Li
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China
| | - Peiqiang Su
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China
| | - Zhuangxia Zhong
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China
| | - Zuni Zeng
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China
| | - Mingli Chen
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China
| | - Di Chen
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China.
| | - Cheng Lan
- Department of Gastroenterology, Hainan General Hospital, Hainan Affiliated Hospital of Hainan Medical University, Haikou, China.
| |
Collapse
|
8
|
Huang ES, Huang Q, Kenkare P, Mudiganti S, Martinez MC, Liang SY. Prevalence of "one and done" phenomenon in adenoma detection within a large community-based healthcare system. Gastrointest Endosc 2025; 101:1038-1050.e2. [PMID: 39481577 DOI: 10.1016/j.gie.2024.10.055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/07/2024] [Revised: 10/07/2024] [Accepted: 10/28/2024] [Indexed: 11/02/2024]
Abstract
BACKGROUND AND AIMS Adenoma detection rate (ADR) is a key quality metric in colonoscopy, reflecting the ability to detect adenomas. However, concerns remain regarding the robustness of ADR as a benchmark. In particular, the "one and done" phenomenon may exist in which physicians are less motivated to find additional adenomas after discovery of the first adenoma. To investigate this topic further, our goal was to understand the relationship between single and multiple adenoma detection. METHODS A retrospective cohort study was conducted by using data from 89,587 screening colonoscopies performed by 32 endoscopists within the Sutter Health-Palo Alto Medical Foundation between 2015 and 2020. ADR, single adenoma detection rate (ADR1), and multiple adenoma detection rate (ADR2+) were analyzed by using multivariate logistic regression and linear regression models. Endoscopists were then fit into 4 categories based on median ADR1 and ADR2+ (low ADR1, high ADR2+ ["all or none"], low ADR1, low ADR2+ ["none and done"], high ADR1, high ADR2+ ["all and done"], or high ADR1, low ADR2+ ["one and done"]). RESULTS The overall ADR was 45.4%. ADR, ADR1, and ADR2+ were significantly associated with similar factors, including older age, male sex, higher body mass index, smoking status, high-risk colonoscopies, Medicare insured, use of mucosal assist devices, longer withdrawal times, adequate preparation, and procedures performed by high-volume, female endoscopists with a longer duration in practice. The median ADR1 and ADR2+ were 23.95% and 21.29%, respectively. ADR1 and ADR2+ were positively correlated (Pearson correlation coefficient [r], .701; P < .001). Only 4 of 32 endoscopists fit our "one and done" category. CONCLUSIONS These findings suggest that ADR1 correlates with ADR2+. Despite concerns, the "one and done" phenomenon is not commonly seen in clinical practice. ADR remains a good surrogate marker for multiple adenoma detection.
Collapse
Affiliation(s)
- Edward S Huang
- Department of Gastroenterology, Palo Alto Medical Foundation, Sutter Health, San Jose, CA.
| | - Qiwen Huang
- Center for Health Systems Research, Palo Alto, CA
| | | | | | | | | |
Collapse
|
9
|
Rex DK. Colonoscopy Remains an Important Option for Primary Screening for Colorectal Cancer. Dig Dis Sci 2025; 70:1595-1605. [PMID: 39666212 DOI: 10.1007/s10620-024-08760-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/07/2024] [Accepted: 11/14/2024] [Indexed: 12/13/2024]
Abstract
Colonoscopy remains the most commonly used colorectal cancer screening test in the United States. A substantial portion of the screening population value the high sensitivity of colonoscopy for precancerous colorectal lesions of all sizes, which allows it to be performed at 10 year intervals in average-risk persons with negative examinations. Emerging evidence supports the eventual endorsement of 15 year intervals for patients with normal examinations. Considerable evidence supports an impact of colonoscopy on colorectal cancer incidence and mortality, including a randomized controlled trial of colonoscopy vs. no screening, numerous case-control and cohort studies, an impact of fecal blood testing on cancer incidence, and the impact of one randomized controlled trial of flexible sigmoidoscopy on proximal colon cancer incidence. Colonoscopy is the gold standard for detection of colorectal precancerous lesions, and continues to evolve with regard to sensitivity for precancerous lesions and the effectiveness and safety of precancerous lesion resection. Gains in detection of precancerous lesions have followed from a robust movement to improve colonoscopy quality, and development of non-device techniques such as patient rotation during withdrawal, water exchange colonoscopy, and double examination of one or more colonic segments. Further, development of devices to improve mucosal exposure during withdrawal (e.g. Endocuff Vision, distal cap attachment, and Computer-Aided Quality), and devices that highlight flat lesions (e.g. chromoendoscopy, electronic chromoendoscopy, and Computer-Aided Detection) have created opportunities to achieve very high levels of detection and thereby increase the protective benefits of colonoscopy. Further, colonoscopy resection safety has improved via the widespread use of cold resection for lesions < 10 mm in size, as well as sessile serrated lesions of all sizes. Colonoscopy can be offered to patients as one of multiple options for screening, or as the test of choice for patients with the highest pre-screening probability of cancer and precancerous lesions, or as the first test offered followed by offers of other screening tests if colonoscopy is declined (sequential offers of screening). Sequential offers of screening result in overall adherence to screening similar to offering multiple options, but with a higher fraction of patients undergoing colonoscopy. Given the long-lasting protective effects of colonoscopy and its improving effectiveness and safety, colonoscopy remains a useful option for primary average-risk colorectal cancer screening.
Collapse
Affiliation(s)
- Douglas K Rex
- Division of Gastroenterology/Hepatology, Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, USA.
| |
Collapse
|
10
|
Ren X, Zhou W, Yuan N, Li F, Ruan Y, Zhou H. Prompt-based polyp segmentation during endoscopy. Med Image Anal 2025; 102:103510. [PMID: 40073580 DOI: 10.1016/j.media.2025.103510] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2024] [Revised: 12/26/2024] [Accepted: 02/15/2025] [Indexed: 03/14/2025]
Abstract
Accurate judgment and identification of polyp size is crucial in endoscopic diagnosis. However, the indistinct boundaries of polyps lead to missegmentation and missed cancer diagnoses. In this paper, a prompt-based polyp segmentation method (PPSM) is proposed to assist in early-stage cancer diagnosis during endoscopy. It combines endoscopists' experience and artificial intelligence technology. Firstly, a prompt-based polyp segmentation network (PPSN) is presented, which contains the prompt encoding module (PEM), the feature extraction encoding module (FEEM), and the mask decoding module (MDM). The PEM encodes prompts to guide the FEEM for feature extracting and the MDM for mask generating. So that PPSN can segment polyps efficiently. Secondly, endoscopists' ocular attention data (gazes) are used as prompts, which can enhance PPSN's accuracy for segmenting polyps and obtain prompt data effectively in real-world. To reinforce the PPSN's stability, non-uniform dot matrix prompts are generated to compensate for frame loss during the eye-tracking. Moreover, a data augmentation method based on the segment anything model (SAM) is introduced to enrich the prompt dataset and improve the PPSN's adaptability. Experiments demonstrate the PPSM's accuracy and real-time capability. The results from cross-training and cross-testing on four datasets show the PPSM's generalization. Based on the research results, a disposable electronic endoscope with the real-time auxiliary diagnosis function for early cancer and an image processor have been developed. Part of the code and the method for generating the prompts dataset are available at https://github.com/XinZhenRen/PPSM.
Collapse
Affiliation(s)
- Xinzhen Ren
- Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, CO 200444, China
| | - Wenju Zhou
- Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, CO 200444, China.
| | - Naitong Yuan
- Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, CO 200444, China
| | - Fang Li
- Department of Obstetrics and Gynecology, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, CO 200120, China.
| | - Yetian Ruan
- Department of Obstetrics and Gynecology, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, CO 200120, China
| | - Huiyu Zhou
- School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK
| |
Collapse
|
11
|
Enslin S, Kaul V. Past, Present, and Future: A History Lesson in Artificial Intelligence. Gastrointest Endosc Clin N Am 2025; 35:265-278. [PMID: 40021228 DOI: 10.1016/j.giec.2024.09.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/04/2025]
Abstract
Over the past 5 decades, artificial intelligence (AI) has evolved rapidly. Moving from basic models to advanced machine learning and deep learning systems, the impact of AI on various fields, including medicine, has been profound. In gastroenterology, AI-driven computer-aided detection and computer-aided diagnosis systems have revolutionized endoscopy, imaging, and pathology detection. The future promises further advancements in diagnostic precision, personalized treatment, and clinical research. However, challenges such as transparency, liability, and ethical concerns must be addressed. By fostering collaboration, robust governance and development of quality metrics, AI can be leveraged to enhance patient care and advance scientific knowledge.
Collapse
Affiliation(s)
- Sarah Enslin
- Division of Gastroenterology and Hepatology, Center for Advanced Therapeutic Endoscopy, University of Rochester Medical Center, 601 Elmwood Avenue, Box 646, Rochester, NY 14642, USA
| | - Vivek Kaul
- Division of Gastroenterology and Hepatology, Center for Advanced Therapeutic Endoscopy, University of Rochester Medical Center, 601 Elmwood Avenue, Box 646, Rochester, NY 14642, USA.
| |
Collapse
|
12
|
Kang AJ, Rodrigues T, Patel RV, Keswani RN. Impact of Artificial Intelligence on Gastroenterology Trainee Education. Gastrointest Endosc Clin N Am 2025; 35:457-467. [PMID: 40021241 DOI: 10.1016/j.giec.2024.12.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/03/2025]
Abstract
Artificial intelligence (AI) is transforming gastroenterology, particularly in endoscopy, which has a direct impact on trainees and their education. AI can serve as a valuable resource, providing real-time feedback and aiding in tasks like polyp detection and lesion differentiation, which are challenging for trainees. However, its implementation raises concerns about cognitive overload, overreliance, and even access disparities, which could affect training outcomes. Beyond endoscopy, AI shows promise in clinical management and interpreting diagnostic studies such as motility testing. Thoughtful adoption of AI can optimize training and prepare future trainees for the modern healthcare landscape.
Collapse
Affiliation(s)
- Anthony J Kang
- Division of Gastroenterology & Hepatology, Northwestern Feinberg School of Medicine, Chicago, IL, USA
| | - Terrance Rodrigues
- Division of Gastroenterology & Hepatology, Northwestern Feinberg School of Medicine, Chicago, IL, USA
| | - Ronak V Patel
- Division of Gastroenterology & Hepatology, Northwestern Feinberg School of Medicine, Chicago, IL, USA
| | - Rajesh N Keswani
- Division of Gastroenterology & Hepatology, Northwestern Feinberg School of Medicine, Chicago, IL, USA.
| |
Collapse
|
13
|
Rizkala T, Menini M, Massimi D, Repici A. Role of Artificial Intelligence for Colon Polyp Detection and Diagnosis and Colon Cancer. Gastrointest Endosc Clin N Am 2025; 35:389-400. [PMID: 40021235 DOI: 10.1016/j.giec.2024.10.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/03/2025]
Abstract
The broad use of artificial intelligence (AI) and its various applications have already shown significant impact in medicine and in everyday life. In gastroenterology, the most studied AI tools at present are computer-aided detection (CADe) and computer-aided diagnosis (CADx). These tools have been mainly assessed during colonoscopy for the detection of polyps and for the prediction of their histology based on their appearance. Their use aims to improve colonoscopy quality, standardize procedures, and potentially reduce costs. Data on CADe demonstrate clear benefits that are applicable to clinical practice. While CADx shows good diagnostic performance, its additional benefits in assisting endoscopists remain unclear.
Collapse
Affiliation(s)
- Tommy Rizkala
- Endoscopy Unit, Department of Gastroenterology, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, Milan 20089, Italy
| | - Maddalena Menini
- Endoscopy Unit, Department of Gastroenterology, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, Milan 20089, Italy
| | - Davide Massimi
- Endoscopy Unit, Department of Gastroenterology, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, Milan 20089, Italy
| | - Alessandro Repici
- Endoscopy Unit, Department of Gastroenterology, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, Milan 20089, Italy; Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, Milan 20072, Italy.
| |
Collapse
|
14
|
Choi CH, Lee JH, Koh MS, Lee JY. Risk Factors of Missed Adenoma Detected by Colonoscopic Polypectomy and Its Impact of the Endoscopic System. Dig Dis Sci 2025; 70:1503-1510. [PMID: 39992354 DOI: 10.1007/s10620-025-08937-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/24/2024] [Accepted: 02/16/2025] [Indexed: 02/25/2025]
Abstract
BACKGROUND The adenoma detection rate is a key colonoscopy quality indicator, but the adenoma miss rate (AMR) is more strongly linked to post-colonoscopy colorectal cancer risk. While studies examined high-definition colonoscopy and AMR, no studies have assessed its impact on consecutive polypectomy. AIM This study aimed to identify adenomas missed in screening or surveillance colonoscopy and determine if the endoscopic system affects the miss rate. METHODS This retrospective study analyzed patients referred to Dong-A University Hospital for polypectomy after polyps were detected during screening or surveillance colonoscopy at 24 healthcare institutions. Endoscopic systems used in these colonoscopies were classified as FHD (FHD) or non-FHD. Consecutive polypectomies were performed by a single expert between March 2020 and February 2022 using the FHD system. The AMR was compared and analyzed for screening or surveillance colonoscopies performed using FHD endoscopic systems and those using non-FHD endoscopic systems. RESULTS Of 542 polyps, 186 were missed (miss rate: 25.22%). Miss rates for adenoma and advanced neoplasia were 27.34% and 14.69%. Univariate analysis identified age, adenoma count, and endoscopic system as significant factors. However, only the endoscopic system remained significant in the multivariate analysis. In screening or surveillance colonoscopy, the use of FHD endoscopic systems demonstrated a lower AMR compared to non-FHD systems (21.86% vs. 31.41%, P = 0.014). CONCLUSION The use of FHD endoscopic systems reduced AMR compared to non-FHD systems.
Collapse
Affiliation(s)
- Chi Hyeon Choi
- Department of Internal Medicine, Dong-A University College of Medicine, Busan, 49201, South Korea
| | - Jong Hoon Lee
- Department of Internal Medicine, Dong-A University College of Medicine, Busan, 49201, South Korea
| | - Myeong Seok Koh
- Department of Internal Medicine, Dong-A University College of Medicine, Busan, 49201, South Korea
| | - Jong Yoon Lee
- Department of Internal Medicine, Dong-A University College of Medicine, Busan, 49201, South Korea.
| |
Collapse
|
15
|
Sultan S, Shung DL, Kolb JM, Foroutan F, Hassan C, Kahi CJ, Liang PS, Levin TR, Siddique SM, Lebwohl B. AGA Living Clinical Practice Guideline on Computer-Aided Detection-Assisted Colonoscopy. Gastroenterology 2025; 168:691-700. [PMID: 40121061 DOI: 10.1053/j.gastro.2025.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/25/2025]
Abstract
BACKGROUND & AIMS This American Gastroenterological Association (AGA) guideline is intended to provide an overview of the evidence and support endoscopists and patients on the use of computer-aided detection (CADe) systems for the detection of colorectal polyps during colonoscopy. METHODS A multidisciplinary panel of content experts and guideline methodologists used the Grading of Recommendations Assessment, Development and Evaluation framework and relied on the following sources of evidence: (1) a systematic review examining the desirable and undesirable effects (ie, benefits and harms) of CADe-assisted colonoscopy, (2) a microsimulation study estimating the effects of CADe on longer-term patient-important outcomes, (3) a systematic search of evidence evaluating the values and preferences of patients undergoing colonoscopy, and (4) a systematic review of studies evaluating health care providers' trust in artificial intelligence technology in gastroenterology. RESULTS The panel reached the conclusion that no recommendation could be made for or against the use of CADe-assisted colonoscopy in light of very low certainty of evidence for the critical outcomes, desirable and undesirable (11 fewer colorectal cancers per 10,000 individuals and 2 fewer colorectal cancer deaths per 10,000 individuals), increased burden of more intensive surveillance colonoscopies (635 more per 10,000 individuals), and cost and resource implications. The panel acknowledged the 8% (95% CI, 6%-10%) increase in adenoma detection rate and 2% (95% CI, 0%-4%) increase in advanced adenoma and/or sessile serrated lesion detection rate. CONCLUSIONS This guideline highlights the close tradeoff between desirable and undesirable effects and the limitations in the current evidence to support a recommendation. The panel acknowledged the potential for CADe to continually improve as an iterative artificial intelligence application. Ongoing publications providing evidence for critical outcomes will help inform a future recommendation.
Collapse
Affiliation(s)
- Shahnaz Sultan
- Division of Gastroenterology, Hepatology, and Nutrition, University of Minnesota, Minneapolis, Minnesota; Minneapolis Veterans Affairs Healthcare System, Minneapolis, Minnesota
| | - Dennis L Shung
- Department of Medicine, Section of Digestive Diseases, Yale School of Medicine, New Haven, Connecticut
| | - Jennifer M Kolb
- Vatche and Tamar Manoukian Division of Digestive Diseases, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, California; Division of Gastroenterology, Hepatology and Parenteral Nutrition, Veterans Affairs Greater Los Angeles Healthcare System, Los Angeles, California
| | - Farid Foroutan
- MAGIC Evidence Ecosystem Foundation, Oslo, Norway; Ted Rogers Centre for Heart Research, University Health Network, Toronto, Ontario, Canada
| | - Cesare Hassan
- IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy; Department of Biomedical Sciences, Humanitas University, Milan, Italy
| | - Charles J Kahi
- Department of Gastroenterology, Indiana University Medical Center, Indianapolis, Indiana
| | - Peter S Liang
- Department of Medicine, Division of Gastroenterology and Hepatology, NYU Langone Health, New York, New York; Department of Medicine, Veterans Affairs New York Harbor Health Care System, New York, New York
| | - Theodore R Levin
- Division of Research, Kaiser Permanente Northern California, Pleasanton, California; Department of Gastroenterology, Kaiser Permanente Walnut Creek, Walnut Creek, California
| | - Shazia Mehmood Siddique
- Division of Gastroenterology, University of Pennsylvania, Philadelphia, Pennsylvania; Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania; Center for Healthcare Improvement and Patient Safety, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Benjamin Lebwohl
- Department of Medicine, Columbia University Irving Medical Center, New York, New York; Department of Epidemiology, Mailman School of Public Health, Columbia University, New York, New York
| |
Collapse
|
16
|
Okumura T, Hotta K, Imai K, Ito S, Kishida Y, Takada K, Kawaguchi D, Mori Y, Tanaka Y, Tsushima T, Kawata N, Maeda Y, Yoshida M, Yamamoto Y, Minamide T, Ishiwatari H, Sato J, Matsubayashi H, Ono H. Efficacy of texture and color enhancement imaging for the visibility and diagnostic accuracy of non-polypoid colorectal lesions. DEN OPEN 2025; 5:e380. [PMID: 38817687 PMCID: PMC11136699 DOI: 10.1002/deo2.380] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Revised: 04/11/2024] [Accepted: 04/21/2024] [Indexed: 06/01/2024]
Abstract
Objective A newly launched endoscopy system (EVIS X1, CV-1500; Olympus) is equipped with texture and color enhancement imaging (TXI). We aimed to investigate the efficacy of TXI for the visibility and diagnostic accuracy of non-polypoid colorectal lesions. Methods We examined 100 non-polypoid lesions in 42 patients from the same position, angle, and distance of the view in three modes: white light imaging (WLI), narrow-band imaging (NBI), and TXI. The primary outcome was to compare polyp visibility in the three modes using subjective polyp visibility score and objective color difference values. The secondary outcome was to compare the diagnostic accuracy without magnification. Results Overall, the visibility score of TXI was significantly higher than that of WLI (3.7 ± 1.1 vs. 3.6 ± 1.1; p = 0.008) and lower than that of NBI (3.7 ± 1.1 vs. 3.8 ± 1.1; p = 0.013). Color difference values of TXI were higher than those of WLI (11.5 ± 6.9 vs. 9.1 ± 5.4; p < 0.001) and lower than those of NBI (11.5 ± 6.9 vs. 13.1 ± 7.7; p = 0.002). No significant differences in TXI and NBI (visibility score: 3.7 ± 1.0 vs. 3.8 ± 1.1; p = 0.833, color difference values: 11.6 ± 7.1 vs. 12.9 ± 8.3; p = 0.099) were observed for neoplastic lesions. Moreover, the diagnostic accuracy of TXI was significantly higher than that of NBI (65.5% vs. 57.6%, p = 0.012) for neoplastic lesions. Conclusions TXI demonstrated higher visibility than that of WLI and lower than that of NBI. Further investigations are warranted to validate the performance of the TXI mode comprehensively.
Collapse
Affiliation(s)
- Taishi Okumura
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | - Kinichi Hotta
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | - Kenichiro Imai
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | - Sayo Ito
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | | | | | - Daiki Kawaguchi
- Division of Gastrointestinal OncologyShizuoka Cancer CenterShizuokaJapan
| | - Yukihiro Mori
- Division of Colon and Rectal SurgeryShizuoka Cancer CenterShizuokaJapan
| | - Yusuke Tanaka
- Division of Colon and Rectal SurgeryShizuoka Cancer CenterShizuokaJapan
| | - Takahiro Tsushima
- Division of Gastrointestinal OncologyShizuoka Cancer CenterShizuokaJapan
| | - Noboru Kawata
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | - Yuki Maeda
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | - Masao Yoshida
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | | | | | | | - Junya Sato
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| | | | - Hiroyuki Ono
- Division of EndoscopyShizuoka Cancer CenterShizuokaJapan
| |
Collapse
|
17
|
Papachrysos N, Smedsrud PH, Ånonsen KV, Berstad TJD, Espeland H, Petlund A, Hedenström PJ, Halvorsen P, Varkey J, Hammer HL, Riegler MA, de Lange T. A comparative study benchmarking colon polyp with computer-aided detection (CADe) software. DEN OPEN 2025; 5:e70061. [PMID: 39830225 PMCID: PMC11742239 DOI: 10.1002/deo2.70061] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/14/2024] [Revised: 12/27/2024] [Accepted: 01/08/2025] [Indexed: 01/22/2025]
Abstract
Background and aims Computer-aided detection software (CADe) has shown promising results in real-time polyp detection, but a limited head-to-head comparison of the available CADe systems has been performed. Moreover, such systems have not been compared to endoscopists using standardized videos. This study aims to compare the performance of three CADe systems in detecting polyps, employing a novel standardized methodology. Methods Videos from 300 colonoscopies conducted at Oslo University Hospital were analyzed. Short video clips (20-45 s) presenting normal mucosa or polyps were randomly selected. These videos were then streamed through each CADe system from Medtronic, Olympus, and Augere Medical. Each system featured diverse configurations, resulting in a total of six software settings. Sensitivity and false positivity (FP) were assessed by comparing the CADe systems to both the mean of the systems and pairwise between them. Furthermore, the systems' performance was compared to the performance of five endoscopists. Results CADe systems' sensitivity ranged between 84.9% and 98.7%, with statistically significant differences observed between the systems, both in comparison to the mean and to each other. FP rates ranged between 1.2% and 5.6%, also differing statistically significantly between the systems. The CADe systems achieving the highest sensitivity also exhibited the highest FP. Statistically significant differences in the alert delay were observed between different CADe systems and endoscopists. Conclusions This study highlights significant differences between commercially available CADe software regarding sensitivity and FP, but a superior performance compared to endoscopists. The software with the highest sensitivity also exhibited the highest FP, highlighting the need for further refinement.
Collapse
Affiliation(s)
- Nikolaos Papachrysos
- Department of Medicine, Geriatrics and EmergenciesDivision of GastroenterologySahlgrenska University Hospital/ÖstraGothenburgSweden
- Department of Molecular and Clinical Medicine, Institute of MedicineUniversity of GothenburgGothenburgSweden
| | - Pia Helén Smedsrud
- Augere Medical ASOsloNorway
- Department of InformaticsUniversity of OsloOsloNorway
- SimulaMetOsloNorway
| | - Kim V. Ånonsen
- Department of GastroenterologyOslo University HospitalOsloNorway
| | | | | | | | - Per J. Hedenström
- Department of Molecular and Clinical Medicine, Institute of MedicineUniversity of GothenburgGothenburgSweden
- Department of Specialized MedicineDivision of GastroenterologySahlgrenska University HospitalGothenburgSweden
| | - Pål Halvorsen
- SimulaMetOsloNorway
- Oslo Metropolitan UniversityOsloNorway
| | - Jonas Varkey
- Department of Molecular and Clinical Medicine, Institute of MedicineUniversity of GothenburgGothenburgSweden
- Department of Specialized MedicineDivision of GastroenterologySahlgrenska University HospitalGothenburgSweden
| | - Hugo L. Hammer
- SimulaMetOsloNorway
- Oslo Metropolitan UniversityOsloNorway
| | | | - Thomas de Lange
- Department of Molecular and Clinical Medicine, Institute of MedicineUniversity of GothenburgGothenburgSweden
- Augere Medical ASOsloNorway
- Department of Medicine & EmergenciesSahlgrenska University Hospital/Mölndal, Västra Götaland CountyGothenburgSweden
| |
Collapse
|
18
|
Guo Z, Hu Y, Ge P, Chan IN, Yan T, Wong PK, Xu S, Li Z, Gao S. Enhancing colorectal polyp classification using gaze-based attention networks. PEERJ COMPUTER SCIENCE 2025; 11:e2780. [DOI: 10.7717/peerj-cs.2780] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/03/2025]
Abstract
Colorectal polyps are potential precursor lesions of colorectal cancer. Accurate classification of colorectal polyps during endoscopy is crucial for early diagnosis and effective treatment. Automatic and accurate classification of colorectal polyps based on convolutional neural networks (CNNs) during endoscopy is vital for assisting endoscopists in diagnosis and treatment. However, this task remains challenging due to difficulties in the data acquisition and annotation processes, the poor interpretability of the data output, and the lack of widespread acceptance of the CNN models by clinicians. This study proposes an innovative approach that utilizes gaze attention information from endoscopists as an auxiliary supervisory signal to train a CNN-based model for the classification of colorectal polyps. Gaze information from the reading of endoscopic images was first recorded through an eye-tracker. Then, the gaze information was processed and applied to supervise the CNN model’s attention via an attention consistency module. Comprehensive experiments were conducted on a dataset that contained three types of colorectal polyps. The results showed that EfficientNet_b1 with supervised gaze information achieved an overall test accuracy of 86.96%, a precision of 87.92%, a recall of 88.41%, an F1 score of 88.16%, the area under the receiver operating characteristic (ROC) curve (AUC) is 0.9022. All evaluation metrics surpassed those of EfficientNet_b1 without gaze information supervision. The class activation maps generated by the proposed network also indicate that the endoscopist’s gaze-attention information, as auxiliary prior knowledge, increases the accuracy of colorectal polyp classification, offering a new solution to the field of medical image analysis.
Collapse
Affiliation(s)
- Zhenghao Guo
- School of Mechanical Engineering, Hubei University of Arts and Science, Xiangyang, China
| | - Yanyan Hu
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, China
| | - Peixuan Ge
- Department of Electromechanical Engineering, University of Macau, Taipa, Macao, China
| | - In Neng Chan
- Department of Electromechanical Engineering, University of Macau, Taipa, Macao, China
| | - Tao Yan
- School of Mechanical Engineering, Hubei University of Arts and Science, Xiangyang, China
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, China
- Department of Electromechanical Engineering, University of Macau, Taipa, Macao, China
| | - Pak Kin Wong
- Department of Electromechanical Engineering, University of Macau, Taipa, Macao, China
| | - Shaoyong Xu
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, China
| | - Zheng Li
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, China
| | - Shan Gao
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, China
| |
Collapse
|
19
|
Bustamante-Balén M, Merino Rodríguez B, Barranco L, Monje J, Álvarez M, de Pedro S, Oyagüez I, Van Lent N, Mareque M. Cost-effectiveness analysis of artificial intelligence-aided colonoscopy for adenoma detection and characterization in Spain. Endosc Int Open 2025; 13:a25097278. [PMID: 40109314 PMCID: PMC11922311 DOI: 10.1055/a-2509-7278] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/01/2024] [Accepted: 12/17/2024] [Indexed: 03/22/2025] Open
Abstract
Background and study aims The aim of this study was to assess the cost-effectiveness of an intelligent endoscopy module for computer-assisted detection and characterization (CADe/CADx) compared with standard practice, from a Spanish National Health System perspective. Methods A Markov model was designed to estimate total costs, life years gained (LYG), and quality-adjusted life years (QALYs) over a lifetime horizon with annual cycles. A hypothetical cohort of 1,000 patients eligible for colonoscopy (mean age 61.32 years) was distributed between Markov states according to polyp size, location, and histology based on national screening program data. CADe/CADx efficacy was determined based on adenoma miss rates and natural disease evolution was simulated according to annual transition probabilities. Detected polyp management involved polypectomy and histopathology in standard practice, whereas with CADe/CADx leave-in-situ strategy was applied for ≤ 5 mm rectosigmoid non-adenomas and resect-and-discard strategy for the rest of ≤ 5mm polyps. Unit costs (€,2024) included the diagnostic procedure and polyp and colorectal cancer (CRC) management. A 3% annual discount rate was applied to costs and outcomes. Model inputs were validated by an expert panel. Results CADe/CADx was more effective (16.37 LYG and 14.32 QALYs) than standard practice (16.33 LYG and 14.27 QALYs) over a lifetime horizon. Total cost per patient was €2,300.76 with CADe/CADx and €2,508.75 with colonoscopy alone. In a hypothetical cohort of 1,000 patients, CADe/CADx avoided 173 polypectomies, 370 histopathologies, and 7 CRC cases. Sensitivity analyses confirmed model robustness. Conclusions The results of this analysis suggest that CADe/CADx would result in a dominant strategy versus standard practice in patients undergoing colonoscopy in Spain.
Collapse
Affiliation(s)
- Marco Bustamante-Balén
- Digestive Endoscopy Unit, Gastroenterology Department, La Fe University Hospital, Valencia, Spain
- Health Research Institute La Fe, IIS La Fe, Valencia, Spain
| | - Beatriz Merino Rodríguez
- Endoscopy Unit, Department of Gastroenterology, Gregorio Marañón General University Hospital, Madrid, Spain
| | - Luis Barranco
- Endoscopy Unit, Digestive Department, Hospital del Mar, Barcelona, Spain
| | - Julen Monje
- Health Economics & Outcomes Research Unit, Medtronic Ibérica S.A., Madrid, Spain
| | - María Álvarez
- Health Economics & Outcomes Research Unit, Medtronic Ibérica S.A., Madrid, Spain
| | - Sofía de Pedro
- Pharmacoeconomics & Outcomes Research Iberia (PORIB), Madrid, Spain
| | - Itziar Oyagüez
- Pharmacoeconomics & Outcomes Research Iberia (PORIB), Madrid, Spain
| | - Nancy Van Lent
- Health Economics & Outcomes Research, Medtronic International Trading Sarl, Tolochenaz, Switzerland
| | - María Mareque
- Pharmacoeconomics & Outcomes Research Iberia (PORIB), Madrid, Spain
| |
Collapse
|
20
|
Kinugasa H, Hiraoka S, Kobayashi S, Matsubara M, Nagahara T, Higashi R, Takei K, Ohmori M, Nakamura T, Tsuzuki T, Tanaka S, Hirai R, Toyosawa J, Aoyama Y, Yamasaki Y, Inokuchi T, Takahara M, Tanaka T, Mitsuhashi T, Otsuka M. Acetic Acid-Indigo Carmine Chromocolonoscopy for Proximal Serrated Lesions: A Randomized, 3-Arm Colonoscopy Study. Am J Gastroenterol 2025:00000434-990000000-01639. [PMID: 40079452 DOI: 10.14309/ajg.0000000000003411] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/22/2024] [Accepted: 02/21/2025] [Indexed: 03/15/2025]
Abstract
INTRODUCTION Aggressive colorectal cancer (CRC) frequently originates from serrated lesions (SLs), particularly in the proximal colon, which are challenging to detect using standard screening colonoscopy. Although duplicate examinations or chromocolonoscopies are recommended for detecting proximal SLs, evidence from randomized trials is limited. We evaluated the effectiveness of tandem colonoscopy with an acetic acid-indigo carmine mixture (AIM) for detecting SLs in the proximal colon compared with white-light imaging (WLI) and indigo carmine (IC). METHODS This 3-arm, multicenter, randomized controlled trial involving 9 institutions enrolled patients undergoing colonoscopy and assigned them randomly to the WLI, IC, or AIM group. The primary outcomes were the SL-detection rate (SDR) of proximal lesions during the second examination (SDR 2nd ) and SL additional rate (SAR). Secondary outcomes included the detection and additional rates of other polyps, factors contributing to SAR, and complications. RESULTS Between 2021 and 2024, 1,319 participants with 1,267 polyps were included in the analysis. With AIM, the SDR 2nd and SAR were significantly higher compared with WLI or IC (WLI vs AIM: 2.7% vs 14.0%, P < 0.001; IC vs AIM: 7.9% vs 14.0%, P = 0.002, and WLI vs AIM: 22.4% vs 69.3%, P < 0.001; IC vs AIM: 45.8% vs 69.3%, P = 0.001). AIM conferred a higher adenoma detection rate 2nd than with WLI (10.5% vs 24.7%; P < 0.001) and was an independent factor for SAR (odds ratio [95% confidence interval]: 7.79 [3.76-17.08]). No major adverse events were observed. DISCUSSION AIM significantly improved proximal colon SDRs and outperformed WLI and IC. The relationship between SDR and CRC incidence warrants further investigation.
Collapse
Affiliation(s)
- Hideaki Kinugasa
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Sakiko Hiraoka
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Sayo Kobayashi
- Department of Internal Medicine, Fukuyama City Hospital, Hiroshima, Japan
| | - Minoru Matsubara
- Department of Gastroenterology and Hepatology, Sumitomo Besshi Hospital, Ehime, Japan
| | - Teruya Nagahara
- Department of Gastroenterology and Hepatology, Mitoyo General Hospital, Kagawa, Japan
| | - Reiji Higashi
- Department of Gastroenterology and Hepatology, Ichinomiyanishi Hospital, Aichi, Japan
| | - Kensuke Takei
- Department of Internal Medicine, Tsuyama Chuo Hospital, Okayama, Japan
| | - Masayasu Ohmori
- Department of Medicine, Hiroshima City Hiroshima Citizens Hospital, Hiroshima, Japan
| | - Takashi Nakamura
- Department of Internal Medicine, Takahashi Central Hospital, Okayama, Japan
| | - Takao Tsuzuki
- Department of Internal Medicine, Japanese Red Cross Society Himeji Hospital, Hyogo, Japan
| | - Shouichi Tanaka
- Department of Gastroenterology and Hepatology, Iwakuni National Hospital, Yamaguchi, Japan
| | - Ryosuke Hirai
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Junki Toyosawa
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Yuki Aoyama
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Yasushi Yamasaki
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Toshihiro Inokuchi
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Masahiro Takahara
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Takehiro Tanaka
- Department of Pathology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Toshiharu Mitsuhashi
- Center for Innovative Clinical Medicine, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| | - Motoyuki Otsuka
- Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan
| |
Collapse
|
21
|
Jahn B, Bundo M, Arvandi M, Schaffner M, Todorovic J, Sroczynski G, Knudsen A, Fischer T, Schiller-Fruehwirth I, Öfner D, Renner F, Jonas M, Kuchin I, Kruse J, Santamaria J, Ferlitsch M, Siebert U. One in three adenomas could be missed by white-light colonoscopy - findings from a systematic review and meta-analysis. BMC Gastroenterol 2025; 25:170. [PMID: 40082770 PMCID: PMC11908064 DOI: 10.1186/s12876-025-03679-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/13/2024] [Accepted: 02/11/2025] [Indexed: 03/16/2025] Open
Abstract
BACKGROUND White light (conventional) colonoscopy (WLC) is widely used for colorectal cancer screening, diagnosis and surveillance but endoscopists may fail to detect adenomas. Our goal was to assess and synthesize overall and subgroup-specific adenoma miss rates (AMR) of WLC in daily practice. METHODS We conducted a systematic review in MEDLINE, EMBASE, Cochrane Library, and grey literature on studies evaluating diagnostic WLC accuracy in tandem studies with novel-colonoscopic technologies (NCT) in subjects undergoing screening, diagnostic or surveillance colonoscopy. Information on study design, AMR overall and specific for adenoma size, histology, location, morphology and further outcomes were extracted and reported in standardized evidence tables. Study quality was assessed using the QUADAS-2 tool. Random-effects meta-analyses and meta-regression were performed to estimate pooled estimates for AMR with 95% confidence intervals (95% CI) and to explain heterogeneity. RESULTS Out of 5,963 identified studies, we included sixteen studies with 4,101 individuals in our meta-analysis. One in three adenomas (34%; 95% CI: 30-38%) was missed by WLC in daily practice individuals. Subgroup analyses showed significant AMR differences by size (36%, adenomas 1-5 mm; 27%, adenomas 6-9 mm; 12%, adenomas ≥ 10 mm), histology (non-advanced: 42%, advanced: 21%), morphology (flat: 50%, polypoid: 27%), but not by location (distal: 36%, proximal: 36%). CONCLUSIONS Based on our meta-analysis, one in three adenomas could be missed by WLC. This may significantly contribute to interval cancers. Our results should be considered in health technology assessment when interpreting sensitivity of fecal occult blood or other screening tests derived from studies using WLC as "gold standard".
Collapse
Affiliation(s)
- Beate Jahn
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Marvin Bundo
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
- Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland
- Oeschger Center for Climate Change Research, University of Bern, Bern, Switzerland
| | - Marjan Arvandi
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Monika Schaffner
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Jovan Todorovic
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Gaby Sroczynski
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Amy Knudsen
- Institute for Technology Assessment, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Timo Fischer
- Main Association of Austrian Social Security Institutions, Vienna, Austria
| | | | - Dietmar Öfner
- Department of Visceral, Transplant and Thoracic Surgery, Medical University of Innsbruck, Innsbruck, Austria
| | | | - Michael Jonas
- Medical Association of Vorarlberg, Dornbirn, Austria
| | - Igor Kuchin
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Julia Kruse
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Júlia Santamaria
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria
| | - Monika Ferlitsch
- Department of Internal Medicine III, Division of Gastroenterology and Hepatology, Medical University of Vienna, Vienna, Austria
| | - Uwe Siebert
- Department of Public Health, Health Services Research and Health Technology Assessment, UMIT TIROL - University for Health Sciences and Technology, Hall in Tirol, Austria.
- Institute for Technology Assessment, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
- Division of Health Technology Assessment and Bioinformatics, ONCOTYROL - Center for Personalized Cancer Medicine, Innsbruck, Austria.
- Center for Health Decision Science, Departments of Epidemiology and Health Policy & Management, Harvard T. H. Chan School of Public Health, Boston, USA.
| |
Collapse
|
22
|
Shen H, Sun Y, Qian J, Wu J, Zhong X, Li G, Li W. Low-residue diet with oral nutritional supplements prior to colonoscopy improves the quality of bowel preparation: an endoscopist-blinded, randomized controlled trial. BMC Gastroenterol 2025; 25:166. [PMID: 40075287 PMCID: PMC11900647 DOI: 10.1186/s12876-025-03751-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/14/2024] [Accepted: 03/03/2025] [Indexed: 03/14/2025] Open
Abstract
BACKGROUND Poor bowel preparation has been a great problem of endoscopists for a long time. Low-residue diet (LRD) is often recommended on the day before colonoscopy. However, the quality of bowel preparation with LRD alone is suboptimal. The aim of our study was to examine whether patients who consumed LRD with oral nutritional supplements (ONSs) had higher quality of bowel preparation than patients who consumed LRD alone before colonoscopy. METHODS An endoscopist-blinded, randomized controlled trial was conducted in inpatients who scheduled for colonoscopy with sedation. Patients were randomized to the non-ONS group and the ONS group. The primary outcomes were the rates of adequate bowel preparation measured by the Boston Bowel Preparation Scale (BBPS), the Ottawa Bowel Preparation Scale (OBPS) and the Colon Endoscopic Bubble Scale (CEBuS). The secondary outcomes were the adenoma detection rate (ADR), polyp detection rate (PDR), intubation time, withdrawal time and rates of adverse events. RESULTS In both groups, 100 patients were analyzed. The rates of adequate bowel preparation measured by the BBPS and OBPS and PDR were significantly higher in the ONS group than in the non-ONS group (all P < 0.05). However, no significant differences were observed in the CEBuS scores, ADR, intubation time and rates of adverse events between the two groups (all P > 0.05). The withdrawal time was longer in the non-ONS group than the in the ONS group (P < 0.05). CONCLUSIONS LRD with ONSs helps increase the quality of bowel preparation. To help with colorectal cancer (CRC) screening, further studies are warrant. TRIAL REGISTRATION [Chinese Clinical Trial Registry], [ChiCTR2400091660], [31/10/2024], [Retrospectively registered].
Collapse
Affiliation(s)
- Huilin Shen
- Department of Geriatrics, Affiliated Hospital of Hangzhou Normal University, Hangzhou, Zhejiang, China
| | - Yijie Sun
- Department of Gastroenterology, Affiliated Hospital of Hangzhou Normal University, No. 126 Wenzhou Road, Gongshu District, Hangzhou, Zhejiang, 310015, China
| | - Jin Qian
- Department of Gastroenterology, Affiliated Hospital of Hangzhou Normal University, No. 126 Wenzhou Road, Gongshu District, Hangzhou, Zhejiang, 310015, China
| | - Jiaqi Wu
- Department of Gastroenterology, Affiliated Hospital of Hangzhou Normal University, No. 126 Wenzhou Road, Gongshu District, Hangzhou, Zhejiang, 310015, China
| | - Xueqing Zhong
- Department of Gastroenterology, Affiliated Hospital of Hangzhou Normal University, No. 126 Wenzhou Road, Gongshu District, Hangzhou, Zhejiang, 310015, China
| | - Guodong Li
- Department of Gastroenterology, Affiliated Hospital of Hangzhou Normal University, No. 126 Wenzhou Road, Gongshu District, Hangzhou, Zhejiang, 310015, China
| | - Weimin Li
- Department of Gastroenterology, Affiliated Hospital of Hangzhou Normal University, No. 126 Wenzhou Road, Gongshu District, Hangzhou, Zhejiang, 310015, China.
| |
Collapse
|
23
|
Hassan C, Bisschops R, Sharma P, Mori Y. Colon Cancer Screening, Surveillance, and Treatment: Novel Artificial Intelligence Driving Strategies in the Management of Colon Lesions. Gastroenterology 2025:S0016-5085(25)00478-0. [PMID: 40054749 DOI: 10.1053/j.gastro.2025.02.021] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/19/2024] [Revised: 02/09/2025] [Accepted: 02/15/2025] [Indexed: 03/25/2025]
Abstract
Colonoscopy, a crucial procedure for detecting and removing colorectal polyps, has seen transformative advancements through the integration of artificial intelligence, specifically in computer-aided detection (CADe) and diagnosis (CADx). These tools enhance real-time detection and characterization of lesions, potentially reducing human error, and standardizing the quality of colonoscopy across endoscopists. CADe has proven effective in increasing adenoma detection rate, potentially reducing long-term colorectal cancer incidence. However, CADe's benefits are accompanied by challenges, such as potentially longer procedure times, increased non-neoplastic polyp resections, and a higher surveillance burden. CADx, although promising in differentiating neoplastic and non-neoplastic diminutive polyps, encounters limitations in accuracy, particularly in the proximal colon. Real-world data also revealed gaps between trial efficacy and practical outcomes, emphasizing the need for further research in uncontrolled settings. Moreover, CADx limited specificity and binary output underscore the necessity for explainable artificial intelligence to gain endoscopists' trust. This review aimed to explore the benefits, harms, and limitations of artificial intelligence for colon cancer screening, surveillance, and treatment focusing on CADe and CADx systems for lesion detection and characterization, respectively, while addressing challenges in integrating these technologies into clinical practice.
Collapse
Affiliation(s)
- Cesare Hassan
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy; Department of Gastroenterology, Istituto di Ricovero e Cura a Carattere Scientifico, Humanitas Research Hospital, Rozzano, Italy.
| | - Raf Bisschops
- Department of Gastroenterology and Hepatology, University Hospitals Leuven, Leuven, Belgium; Translational Research Center in Gastrointestinal Disorders, Katholieke Universiteit Leuven, Leuven, Belgium
| | - Prateek Sharma
- Department of Gastroenterology and Hepatology, Kansas City Veterans Affairs Medical Center, Kansas City, Missouri
| | - Yuichi Mori
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan; Clinical Effectiveness Research Group, University of Oslo, Oslo, Norway; Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway
| |
Collapse
|
24
|
Zhang C, Tao X, Pan J, Huang L, Dong Z, Lin J, Su H, Zhu Y, Du H, Xiao B, Chen M, Wu L, Yu H. The Effect of Computer-Aided Device on Adenoma Detection Rate in Different Implement Scenarios: A Real-World Study. J Gastroenterol Hepatol 2025; 40:692-705. [PMID: 39663912 DOI: 10.1111/jgh.16847] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/05/2024] [Revised: 11/11/2024] [Accepted: 11/24/2024] [Indexed: 12/13/2024]
Abstract
BACKGROUND Several recent studies have found that the efficacy of computer-aided polyp detection (CADe) on the adenoma detection rate (ADR) diminished in real-world settings. The role of unmeasured factors in AI-human interaction, such as monitor approaches, remains unknown. This study aimed to validate the effectiveness of CADe in the real world and assess the impact of monitor approaches. METHODS A retrospective propensity score-matched cohort study was conducted using routine data from a tertiary endoscopy center in China before and after the implementation of CADe. Four propensity score-matched cohorts were established: Cohort 1: pre-CADe matched with dual-monitor CADe-assisted group; Cohort 2: dual-monitor CADe-assisted with single-monitor CADe-assisted group; Cohort 3: pre-CADe with single-monitor CADe-assisted group; and Cohort 4: pre-CADe with CADe period. ADR was set as the primary outcome. RESULTS There were 5390, 6083, and 6131 eligible patients in the pre-CADe group, dual-monitor group, and single-monitor group, respectively. In the matched analysis, results indicated that regardless of the monitor setup, CADe-assisted groups showed a trend of increased ADR compared with the pre-CADe period (CADe period: OR 1.141, 95% CI 1.047-1.243; p = 0.003; dual-monitor: OR 1.178, 95% CI 1.069-1.299, p = 0.001; single-monitor: OR 1.094, 95% CI 0.998-1.200, p = 0.056). Moreover, no significant difference between different monitor approaches was observed, although dual-monitor setup showed an increasing tendency on ADR compared with single-monitor setup (OR 1.069, 95% CI 0.985-1.161, p = 0.109). CONCLUSION CADe shows great potential to improve ADR during colonoscopy in the real world. Meanwhile, changes in monitor setup do not significantly impact the assistance capability of CADe. Further research dedicated to evaluating the unmeasured elements in the AI-clinician hybrid for better implementation of CADe would be beneficial.
Collapse
Affiliation(s)
- Chenxia Zhang
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Xiao Tao
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Jie Pan
- Department of Gastroenterology, Wenzhou Central Hospital, Wenzhou, Zhejiang Province, China
- Department of Gastroenterology, The Dingli Clinical College of Wenzhou Medical University, Wenzhou, Zhejiang Province, China
- Department of Gastroenterology, The Second Affiliated Hospital of Shanghai University, Wenzhou, Zhejiang Province, China
| | - Li Huang
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Zehua Dong
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Jiejun Lin
- Department of Gastroenterology, Wenzhou Central Hospital, Wenzhou, Zhejiang Province, China
- Department of Gastroenterology, The Dingli Clinical College of Wenzhou Medical University, Wenzhou, Zhejiang Province, China
- Department of Gastroenterology, The Second Affiliated Hospital of Shanghai University, Wenzhou, Zhejiang Province, China
| | - Huang Su
- Department of Gastroenterology, Wenzhou Central Hospital, Wenzhou, Zhejiang Province, China
- Department of Gastroenterology, The Dingli Clinical College of Wenzhou Medical University, Wenzhou, Zhejiang Province, China
- Department of Gastroenterology, The Second Affiliated Hospital of Shanghai University, Wenzhou, Zhejiang Province, China
| | - Yijie Zhu
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Hongliu Du
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Bing Xiao
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Mingkai Chen
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Lianlian Wu
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| | - Honggang Yu
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
- Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China
- Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China
| |
Collapse
|
25
|
Cold KM, Vamadevan A, Heen A, Vilmann AS, Rasmussen M, Konge L, Svendsen MBS. Is the Transverse Colon Overlooked? Establishing a Comprehensive Colonoscopy Database from a Multicenter Cluster-Randomized Controlled Trial. Diagnostics (Basel) 2025; 15:591. [PMID: 40075838 PMCID: PMC11898687 DOI: 10.3390/diagnostics15050591] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2024] [Revised: 02/21/2025] [Accepted: 02/25/2025] [Indexed: 03/14/2025] Open
Abstract
Background and Study Aim: Colonoscopy holds the highest volume of all endoscopic procedures, allowing for large colonoscopy databases to serve as valuable datasets for quality assurance. We aimed to build a comprehensive colonoscopy database for quality assurance and the training of future AIs. Materials and Methods: As part of a cluster-randomized controlled trial, a designated, onsite medical student was used to acquire procedural and patient-specific data, ensuring a high level of data integrity. The following data were thereby collected for all colonoscopies: full colonoscopy vides, colonoscope position (XYZ-coordinates), intraprocedural timestamps, pathological report, endoscopist description, endoscopist planning, and patient-reported discomfort. Results: A total of 1447 patients were included from the 1st of February 2022 to the 21st of November 2023; 1191 colonoscopies were registered as completed, 88 were stopped due to inadequate bowel cleansing, and 41 were stopped due to patient discomfort. Of the 1191 completed colonoscopies, 601 contained polypectomies (50.4%), and 590 did not (49.6%). Comparing colonoscopies with polypectomies to those without the withdrawal time (caecum to extubating the scope) was significantly longer for all parts of the colon (p values < 0.001), except the transverse colon (p value = 0.92). The database was used to train an AI, automatically and objectively evaluating bowel preparation. Conclusions: We established the most thorough database in colonoscopy with previously inaccessible information, indicating that the transverse colon differs from the other parts of the colon in terms of withdrawal time for procedures with polypectomies. To further explore these findings and reach the full potential of the database, an AI evaluating bowel preparation was developed. Several research partners have been identified to collaborate in the development of future AIs.
Collapse
Affiliation(s)
- Kristoffer Mazanti Cold
- Copenhagen Academy for Medical Education and Simulation (CAMES) Rigshospitalet, Capital Region of Denmark, 2100 Copenhagen, Denmark; (K.M.C.); (A.V.); (A.H.); (A.S.V.); (L.K.)
- Faculty of Health Sciences, University of Copenhagen, 2200 Copenhagen, Denmark
| | - Anishan Vamadevan
- Copenhagen Academy for Medical Education and Simulation (CAMES) Rigshospitalet, Capital Region of Denmark, 2100 Copenhagen, Denmark; (K.M.C.); (A.V.); (A.H.); (A.S.V.); (L.K.)
| | - Amihai Heen
- Copenhagen Academy for Medical Education and Simulation (CAMES) Rigshospitalet, Capital Region of Denmark, 2100 Copenhagen, Denmark; (K.M.C.); (A.V.); (A.H.); (A.S.V.); (L.K.)
| | - Andreas Slot Vilmann
- Copenhagen Academy for Medical Education and Simulation (CAMES) Rigshospitalet, Capital Region of Denmark, 2100 Copenhagen, Denmark; (K.M.C.); (A.V.); (A.H.); (A.S.V.); (L.K.)
- Department of Gastrointestinal and Hepatic Diseases, Copenhagen University Hospital—Herlev and Gentofte, 2730 Herlev, Denmark
| | - Morten Rasmussen
- Danish Colorectal Cancer Screening Database (DCCSD) Steering Committee, 8200 Aarhus, Denmark;
- Bispebjerg University Hospital, 2400 Copenhagen, Denmark
| | - Lars Konge
- Copenhagen Academy for Medical Education and Simulation (CAMES) Rigshospitalet, Capital Region of Denmark, 2100 Copenhagen, Denmark; (K.M.C.); (A.V.); (A.H.); (A.S.V.); (L.K.)
- Faculty of Health Sciences, University of Copenhagen, 2200 Copenhagen, Denmark
| | - Morten Bo Søndergaard Svendsen
- Copenhagen Academy for Medical Education and Simulation (CAMES) Rigshospitalet, Capital Region of Denmark, 2100 Copenhagen, Denmark; (K.M.C.); (A.V.); (A.H.); (A.S.V.); (L.K.)
- Department of Computer Science, Faculty of Science, University of Copenhagen, 2200 Copenhagen, Denmark
| |
Collapse
|
26
|
Spadaccini M, Menini M, Massimi D, Rizkala T, De Sire R, Alfarone L, Capogreco A, Colombo M, Maselli R, Fugazza A, Brandaleone L, Di Martino A, Ramai D, Repici A, Hassan C. AI and Polyp Detection During Colonoscopy. Cancers (Basel) 2025; 17:797. [PMID: 40075645 PMCID: PMC11898786 DOI: 10.3390/cancers17050797] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2025] [Revised: 02/18/2025] [Accepted: 02/24/2025] [Indexed: 03/14/2025] Open
Abstract
Colorectal cancer (CRC) prevention depends on effective colonoscopy; yet variability in adenoma detection rates (ADRs) and missed lesions remain significant hurdles. Artificial intelligence-powered computer-aided detection (CADe) systems offer promising advancements in enhancing polyp detection. This review examines the role of CADe in improving ADR and reducing adenoma miss rates (AMRs) while addressing its broader clinical implications. CADe has demonstrated consistent improvements in ADRs and AMRs; largely by detecting diminutive polyps, but shows limited efficacy in identifying advanced adenomas or sessile serrated lesions. Challenges such as operator deskilling and the need for enhanced algorithms persist. Combining CADe with adjunctive techniques has shown potential for further optimizing performance. While CADe has standardized detection quality; its long-term impact on CRC incidence and mortality remains inconclusive. Future research should focus on refining CADe technology and assessing its effectiveness in reducing the global burden of CRC.
Collapse
Affiliation(s)
- Marco Spadaccini
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Maddalena Menini
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Davide Massimi
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Tommy Rizkala
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Roberto De Sire
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Ludovico Alfarone
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Antonio Capogreco
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Matteo Colombo
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Roberta Maselli
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Alessandro Fugazza
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Luca Brandaleone
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Antonio Di Martino
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Daryl Ramai
- Division of Gastroenterology and Hepatology, University of Utah, Salt Lake City, UT 84112, USA
| | - Alessandro Repici
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| | - Cesare Hassan
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy; (M.S.); (M.M.); (L.B.); (C.H.)
- Department of Gastroneterology, IRCCS Humanitas Research Hospital, Via Alessandro Manzoni 56, Rozzano, 20089 Milan, Italy (R.D.S.)
| |
Collapse
|
27
|
Lagström RMB, Bräuner KB, Bielik J, Rosen AW, Crone JG, Gögenur I, Bulut M. Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial. Endosc Int Open 2025; 13:a25215169. [PMID: 40018072 PMCID: PMC11866038 DOI: 10.1055/a-2521-5169] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/04/2024] [Accepted: 01/15/2025] [Indexed: 03/01/2025] Open
Abstract
Background and study aims Adenoma detection rate (ADR) is a key performance measure with variability among endoscopists. Artificial intelligence (AI) in colonoscopy could reduce this variability and has shown to improve ADR. This study assessed the impact of AI on ADR among Danish endoscopists of varying experience levels. Patients and methods We conducted a prospective, quasi-randomized, controlled, multicenter trial involving patients aged 18 and older undergoing screening, surveillance, and diagnostic colonoscopy at four centers. Participants were assigned to AI-assisted colonoscopy (GI Genius, Medtronic) or conventional colonoscopy. Endoscopists were classified as experts (> 1000 colonoscopies) or non-experts (≤ 1000 colonoscopies). The primary outcome was ADR. We performed a subgroup analysis stratified on endoscopist experience and a subset analysis of the screening population. Results A total of 795 patients were analyzed: 400 in the AI group and 395 in the control group. The AI group demonstrated a significantly higher ADR than the control group (59.1% vs. 46.6%, P < 0.001). The increase was significant among experts (59.9% vs. 47.3%, P < 0.002) but not among non-experts. AI assistance significantly improved ADR (74.4% vs. 58.1%, P = 0.003) in screening colonoscopies. Polyp detection rate (PDR) was also higher in the AI group (69.8% vs. 56.2%, P < 0.001). There was no significant difference in the non-neoplastic resection rate (NNRR) (15.1% vs. 17.1%, P = 0.542). Conclusions AI-assisted colonoscopy significantly increased ADR by 12.5% overall, with a notable 16.3% increase in the screening population. The unchanged NNRR indicates that the higher PDR was due to increased ADR, not unnecessary resections.
Collapse
Affiliation(s)
| | - Karoline Bendix Bräuner
- Department of Surgery, Zealand University Hospital Koge, Køge, Denmark
- Department of Surgery, Slagelse Hospital, Slagelse, Denmark
| | - Julia Bielik
- Department of Surgery, Holbæk Sygehus, Holbæk, Denmark
| | | | | | - Ismail Gögenur
- Department of Surgery, Zealand University Hospital Koge, Køge, Denmark
- Department of Clinical Medicine, University of Copenhagen Faculty of Health and Medical Sciences, Copenhagen, Denmark
| | - Mustafa Bulut
- Department of Surgery, Zealand University Hospital Koge, Køge, Denmark
- Department of Clinical Medicine, University of Copenhagen Faculty of Health and Medical Sciences, Copenhagen, Denmark
- Copenhagen Academy for Medical Education and Simulation (CAMES), Copenhagen, Denmark
| |
Collapse
|
28
|
Davila-Piñón P, Pedrido T, Díez-Martín AI, Herrero J, Puga M, Rivas L, Sánchez E, Zarraquiños S, Pin N, Vega P, Soto S, Remedios D, Domínguez-Carbajales R, Fdez-Riverola F, Nogueira-Rodríguez A, Glez-Peña D, Reboiro-Jato M, López-Fernández H, Cubiella J. PolyDeep Advance 1: Clinical Validation of a Computer-Aided Detection System for Colorectal Polyp Detection with a Second Observer Design. Diagnostics (Basel) 2025; 15:458. [PMID: 40002609 PMCID: PMC11854325 DOI: 10.3390/diagnostics15040458] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2024] [Revised: 02/05/2025] [Accepted: 02/11/2025] [Indexed: 02/27/2025] Open
Abstract
Background: PolyDeep is a computer-aided detection and characterization system that has demonstrated a high diagnostic yield for in vitro detection of colorectal polyps. Our objective is to compare the diagnostic performance of expert endoscopists and PolyDeep for colorectal polyp detection. Methods: PolyDeep Advance 1 (NCT05514301) is an unicentric diagnostic test study with a second observer design. Endoscopists performed colonoscopy blinded to PolyDeep's detection results. The main endpoint was the sensitivity for colorectal polyp (adenoma, serrated or hyperplastic lesion) detection. The secondary endpoints were the diagnostic performance for diminutive lesions (≤5 mm), neoplasia (adenoma, serrated lesion) and adenoma detection. Results: We included 205 patients (55.1% male, 63.0 ± 6.2 years of age) referred to colonoscopy (positive faecal immunochemical occult blood test = 60.5%, surveillance colonoscopy = 39.5%). We excluded eight patients due to incomplete colonoscopy. Endoscopists detected 384 lesions, of which 39 were not detected by PolyDeep. In contrast, PolyDeep predicted 410 possible additional lesions, 26 of these predictions confirmed by endoscopists as lesions, resulting in a potential 6.8% detection increase with respect to the 384 lesions detected by the endoscopists. In total, 410 lesions were detected, 20 were not retrieved, five were colorectal adenocarcinoma, 343 were colorectal polyps (231 adenomas, 39 serrated and 73 hyperplastic polyps), 42 were normal mucosa and 289 were ≤5 mm. We did not find statistically significant differences between endoscopists and PolyDeep for colorectal polyp detection (Sensitivity = 94.2%, 91.5%, p = 0.2; Specificity = 9.5%, 14.3%, p = 0.7), diminutive lesions (Sensitivity = 92.3%, 89.5%, p = 0.4; Specificity = 9.8%, 14.6%, p = 0.7), neoplasia (Sensitivity = 95.2%, 92.9%, p = 0.3; Specificity = 9.6%, 13.9%, p = 0.4) and adenoma detection (Sensitivity = 94.4%, 92.6%, p = 0.5; Specificity = 7.2%, 11.8%, p = 0.2). Conclusions: Expert endoscopists and PolyDeep have similar diagnostic performance for colorectal polyp detection.
Collapse
Grants
- DPI2017-87494-R MICIU/AEI/10.13039/501100011033 ERDF A way of making Europe
- PDC2021-121644-I00 by MICIU/AEI/10.13039/501100011033 European Union NextGenerationEU/PRTR
- PI21/01771 Instituto de Salud Carlos III, Madrid, Spain
- CD22/00087 Instituto de Salud Carlos III, Madrid, Spain
- INT22/00009 Instituto de Salud Carlos III, Madrid, Spain
- FI22/00203 Instituto de Salud Carlos III, Madrid, Spain
- ED431G 2019/06 Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia)
- ED431C 2022/03-GRC Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia)
- ED481B-2023-005 Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia)
- ED431G 2019/06 ERDF A way of making Europe
- ED431C 2022/03-GRC ERDF A way of making Europe
- ED481B-2023-005 ERDF A way of making Europe
- 2022 Grant of Oncology-Tamarite- Spanish Association of Gastroenterology
Collapse
Affiliation(s)
- Pedro Davila-Piñón
- Research Group in Gastrointestinal Oncology Ourense (REGGIOu), Hospital Universitario de Ourense, 32005 Ourense, Spain; (P.D.-P.); (T.P.); (A.I.D.-M.)
- Fundación Pública Galega de Investigación Biomédica Galicia Sur, Hospital Universitario de Ourense, SERGAS, 32005 Ourense, Spain
| | - Teresa Pedrido
- Research Group in Gastrointestinal Oncology Ourense (REGGIOu), Hospital Universitario de Ourense, 32005 Ourense, Spain; (P.D.-P.); (T.P.); (A.I.D.-M.)
| | - Astrid Irene Díez-Martín
- Research Group in Gastrointestinal Oncology Ourense (REGGIOu), Hospital Universitario de Ourense, 32005 Ourense, Spain; (P.D.-P.); (T.P.); (A.I.D.-M.)
- Fundación Pública Galega de Investigación Biomédica Galicia Sur, Hospital Universitario de Ourense, SERGAS, 32005 Ourense, Spain
| | - Jesús Herrero
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Manuel Puga
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Laura Rivas
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Eloy Sánchez
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Sara Zarraquiños
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Noel Pin
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Pablo Vega
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - Santiago Soto
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | - David Remedios
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| | | | - Florentino Fdez-Riverola
- Department of Computer Science, Escuela Superior de Ingenieria Informática (ESEI), CINBIO, University of Vigo, 32004 Ourense, Spain; (F.F.-R.); (A.N.-R.); (D.G.-P.); (M.R.-J.)
- Next Generation Computer Systems Group (SING) Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), 32004 Ourense, Spain
| | - Alba Nogueira-Rodríguez
- Department of Computer Science, Escuela Superior de Ingenieria Informática (ESEI), CINBIO, University of Vigo, 32004 Ourense, Spain; (F.F.-R.); (A.N.-R.); (D.G.-P.); (M.R.-J.)
- Next Generation Computer Systems Group (SING) Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), 32004 Ourense, Spain
- Instituto de Investigação e Inovação em Saúde (i3S), Universidade do Porto, Rua Alfredo Allen 208, 4200-135 Porto, Portugal
| | - Daniel Glez-Peña
- Department of Computer Science, Escuela Superior de Ingenieria Informática (ESEI), CINBIO, University of Vigo, 32004 Ourense, Spain; (F.F.-R.); (A.N.-R.); (D.G.-P.); (M.R.-J.)
- Next Generation Computer Systems Group (SING) Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), 32004 Ourense, Spain
| | - Miguel Reboiro-Jato
- Department of Computer Science, Escuela Superior de Ingenieria Informática (ESEI), CINBIO, University of Vigo, 32004 Ourense, Spain; (F.F.-R.); (A.N.-R.); (D.G.-P.); (M.R.-J.)
- Next Generation Computer Systems Group (SING) Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), 32004 Ourense, Spain
| | - Hugo López-Fernández
- Department of Computer Science, Escuela Superior de Ingenieria Informática (ESEI), CINBIO, University of Vigo, 32004 Ourense, Spain; (F.F.-R.); (A.N.-R.); (D.G.-P.); (M.R.-J.)
- Next Generation Computer Systems Group (SING) Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), 32004 Ourense, Spain
| | - Joaquín Cubiella
- Research Group in Gastrointestinal Oncology Ourense (REGGIOu), Hospital Universitario de Ourense, 32005 Ourense, Spain; (P.D.-P.); (T.P.); (A.I.D.-M.)
- Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain; (J.H.); (M.P.); (L.R.); (E.S.); (S.Z.); (N.P.); (P.V.); (S.S.); (D.R.)
| |
Collapse
|
29
|
Spadaccini M, Hassan C, Mori Y, Massimi D, Correale L, Facciorusso A, Patel HK, Rizkala T, Khalaf K, Ramai D, Rondonotti E, Maselli R, Rex DK, Bhandari P, Sharma P, Repici A. Variability in computer-aided detection effect on adenoma detection rate in randomized controlled trials: A meta-regression analysis. Dig Liver Dis 2025:S1590-8658(25)00205-1. [PMID: 39924430 DOI: 10.1016/j.dld.2025.01.192] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/25/2024] [Revised: 12/16/2024] [Accepted: 01/21/2025] [Indexed: 02/11/2025]
Abstract
BACKGROUND Computer-aided detection (CADe) systems may increase adenoma detection rate (ADR) during colonoscopy. However, the variable results of CADe effects in different RCTs warrant investigation into factors influencing these results. AIMS Investigate the different variables possibly affecting the impact of CADe-assisted colonoscopy and its effect on ADR. METHODS We searched MEDLINE, EMBASE, and Scopus databases until July 2023 for RCTs reporting performance of CADe systems in the detection of colorectal neoplasia. The main outcome was pooled ADR. A random-effects meta-analysis was performed to obtain the pooled risk ratios (RR) with 95 % confidence intervals (CI)). To explore sources of heterogeneity, we conducted a meta-regression analysis using both univariable and multivariable mixed-effects models. Potential explanatory variables included factors influencing adenoma prevalence, such as patient gender, age, and colonoscopy indication. We also included both key (ADR), and minor (Withdrawal time) performance measures considered as quality indicators for colonoscopy. RESULTS Twenty-three randomized controlled trials (RCTs) on 19,077 patients were include. ADR was higher in the CADe group (46 % [95 % CI 39-52]) than in the standard colonoscopy group (38 % [95 % CI 31-46]) with a risk ratio of 1.22 [95 % CI 1.14-1.29]); and a substantial level of heterogeneity (I2 = 67.69 %). In the univariable meta-regression analysis, patient age, ADR in control arms, and withdrawal time were the strongest predictors of CADe effect on ADR (P < .001). In multivariable meta-regression, ADR in control arms, and withdrawal time were simultaneous significant predictors of the proportion of the CADe effect on ADR. CONCLUSION The substantial level of heterogeneity found appeared to be associated with variability in colonoscopy quality performances across the studies, namely ADR in control arm, and withdrawal time.
Collapse
Affiliation(s)
- Marco Spadaccini
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy; Humanitas Clinical and Research Center -IRCCS-, Endoscopy Unit, Rozzano, Italy.
| | - Cesare Hassan
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy; Humanitas Clinical and Research Center -IRCCS-, Endoscopy Unit, Rozzano, Italy
| | - Yuichi Mori
- University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway; Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
| | - Davide Massimi
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy; Humanitas Clinical and Research Center -IRCCS-, Endoscopy Unit, Rozzano, Italy
| | - Loredana Correale
- Humanitas Clinical and Research Center -IRCCS-, Endoscopy Unit, Rozzano, Italy
| | - Antonio Facciorusso
- University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway; University of Salento, Gastroenterology Unit, Department of Experimental Medicine, Lecce, Italy
| | - Harsh K Patel
- Kansas City VA Medical Center, Gastroenterology and Hepatology, Kansas City, United States
| | - Tommy Rizkala
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy
| | - Kareem Khalaf
- St. Michael's Hospital, University of Toronto, Division of Gastroenterology, Toronto, Ontario, Canada
| | - Daryl Ramai
- University of Utah Health, Gastroenterology and Hepatology, Salt Lake City, UT, USA
| | | | - Roberta Maselli
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy; Humanitas Clinical and Research Center -IRCCS-, Endoscopy Unit, Rozzano, Italy
| | - Douglas K Rex
- Indiana University School of Medicine, Division of Gastroenterology, Indianapolis, Indiana, USA
| | - Pradeep Bhandari
- Queen Alexandra Hospital, Department of Gastroenterology, Portsmouth, UK
| | - Prateek Sharma
- Kansas City VA Medical Center, Gastroenterology and Hepatology, Kansas City, United States
| | - Alessandro Repici
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy; Humanitas Clinical and Research Center -IRCCS-, Endoscopy Unit, Rozzano, Italy
| |
Collapse
|
30
|
Ishibashi F, Suzuki S. Practical utility of linked color imaging in colonoscopy: Updated literature review. Dig Endosc 2025; 37:147-156. [PMID: 39253814 DOI: 10.1111/den.14915] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/12/2024] [Accepted: 08/13/2024] [Indexed: 09/11/2024]
Abstract
The remarkable recent developments in image-enhanced endoscopy (IEE) have significantly contributed to the advancement of diagnostic techniques. Linked color imaging (LCI) is an IEE technique in which color differences are expanded by processing image data to enhance short-wavelength narrow-band light. This feature of LCI causes reddish areas to appear redder and whitish areas to appear whiter. Because most colorectal lesions, such as neoplastic and inflammatory lesions, have a reddish tone, LCI is an effective tool for identifying colorectal lesions by clarifying the redder areas and distinguishing them from the surrounding normal mucosa. To date, eight randomized controlled trials have been conducted to evaluate the effectiveness of LCI in identifying colorectal adenomatous lesions. The results of a meta-analysis integrating these studies demonstrated that LCI was superior to white-light endoscopy for detecting colorectal adenomatous lesions. LCI also improves the detection of serrated lesions by enhancing their whiteness. Furthermore, accumulating evidence suggests that LCI is superior to white-light endoscopy for the diagnosis of the colonic mucosa in patients with ulcerative colitis. In this review, based on a comprehensive search of the current literature since the implementation of LCI, the utility of LCI in the detection and diagnosis of colorectal lesions is discussed. Additionally, the latest data, including attempts to combine artificial intelligence and LCI, are presented.
Collapse
Affiliation(s)
- Fumiaki Ishibashi
- Department of Gastroenterology, International University of Health and Welfare Ichikawa Hospital, Chiba, Japan
| | - Sho Suzuki
- Department of Gastroenterology, International University of Health and Welfare Ichikawa Hospital, Chiba, Japan
| |
Collapse
|
31
|
Wu J, Zhang Q, Li X, Bai T, Hou X, Li G, Song J. The Effect of the Second Forward View on the Detection Rate of Sessile Serrated Lesions in the Proximal Colon: A Single-Center Prospective Randomized Controlled Study. Clin Transl Gastroenterol 2025; 16:e00805. [PMID: 39688959 PMCID: PMC11845190 DOI: 10.14309/ctg.0000000000000805] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/05/2024] [Accepted: 12/06/2024] [Indexed: 12/19/2024] Open
Abstract
INTRODUCTION The detection rate of proximal sessile serrated lesion (PSSLDR) is linked to the incidence and mortality of colorectal cancer. However, research on second forward view (SFV) examinations for PSSLDR remains limited. This first randomized controlled trial assessed the impact of the proximal SFV on the PSSLDR. METHODS Patients were randomized into 2 groups during proximal colonoscopy: standard colonoscopy (SC) and SFV. The SC group underwent a standard examination, whereas the SFV group underwent a second examination of the proximal colon (cecum to splenic flexure). The primary outcome was PSSLDR, with secondary outcomes, including the proximal polyp detection rate (PPDR), proximal adenoma detection rate (PADR), and lesion miss rate, compared between the 2 groups. RESULTS Among 246 patients (SC = 124; SFV = 122), SFV significantly improved the PSSLDR by 7.4% compared with SC (9.8% vs 2.4%, P = 0.017). SFV increased the PPDR by 20.2% (55.7% vs 35.5%, P = 0.002) and PADR by 12.7% (37.7% vs 25%, P = 0.039). Multivariate analysis revealed that sessile serrated lesions (odds ratio [OR] = 7.70, 95% confidence interval [CI] [1.58, 37.59]), inflammatory polyps (OR = 4.24, 95% CI [1.73, 10.39]), and lesion size (OR = 0.76, 95% CI [0.60, 0.96]) were associated with proximal missed lesions. The overall polyp miss rate was 52.9%, with miss rates of 61.0% for polyps <5 mm, 80% for sessile serrated lesions, and 42.2% for adenomas. Furthermore, 12.3% of patients experienced changes in surveillance intervals from SFV examination. DISCUSSION SFV examination of the proximal colon significantly improved the PSSLDR by 7.4%, PPDR by 20.2%, and PADR by 12.7%, while shortening the detection interval by 12.3%, making it a valuable and cost-effective addition to routine colonoscopy.
Collapse
Affiliation(s)
- Jiandi Wu
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Qingqing Zhang
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xueyan Li
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Tao Bai
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaohua Hou
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Gangping Li
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jun Song
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|
32
|
Duan C, Sheng J, Ma X. Innovative approaches in colorectal cancer screening: advances in detection methods and the role of artificial intelligence. Therap Adv Gastroenterol 2025; 18:17562848251314829. [PMID: 39898356 PMCID: PMC11783499 DOI: 10.1177/17562848251314829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/21/2024] [Accepted: 01/06/2025] [Indexed: 02/04/2025] Open
Abstract
Colorectal cancer (CRC) is the third most prevalent cancer globally and poses a significant health threat, making early detection crucial. This review paper explored emerging detection methods for early screening of CRC, including gut microbiota, metabolites, genetic markers, and artificial intelligence (AI)-based technologies. Current screening methods have their respective advantages and limitations, particularly in detecting precursors. First, the importance of the gut microbiome in CRC progression is discussed, highlighting how specific microbial alterations can serve as biomarkers for early detection, potentially enhancing diagnostic accuracy when combined with traditional screening methods. Next, research on metabolic reprogramming illustrates the relationship between metabolic changes and CRC, with studies developing metabolite-based detection models that show good sensitivity for early diagnosis. In terms of genetic markers, methylated DNA markers like SEPTIN9 have demonstrated high sensitivity, although further validation across diverse populations is necessary. Lastly, AI technology has shown immense potential in improving adenoma detection rates, significantly enhancing the quality of colonoscopic examinations through image recognition techniques. This review aims to provide a comprehensive perspective on new strategies for CRC screening, emphasizing the potential of noninvasive detection technologies and the prospects of AI and genomics in clinical applications. Despite several challenges, this review advocates for future large-scale prospective studies to validate the effectiveness and cost-effectiveness of these new screening methods while promoting the implementation of screening protocols tailored to individual characteristics.
Collapse
Affiliation(s)
- Changwei Duan
- Medical School of Chinese PLA, Beijing, China Senior Department of Gastroenterology, The First Medical Center of Chinese PLA General Hospital, Beijing, China
- Department of Gastroenterology, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China
| | - Jianqiu Sheng
- Medical School of Chinese PLA, Beijing 100853, China Senior Department of Gastroenterology, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, China
- Department of Gastroenterology, The Seventh Medical Center of Chinese PLA General Hospital, No. 5 Nanmencang, Beijing 100700, China
| | - Xianzong Ma
- Senior Department of Gastroenterology, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, China
- Department of Gastroenterology, The Seventh Medical Center of Chinese PLA General Hospital, No. 28 Fuxing Road, Beijing 100700, China
| |
Collapse
|
33
|
Yin K, Liang H, Guo W, Chen YX, Cui ML, Zhang MX. Artificial intelligence and early cancer of the digestive tract: New challenges and new futures. Shijie Huaren Xiaohua Zazhi 2025; 33:1-10. [DOI: 10.11569/wcjd.v33.i1.1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/14/2024] [Revised: 11/06/2024] [Accepted: 11/21/2024] [Indexed: 01/22/2025] Open
Abstract
Early gastrointestinal tumors have a good prognosis, but they have insidious onset and no specific manifestations, making their diagnosis difficult. With the rapid development of artificial intelligence technology in the medical field, it has shown great potential in clinical work such as diagnosis and prognosis prediction of early gastrointestinal cancer. In this paper, we systematically review the relevant studies on AI in early esophageal cancer, early gastric cancer, early colon cancer, and hepatobiliary pancreatic cancer, and discuss the challenges and futures of AI application in early gastrointestinal cancer.
Collapse
Affiliation(s)
- Kun Yin
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Hao Liang
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Wen Guo
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Ya-Xin Chen
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Man-Li Cui
- Department of Gastroenterology, First Affiliated Hospital of Xi'an Medical College, Xi'an 710077, Shaanxi Province, China
| | - Ming-Xin Zhang
- Department of Gastroenterology, First Affiliated Hospital of Xi'an Medical College, Xi'an 710077, Shaanxi Province, China
| |
Collapse
|
34
|
Morimoto S, Tanaka H, Takehara Y, Yamamoto N, Tanino F, Kamigaichi Y, Yamashita K, Takigawa H, Urabe Y, Kuwai T, Oka S. Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study. J Anus Rectum Colon 2025; 9:127-133. [PMID: 39882234 PMCID: PMC11772792 DOI: 10.23922/jarc.2024-055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/28/2024] [Accepted: 10/26/2024] [Indexed: 01/31/2025] Open
Abstract
Objectives Studies have suggested that computer-aided polyp detection using artificial intelligence improves adenoma identification during colonoscopy. However, its real-world effectiveness remains unclear. Therefore, this study evaluated the usefulness of computer-aided detection during regular surveillance colonoscopy. Methods Consecutive patients who underwent surveillance colonoscopy with computer-aided detection between January and March 2023 and had undergone colonoscopy at least twice during the past 3 years were recruited. The clinicopathological findings of lesions identified using computer-aided detection were evaluated. The detection ability was sub-analyzed based on the expertise of the endoscopist and the presence of diminutive adenomas (size ≤5 mm). Results A total of 78 patients were included. Computer-aided detection identified 46 adenomas in 28 patients; however, no carcinomas were identified. The mean withdrawal time was 824 ± 353 s, and the mean tumor diameter was 3.3 mm (range, 2-8 mm). The most common gross type was 0-Is (70%), followed by 0-Isp (17%) and 0-IIa (13%). The most common tumor locations were the ascending colon and sigmoid colon (28%), followed by the transverse colon (26%), cecum (7%), descending colon (7%), and rectum (4%). Overall, 34.1% and 38.2% of patients with untreated diminutive adenomas and those with no adenomas, respectively, had newly detected adenomas. Endoscopist expertise did not affect the results. Conclusions Computer-aided detection may help identify adenomas during surveillance colonoscopy for patients with untreated diminutive adenomas and those with a history of endoscopic resection.
Collapse
Affiliation(s)
- Shin Morimoto
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Hidenori Tanaka
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Yudai Takehara
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Noriko Yamamoto
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Fumiaki Tanino
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Yuki Kamigaichi
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Ken Yamashita
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Hidehiko Takigawa
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Yuji Urabe
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Toshio Kuwai
- Gastrointestinal Endoscopy and Medicine, Hiroshima University Hospital, Hiroshima, Japan
| | - Shiro Oka
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| |
Collapse
|
35
|
Rex DK, Guardiola JJ, von Renteln D, Mori Y, Sharma P, Hassan C. Detection of large flat colorectal lesions by artificial intelligence: a persistent weakness and blind spot. Gut 2025:gutjnl-2024-334456. [PMID: 39773470 DOI: 10.1136/gutjnl-2024-334456] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/26/2024] [Accepted: 12/19/2024] [Indexed: 01/11/2025]
Affiliation(s)
- Douglas K Rex
- Division of Gastroenterology and Hepatology, Indiana University School of Medicine, Indianapolis, Indiana, USA
| | - John J Guardiola
- Division of Gastroenterology and Hepatology, Indiana University School of Medicine, Indianapolis, Indiana, USA
| | - Daniel von Renteln
- Division of Gastroenterology, Centre Hospitalier de L'Universite de Montreal, Montreal, Quebec, Canada
- Centre Hospitalier de l'Universite de Montreal Centre de Recherche, Montreal, Quebec, Canada
| | - Yuichi Mori
- Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan
| | - Prateek Sharma
- Department of Gastroenterology, Kansas City VA Medical Center, Kansas City, Missouri, USA
- The University of Kansas School of Medicine, Kansas City, Kansas, USA
| | - Cesare Hassan
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| |
Collapse
|
36
|
Mitev S, Saeed H, Rasheed CF, Abdullah A, Murvakov S, Sirakov V, Tchernodrinski S, Spassova Z. Texture and color enhancement imaging versus white light imaging for the detection of colorectal adenomas: Systematic review and meta-analysis. Endosc Int Open 2025; 13:a24749676. [PMID: 39958660 PMCID: PMC11827751 DOI: 10.1055/a-2474-9676] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/16/2024] [Accepted: 11/13/2024] [Indexed: 02/18/2025] Open
Abstract
Background and study aims Texture and color enhancement imaging (TXI) is a novel optical technology designed to improve visibility during endoscopy by highlighting subtle differences in morphology and color. This systematic review and meta-analysis aimed to determine whether TXI, compared with conventional white light imaging (WLI), can improve important colonoscopy quality indicators, specifically the adenoma detection rate (ADR) and adenomas per colonoscopy (APC). Patients and methods We searched PubMed, EMBASE, and the Cochrane Central for studies comparing TXI to WLI in patients undergoing colonoscopy for any indication. Risk ratios (RRs) and mean differences (MDs) were computed using a random-effects model. Results We included 1541 patients from three studies, of which two were randomized controlled trials (RCTs). TXI was used in 775 patients (50.3%). Indications for colonoscopy varied, including positive fecal immunochemical test (FIT), surveillance, and diagnostic workup for abdominal symptoms. In the pooled data, TXI significantly increased both ADR (57,8% versus 43.6%; RR 1.32; 95% confidence interval [CI] 1.20-1.46; P < 0.001; I 2 = 0%) and APC (MD 0.50; 95% CI 0.37-0.64; P < 0.001; I 2 = 0%), compared with WLI. Furthermore, TXI was more effective at detecting nonpolypoid/flat adenomas, proximal/right-sided adenomas, and adenomas ≥ 10 mm in size. Colonoscopies with TXI had shorter withdrawal times. Conclusions Our meta-analysis demonstrates that TXI significantly improves detection of colorectal adenomas in patients undergoing colonoscopy for various indications. TXI has the potential to improve overall quality of colonoscopy and contribute to colorectal cancer prevention.
Collapse
Affiliation(s)
- Stefan Mitev
- Gastroenterology Clinic, University Hospital St Ivan Rilski, Sofia, Bulgaria
| | - Humza Saeed
- Gastroenterology, Rawalpindi Medical University, Rawalpindi, Pakistan
| | - Ch Faizan Rasheed
- Gastroenterology, Rawalpindi Medical University, Rawalpindi, Pakistan
| | - A Abdullah
- Gastroenterology, Rawalpindi Medical University, Rawalpindi, Pakistan
| | - Stefan Murvakov
- HPB Surgery and Transplantology, Military Medical Academy, Sofia, Bulgaria, Sofia, Bulgaria
| | - Vassil Sirakov
- HPB Surgery and Transplantology, Military Medical Academy, Sofia, Bulgaria, Sofia, Bulgaria
| | - Stefan Tchernodrinski
- Division of Academic Internal Medicine and Geriatrics, University of Illinois Chicago, Chicago, United States
| | - Zoya Spassova
- Gastroenterology Clinic, University Hospital St Ivan Rilski, Sofia, Bulgaria
| |
Collapse
|
37
|
Maida M, Marasco G, Maas MHJ, Ramai D, Spadaccini M, Sinagra E, Facciorusso A, Siersema PD, Hassan C. Effectiveness of artificial intelligence assisted colonoscopy on adenoma and polyp miss rate: A meta-analysis of tandem RCTs. Dig Liver Dis 2025; 57:169-175. [PMID: 39322447 DOI: 10.1016/j.dld.2024.09.003] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/23/2024] [Revised: 08/20/2024] [Accepted: 09/01/2024] [Indexed: 09/27/2024]
Abstract
BACKGROUND AND AIMS One-fourth of colorectal neoplasia is missed at screening colonoscopy, representing the leading cause of interval colorectal cancer (I-CRC). This systematic review and meta-analysis summarizes the efficacy of computer-aided colonoscopy (CAC) compared to white-light colonoscopy (WLC) in reducing lesion miss rates. METHODS Major databases were systematically searched through May 2024 for tandem-design RCTs comparing lesion miss rates in CAC-first followed by WLC vs WLC-first followed by CAC. The primary outcomes were adenoma miss rate (AMR) and polyp miss rate (PMR). The secondary outcomes were advanced AMR (aAMR) and sessile serrated lesion miss rate (SMR). RESULTS Six RCTs (1718 patients) were included. AMR was significantly lower for CAC compared to WLC (RR = 0.46; 95 %CI [0.38-0.55]; P < 0.001). PMR was also lower for CAC compared to WLC (RR = 0.44; 95 %CI [0.33-0.60]; P < 0.001). No significant difference in aAMR (RR = 1.28; 95 %CI [0.34-4.83]; P = 0.71) and SMR (RR = 0.44; 95 %CI [0.15-1.28]; P = 0.13) were observed. Sensitivity analysis including only RCTs performed in CRC screening and surveillance setting confirmed lower AMR (RR = 0.48; 95 %CI [0.39-0.58]; P < 0.001) and PMR (RR = 0.50; 95 %CI [0.37-0.66]; P < 0.001), also showing significantly lower SMR (RR = 0.28; 95 %CI [0.11-0.70]; P = 0.007) for CAC compared to WLC. CONCLUSIONS CAC results in significantly lower AMR and PMR compared to WLC overall, and significantly lower AMR, PMR and SMR in the screening/surveillance setting, potentially reducing the incidence of I-CRC.
Collapse
Affiliation(s)
- M Maida
- Department of Medicine and Surgery, University of Enna 'Kore', Enna, Italy; Gastroenterology Unit, Umberto I Hospital, Enna, Italy.
| | - G Marasco
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy; IRCCS Azienda Ospedaliera Universitaria di Bologna, Bologna, Italy
| | - M H J Maas
- Department of Gastroenterology & Hepatology, Radboud University Medical Center, Nijmegen, the Netherlands
| | - D Ramai
- Division of Gastroenterology, Hepatology and Endoscopy, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - M Spadaccini
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy; Endoscopy Unit, Humanitas Clinical and Research Hospital, IRCCS, Rozzano, Italy
| | - E Sinagra
- Gastroenterology Unit, Fondazione Istituto San Raffaele Giglio, Cefalù, Italy
| | - A Facciorusso
- Department of Medical and Surgical Sciences, University of Foggia, Foggia, Italy
| | - P D Siersema
- Depatment of Gastroenterology and Hepatology, Erasmus MC - University Medical Center, Rotterdam, the Netherlands
| | - C Hassan
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy; Endoscopy Unit, Humanitas Clinical and Research Hospital, IRCCS, Rozzano, Italy
| |
Collapse
|
38
|
Park JB, Bae JH. Effectiveness of a novel artificial intelligence-assisted colonoscopy system for adenoma detection: a prospective, propensity score-matched, non-randomized controlled study in Korea. Clin Endosc 2025; 58:112-120. [PMID: 39107138 PMCID: PMC11837574 DOI: 10.5946/ce.2024.168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/24/2024] [Revised: 07/18/2024] [Accepted: 07/21/2024] [Indexed: 08/09/2024] Open
Abstract
BACKGROUND/AIMS The real-world effectiveness of computer-aided detection (CADe) systems during colonoscopies remains uncertain. We assessed the effectiveness of the novel CADe system, ENdoscopy as AI-powered Device (ENAD), in enhancing the adenoma detection rate (ADR) and other quality indicators in real-world clinical practice. METHODS We enrolled patients who underwent elective colonoscopies between May 2022 and October 2022 at a tertiary healthcare center. Standard colonoscopy (SC) was compared to ENAD-assisted colonoscopy. Eight experienced endoscopists performed the procedures in randomly assigned CADe- and non-CADe-assisted rooms. The primary outcome was a comparison of ADR between the ENAD and SC groups. RESULTS A total of 1,758 sex- and age-matched patients were included and evenly distributed into two groups. The ENAD group had a significantly higher ADR (45.1% vs. 38.8%, p=0.010), higher sessile serrated lesion detection rate (SSLDR) (5.7% vs. 2.5%, p=0.001), higher mean number of adenomas per colonoscopy (APC) (0.78±1.17 vs. 0.61±0.99; incidence risk ratio, 1.27; 95% confidence interval, 1.13-1.42), and longer withdrawal time (9.0±3.4 vs. 8.3±3.1, p<0.001) than the SC group. However, the mean withdrawal times were not significantly different between the two groups in cases where no polyps were detected (6.9±1.7 vs. 6.7±1.7, p=0.058). CONCLUSIONS ENAD-assisted colonoscopy significantly improved the ADR, APC, and SSLDR in real-world clinical practice, particularly for smaller and nonpolypoid adenomas.
Collapse
Affiliation(s)
- Jung-Bin Park
- Department of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Jung Ho Bae
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| |
Collapse
|
39
|
van Liere ELSA, Ramsoekh D, Daulton E, Dakkak M, van Lingen JM, Stewart TK, Bosch S, Carvalho B, Dekker E, Jacobs MAJM, Koornstra JJ, Kuijvenhoven JP, van Leerdam ME, de Meij TGJ, Meijer GA, Spaander MCW, Covington JA, de Boer NKH. Faecal Volatile Organic Compounds to Detect Colorectal Neoplasia in Lynch Syndrome-A Prospective Longitudinal Multicentre Study. Aliment Pharmacol Ther 2025; 61:145-158. [PMID: 39422092 PMCID: PMC11636173 DOI: 10.1111/apt.18328] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/22/2024] [Revised: 08/26/2024] [Accepted: 09/25/2024] [Indexed: 10/19/2024]
Abstract
BACKGROUND Non-invasive biomarkers may reduce post-colonoscopy colorectal cancer (CRC) rates and colonoscopy overuse in Lynch syndrome. Unlike faecal immunochemical test (FIT), faecal volatile organic compounds (VOCs) may accurately detect both advanced and non-advanced colorectal neoplasia. AIM The aim of this study was to evaluate the potential of faecal VOCs-separately and with FIT-to guide optimal colonoscopy intervals in Lynch syndrome. METHODS Prospective longitudinal multicentre study in which individuals with Lynch syndrome collected faeces before and after high-quality surveillance colonoscopy. VOC-patterns were analysed using field asymmetric ion mobility spectrometry (FAIMS) and gas chromatography-ion mobility spectrometry (GC-IMS) followed by machine learning pipelines, and combined with FIT at 2.55 μg Hb/g faeces. Gas chromatography time-of-flight mass spectrometry analysed individual VOC abundance. RESULTS Among 200 included individuals (57% female, median 51 years), 62 had relevant neoplasia at colonoscopy: 3 CRC, 6 advanced adenoma (AA), 3 advanced serrated lesion (ASL), and 50 non-advanced adenoma (NAA). Respective sensitivity and negative predictive value for CRC and AA (and also ASL in case of FAIMS) were 100% and 100% using FAIMS (54% specificity), and 89% and 99% using GC-IMS (58% specificity). Respective sensitivity and specificity for any relevant neoplasia were 88% and 44% (FAIMS) and 84% and 28% (GC-IMS); accuracy did not significantly improve upon VOC-FIT. VOC-patterns differed before and after polypectomy (AUC 0.70). NAA showed decreased faecal abundance of butanal, 2-oxohexane, dimethyldisulphide and dimethyltrisulphide. CONCLUSIONS In Lynch syndrome, faecal VOCs may be a promising strategy for postponing colonoscopy and for follow-up after polypectomy. Our results serve as a stepping stone for large validation studies. TRIAL REGISTRATION NL8749.
Collapse
Affiliation(s)
- Elsa L. S. A. van Liere
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- Amsterdam Gastroenterology Endocrinology Metabolism Research InstituteAmsterdamThe Netherlands
| | - Dewkoemar Ramsoekh
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- Amsterdam Gastroenterology Endocrinology Metabolism Research InstituteAmsterdamThe Netherlands
| | - Emma Daulton
- School of EngineeringUniversity of WarwickCoventryUK
| | - Maya Dakkak
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- School of MedicineVrije UniversiteitAmsterdamThe Netherlands
| | - Joris M. van Lingen
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- School of MedicineVrije UniversiteitAmsterdamThe Netherlands
| | | | - Sofie Bosch
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- Amsterdam Gastroenterology Endocrinology Metabolism Research InstituteAmsterdamThe Netherlands
| | - Beatriz Carvalho
- Department of PathologyNetherlands Cancer InstituteAmsterdamThe Netherlands
| | - Evelien Dekker
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- Amsterdam Gastroenterology Endocrinology Metabolism Research InstituteAmsterdamThe Netherlands
| | - Maarten A. J. M. Jacobs
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
| | - Jan Jacob Koornstra
- Department of Gastroenterology and Hepatology, University Medical Center GroningenUniversity of GroningenGroningenThe Netherlands
| | - Johan P. Kuijvenhoven
- Department of Gastroenterology and HepatologySpaarne GasthuisHoofddorpThe Netherlands
| | - Monique E. van Leerdam
- Department of Gastrointestinal OncologyNetherlands Cancer InstituteAmsterdamThe Netherlands
- Department of Gastroenterology and HepatologyLeiden University Medical CenterLeidenThe Netherlands
| | - Tim G. J. de Meij
- Amsterdam Gastroenterology Endocrinology Metabolism Research InstituteAmsterdamThe Netherlands
- Department of Paediatric GastroenterologyAmsterdam University Medical CenterAmsterdamThe Netherlands
| | - Gerrit A. Meijer
- Department of PathologyNetherlands Cancer InstituteAmsterdamThe Netherlands
| | - Manon C. W. Spaander
- Department of Gastroenterology and HepatologyErasmus University Medical CenterRotterdamThe Netherlands
| | | | - Nanne K. H. de Boer
- Department of Gastroenterology and HepatologyAmsterdam University Medical CenterAmsterdamThe Netherlands
- Amsterdam Gastroenterology Endocrinology Metabolism Research InstituteAmsterdamThe Netherlands
| |
Collapse
|
40
|
Makar J, Abdelmalak J, Con D, Hafeez B, Garg M. Use of artificial intelligence improves colonoscopy performance in adenoma detection: a systematic review and meta-analysis. Gastrointest Endosc 2025; 101:68-81.e8. [PMID: 39216648 DOI: 10.1016/j.gie.2024.08.033] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/08/2024] [Revised: 08/17/2024] [Accepted: 08/27/2024] [Indexed: 09/04/2024]
Abstract
BACKGROUND AND AIMS Artificial intelligence (AI) is increasingly used to improve adenoma detection during colonoscopy. This meta-analysis aimed to provide an updated evaluation of computer-aided detection (CADe) systems and their impact on key colonoscopy quality indicators. METHODS We searched the EMBASE, PubMed, and MEDLINE databases from inception until February 15, 2024, for randomized control trials (RCTs) comparing the performance of CADe systems with routine unassisted colonoscopy in the detection of colorectal adenomas. RESULTS Twenty-eight RCTs were selected for inclusion involving 23,861 participants. Random-effects meta-analysis demonstrated a 20% increase in adenoma detection rate (risk ratio [RR], 1.20; 95% confidence interval [CI], 1.14-1.27; P < .01) and 55% decrease in adenoma miss rate (RR, 0.45; 95% CI, 0.37-0.54; P < .01) with AI-assisted colonoscopy. Subgroup analyses involving only expert endoscopists demonstrated a similar effect size (RR, 1.19; 95% CI, 1.11-1.27; P < .001), with similar findings seen in analysis of differing CADe systems and healthcare settings. CADe use also significantly increased adenomas per colonoscopy (weighted mean difference, 0.21; 95% CI, 0.14-0.29; P < .01), primarily because of increased diminutive lesion detection, with no significant difference seen in detection of advanced adenomas. Sessile serrated lesion detection (RR, 1.10; 95% CI, 0.93-1.30; P = .27) and miss rates (RR, 0.44; 95% CI, 0.16-1.19; P = .11) were similar. There was an average 0.15-minute prolongation of withdrawal time with AI-assisted colonoscopy (weighted mean difference, 0.15; 95% CI, 0.04-0.25; P = .01) and a 39% increase in the rate of non-neoplastic resection (RR, 1.39; 95% CI, 1.23-1.57; P < .001). CONCLUSIONS AI-assisted colonoscopy significantly improved adenoma detection but not sessile serrated lesion detection irrespective of endoscopist experience, system type, or healthcare setting.
Collapse
Affiliation(s)
- Jonathan Makar
- Department of Medicine, The University of Melbourne, Melbourne, Victoria, Australia
| | - Jonathan Abdelmalak
- Department of Gastroenterology, Austin Hospital, Heidelberg, Victoria, Australia; Department of Gastroenterology, Alfred Hospital, Melbourne, Victoria, Australia; Central Clinical School, Monash University, Melbourne, Victoria, Australia
| | - Danny Con
- Department of Medicine, The University of Melbourne, Melbourne, Victoria, Australia; Department of Gastroenterology, Austin Hospital, Heidelberg, Victoria, Australia
| | - Bilal Hafeez
- Department of Medicine, The University of Melbourne, Melbourne, Victoria, Australia
| | - Mayur Garg
- Department of Medicine, The University of Melbourne, Melbourne, Victoria, Australia; Department of Gastroenterology, Northern Health, Epping, Victoria, Australia
| |
Collapse
|
41
|
Liu KS, George R, Shin C, Xiong JQ, Jamali T, Liu Y, Roy P, Singh S, Ma S, El-Serag HB, Tan MC. Interval Advanced Adenomas and Neoplasia in Patients with Negative Colonoscopy Following Positive Stool-Based Colorectal Cancer Screening Test. Dig Dis Sci 2025; 70:350-359. [PMID: 39581897 PMCID: PMC11854550 DOI: 10.1007/s10620-024-08748-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/27/2024] [Accepted: 11/07/2024] [Indexed: 11/26/2024]
Abstract
BACKGROUND/AIMS Fecal occult blood test (FOBT) and fecal immunohistochemical test (FIT) are used for colorectal cancer (CRC) screening. However, when no adenomas are found following a positive FOBT/FIT, the future risk of advanced adenomas or colorectal cancer (CRC) is unclear. We determined the incidence and determinants of advanced adenomas or CRC after a negative index colonoscopy following a positive FOBT/FIT. METHODS We identified patients in the Harris Health System (Houston, Texas) who underwent a colonoscopy following a positive FOBT/FIT from 01/2010 to 01/2013. We compared the incidence rates of advanced adenomas (≥ 1 cm, villous histopathology, or high-grade dysplasia) or CRC through 12/2023 for patients without polyps on index colonoscopy (negative colonoscopy) to patients with polyps (positive colonoscopy). We examined risk factors for incident adenomas using Cox regression models. RESULTS Of 2096 patients, 1293 (61.7%) had negative index colonoscopy and 803 (38.3%) had positive index colonoscopy. Overall, 411 patients (19.6%) underwent subsequent colonoscopy with incident adenomas in 241 patients and no incident CRC over mean 12.5 years. The incidence rate of advanced adenomas was 2.08 per 100 person-years after positive index colonoscopy compared to 0.65 per 100 person-years after negative index colonoscopy (age-adjusted incidence rate ratio 3.08, 95% CI 1.27-7.48). Non-Hispanic white race was the strongest risk factor for incident adenomas among patients with negative index colonoscopy. CONCLUSIONS We found a low likelihood of advanced adenomas and no interval CRC following negative index colonoscopy after positive FOBT/FIT. Non-Hispanic white race was a risk factor for incident adenomas, and these patients may warrant closer surveillance.
Collapse
Affiliation(s)
- Kyle S Liu
- Department of Internal Medicine, Washington University in St. Louis, St. Louis, MO, USA
| | - Rollin George
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, MS: BCM 285, Houston, TX, USA
| | - Caleb Shin
- Department of Orthopedic Surgery, HCA Medical City Denton, Denton, TX, USA
| | - Jia Q Xiong
- Department of Internal Medicine, Washington University in St. Louis, St. Louis, MO, USA
| | - Taher Jamali
- Divison of Gastroenterology, Henry Ford Hospital, Detroit, MI, USA
| | - Yan Liu
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, MS: BCM 285, Houston, TX, USA
- Houston VA HSR&D Center for Innovations in Quality, Effectiveness and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, TX, USA
| | - Priya Roy
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, MS: BCM 285, Houston, TX, USA
| | - Sonia Singh
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, MS: BCM 285, Houston, TX, USA
| | - Samuel Ma
- School of Medicine, Baylor College of Medicine, Houston, TX, USA
| | - Hashem B El-Serag
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, MS: BCM 285, Houston, TX, USA
- Houston VA HSR&D Center for Innovations in Quality, Effectiveness and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, TX, USA
| | - Mimi C Tan
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, One Baylor Plaza, MS: BCM 285, Houston, TX, USA.
| |
Collapse
|
42
|
Chen X, Xu B, Wei B, Ji L, Yang C, Zhan Q. Relationship Between Adenoma Detection Rate and Respective Withdrawal Time in Different Colon Segments: A Retrospective, Single-Center Study. JGH Open 2025; 9:e70095. [PMID: 39781025 PMCID: PMC11708806 DOI: 10.1002/jgh3.70095] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2024] [Revised: 12/11/2024] [Accepted: 01/02/2025] [Indexed: 01/11/2025]
Abstract
Background and Aims The 6-min withdrawal time for colonoscopy is widely considered the standard of care. However, there may not be appropriate if the 6-min is equally divided into various colon segments. Since the adenoma detection in each colon segment is not the same, there may be differences with the withdrawal time in different colon segments. Our objective was to evaluate the relationships between adenoma detection rate (ADR) and respective withdrawal time in different colon segments. Methods Outpatients, age range 18-75 years, undertaking complete colonoscopy were enrolled in this study from November 2019 to November 2020 in the digestive endoscopy center. The entire colon was divided into four different segments: ascending colon, transverse colon, descending colon and rectosigmoid colon. The respective withdrawal time and ADR in each colon segment were recorded respectively. Results A total of 586 outpatients (279 males, 307 females) enrolled in this study and the general ADR was 38.2%. The positive withdrawal time (adenomas detected) was longer than negative withdrawal time (non-adenomas detected) (334.04 ± 24.21 s vs. 303.65 ± 5.20 s, t = 1.26, p < 0.001). ADR in ascending colon, transverse colon, descending colon and rectosigmoid colon were respectively 30.5%, 2.9%, 3.1% and 7.5%. While all of their positive withdrawal time were longer than negative withdrawal time (94.34 ± 33.76 s vs. 70.40 ± 41.84 s, t = 3.31, p = 0.001; 85.40 ± 49.76 s vs. 71.66 ± 36.87 s, t = 1.95, p = 0.025; 80.29 ± 39.85 s vs. 69.73 ± 35.96 s, t = 1.40, p = 0.016;100.95 ± 55.92 s vs. 80.96 ± 42.87 s, t = 3.61; p < 0.001, respectively). The withdrawal time threshold in the ascending colon, transverse colon, descending colon, rectosigmoid colon determined by receiver operating characteristic (ROC) curve were 77, 61, 56 and 109 s, respectively. In the ascending colon, ADR was significantly higher (47.0% vs. 33.1%, p < 0.001) when the colonoscopy withdrawal time was ≥ 77 s. When the withdrawal time was ≥ 61 s in the transverse colon (42.7% vs. 32.7%, p = 0.013), ≥ 59 s in the descending colon (42.3% vs. 29.9%, p = 0.004) and ≥ 109 s in rectosigmoid colon (52.2% vs. 33.9%, p < 0.001), ADR was also significantly higher. After adjusting for age, sex and BMI, Logistic regression analysis showed that withdrawal time ≥ 77 s in the ascending colon (OR, 1.796; 95% CI, 1.273-2.532; p < 0.001), ≥ 61 s in the transverse colon (OR, 1.535; 95% CI, 1.094-2.155; p = 0.013), ≥ 56 s in the descending colon (OR, 1.722; 95% CI, 1.193-2.486; p = 0.004) and ≥ 109 s in the rectosigmoid colon (OR, 2.134; 95% CI, 1.446-2.350; p < 0.001) were independent risk factors for the increase of ADR. Conclusions ADR and withdrawal time are all various in individual colon segments. During the operation of colonoscopy, withdrawal time in the ascending colon may be shortened appropriately. The adenomas in the rectosigmoid colon are more likely to be detected and do not take longer withdrawal times. We need to choose the appropriate time according to different colon segments.
Collapse
Affiliation(s)
- Xujin Chen
- Department of GastroenterologyThe Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical UniversityWuxiJiangsuChina
| | - Bingxin Xu
- Department of GastroenterologyThe Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical UniversityWuxiJiangsuChina
| | - Bingni Wei
- Department of GastroenterologyThe Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical UniversityWuxiJiangsuChina
| | - Lin Ji
- Department of GastroenterologyThe Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical UniversityWuxiJiangsuChina
| | - Cheng Yang
- Department of Digestive Endoscopy CenterThe Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical UniversityWuxiJiangsuChina
| | - Qiang Zhan
- Department of GastroenterologyThe Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi People's Hospital, Wuxi Medical Center, Nanjing Medical UniversityWuxiJiangsuChina
| |
Collapse
|
43
|
Khalaf K, Rizkala T, Repici A. The use of artificial intelligence in colonoscopic evaluations. Curr Opin Gastroenterol 2025; 41:3-8. [PMID: 39480883 DOI: 10.1097/mog.0000000000001063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/02/2024]
Abstract
PURPOSE OF REVIEW This review aims to highlight the transformative impact of artificial intelligence in the field of gastrointestinal endoscopy, particularly in the detection and characterization of colorectal polyps. RECENT FINDINGS Over the past decade, artificial intelligence has significantly advanced the medical industry, including gastrointestinal endoscopy. Computer aided diagnosis - detection (CADe) systems have shown notable success in increasing ADR. Recent meta-analyses of RCTs have demonstrated that patients undergoing colonoscopy with CADe assistance had a higher ADR compared with conventional methods. Similarly, computer aided diagnosis - characterization (CADx) systems have proven effective in distinguishing between adenomatous and nonadenomatous polyps, enhancing diagnostic confidence and supporting cost-saving measures like the resect-and-discard strategy. Despite the high performance of these systems, the variability in real-world adoption highlights the importance of integrating artificial intelligence as an assistive tool rather than a replacement for human expertise. SUMMARY Artificial intelligence integration in colonoscopy, through CADe and CADx systems, marks a significant advancement in gastroenterology. These systems enhance lesion detection and characterization, leading to improved diagnostic accuracy, training outcomes, and clinical workflow efficiency. While artificial intelligence offers substantial benefits, the optimal approach involves using artificial intelligence to augment the expertise of endoscopists, ensuring that clinical decisions remain under human oversight.
Collapse
Affiliation(s)
- Kareem Khalaf
- Division of Gastroenterology, St. Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Tommy Rizkala
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele
- Humanitas Clinical and Research Center IRCCS, Endoscopy Unit, Rozzano, Milan, Italy
| | - Alessandro Repici
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele
- Humanitas Clinical and Research Center IRCCS, Endoscopy Unit, Rozzano, Milan, Italy
| |
Collapse
|
44
|
Qin B, Niu H, Qiu L, Zhou H, Lyu P. Fecal methylated syndecan-2 ( SDC2) testing for early screening of colorectal cancerous and precancerous lesions: A real-world retrospective study in China. CANCER PATHOGENESIS AND THERAPY 2025; 3:60-67. [PMID: 39872370 PMCID: PMC11764036 DOI: 10.1016/j.cpt.2024.02.002] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/25/2023] [Revised: 02/03/2024] [Accepted: 02/20/2024] [Indexed: 01/30/2025]
Abstract
Background Colorectal cancer (CRC) is a major public health concern and the second leading cause of cancer-related deaths worldwide. However, challenges remain in deploying effective screening strategies for early-stage CRC. This study aimed to evaluate the effectiveness of a fecal-based syndecan-2 (SDC2) methylation test for the detection of colorectal lesions and CRC. Methods We retrospectively collected data on participants who underwent fecal SDC2 methylation testing from January 1, 2019, to May 30, 2023. Patients with positive results were recommended to undergo colonoscopy. Performance indicators associated with certain clinical characteristics, including positive rate (PR), positive predictive value (PPV), and colonoscopy compliance rate (CCR), were subjected to statistical analysis. Results We analyzed data from 113,209 participants, of whom 11,841 (10.4% PR) had positive fecal SDC2 methylation test results. A total of 4315 participants with positive results adhered to the colonoscopy recommendations, and the CCR was 36.4%. Finally, 3169 colorectal lesions were detected, including 1134 polyps, 875 non-advanced adenomas (NAAs), 770 advanced adenomas (AAs), and 390 CRCs, with PPV values of 26.3% (1134/4315), 20.3% (875/4315), 17.8% (770/4315), and 9.0% (390/4315), respectively. Notably, the PPV for CRC increased significantly with age (χ 2 = 164.40, P < 0.0001). In addition, as the cycle threshold (CT) values increased, the PPVs of AAs and CRCs generally decreased, whereas those of NAAs and polyps significantly increased. Moreover, the clinical patient group had the highest incidence of late-stage CRC (stage II and higher), whereas asymptomatic populations from the staff physical examination group and rural town-based screening programs had the highest number of stage 0 and I CRCs detected (P = 0.0107). Conclusions This study indicates that fecal SDC2 methylation testing combined with colonoscopy may be an effective screening method for colorectal lesions and CRC.
Collapse
Affiliation(s)
- Boyu Qin
- Department of Oncology, The Fifth Medical Center of PLA General Hospital, Beijing 100071, China
| | - Haitao Niu
- National Health Commission of the People's Republic of China, Beijing 100044, China
| | - Lupeng Qiu
- Medical School of Chinese PLA, Beijing 100853, China
| | - Hongfeng Zhou
- Health Management Department, Foresea Life Insurance Guangzhou General Hospital, Guangzhou, Guangdong 510000, China
| | - Peng Lyu
- Cancer Pathogenesis and Therapy, Chinese Medical Association Publishing House, Beijing 100052, China
- Key Laboratory of Knowledge Mining and Service for Medical Journals, National Press and Publication Administration, Beijing 100052, China
- Beijing Beiya Hospital of Traditional Chinese Medicine, Beijing 100029, China
| |
Collapse
|
45
|
Afzal A, Aranan YS, Roberts T, Covington J, Vidal L, Ahmed S, Gill T, Francis N. Diagnostic accuracy of the faecal immunochemical test and volatile organic compound analysis in detecting colorectal polyps: meta-analysis. BJS Open 2024; 9:zrae154. [PMID: 39972538 PMCID: PMC11839406 DOI: 10.1093/bjsopen/zrae154] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2024] [Revised: 11/03/2024] [Accepted: 11/10/2024] [Indexed: 02/21/2025] Open
Abstract
BACKGROUND For the early detection of colorectal cancer, it is important to identify the premalignant lesions to prevent cancer development. Non-invasive testing methods such as the faecal immunochemical test are well established for the screening and triage of patients with suspected colorectal cancer but are not routinely used for polyps. Additionally, the role of volatile organic compounds has been tested for cancer detection. The aim of this review was to determine the diagnostic accuracy of the faecal immunochemical test and volatile organic compounds in detecting colorectal polyps. METHODS Original articles with diagnostic test accuracy measures for both the faecal immunochemical test and volatile organic compounds for advanced adenomas were included. Four databases including Medical Literature Analysis and Retrieval System Online (MEDLINE), Cumulative Index to Nursing and Allied Health Literature (CINAHL), Embase, and Web of Science were searched. The quality assessment tool for diagnostic accuracy study was used to assess the risk of bias and applicability. Meta-analysis was performed using RStudio® and the combined faecal immunochemical test-volatile organic compounds sensitivity and specificity were computed. RESULTS Twenty-two faecal immunochemical tests and 12 volatile organic compound-related articles were included in the systematic review whilst 18 faecal immunochemical tests and eight volatile organic compound-related studies qualified for the meta-analysis. The estimated pooled sensitivity and specificity of the faecal immunochemical test to diagnose advanced adenoma(s) were 36% (95% c.i. 30 to 41) and 89% (95% c.i. 86 to 91) respectively, with an area under the curve of 0.65, whilst volatile organic compounds pooled sensitivity and specificity was 83% (95% c.i. 70 to 91) and 76% (95% c.i. 60 to 87) respectively, with an area under the curve of 0.84. The combined faecal immunochemical test-volatile organic compounds increased the sensitivity to 89% with a specificity of 67%. CONCLUSION Faecal immunochemical testing has a higher specificity but poor sensitivity for detecting advanced adenomas, while volatile organic compound analysis is more sensitive. The combination of both tests enhances the detection rate of advanced adenomas.
Collapse
Affiliation(s)
- Asma Afzal
- Department of Colorectal Surgery, North Tees & Hartlepool NHS Foundation Trust, Stockton-on-Tees, UK
- School of Health & Life Sciences, Teesside University, Middlesbrough, UK
| | | | - Tom Roberts
- Undergraduate Department, University of Bristol, Bristol, UK
| | - James Covington
- Department of School of Engineering, Warwick University, Warwick, UK
| | - Lorena Vidal
- Department of Analytical Chemistry, Nutrition and Food Science, University Institute of Materials and ISABIAL, University of Alicante, Alicante, Spain
| | - Sonia Ahmed
- School of Health & Life Sciences, Teesside University, Middlesbrough, UK
| | - Talvinder Gill
- Department of Colorectal Surgery, North Tees & Hartlepool NHS Foundation Trust, Stockton-on-Tees, UK
| | - Nader Francis
- Department of Surgery, Yeovil Hospital, Southwest Yeovil, UK
- Department of Education and Research, Griffin Institute, London, UK
| |
Collapse
|
46
|
Kim HJ, Yoon H, Lee JW. [Efficacy of Second Forward-View Colonoscopy to Improve Adenoma Detection of Right-Side Colon: Systematic Review and Meta-Analysis]. THE KOREAN JOURNAL OF GASTROENTEROLOGY = TAEHAN SOHWAGI HAKHOE CHI 2024; 84:265-273. [PMID: 39716948 DOI: 10.4166/kjg.2024.117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/08/2024] [Revised: 10/13/2024] [Accepted: 10/14/2024] [Indexed: 12/25/2024]
Abstract
Background/Aims The second forward view (SFV) has been considered an effective method to improve the adenoma detection rate (ADR) in the right-side colon. On the other hand, there is insufficient evidence on how much the ADR is improved compared to standard one forward view (OFV) colonoscopy. A systematic review and meta-analysis were performed to determine the efficacy of improvement in the ADR by SFV colonoscopy. Methods This study conducted a systematic literature search in Medline, Embase, and Cochrane Library until Sep 2024. Two independent investigators (HJK, JWL) conducted a database search, and studies regarding the SFV or retroflexion were selected. The primary outcomes were the ADR of the right-side colon, polyp detection rate, and withdrawal time. Statistical analyses were performed using STATA 18.0 Special edition. Results Ten studies with 5,886 patients were included in this review. The pooled ADR of SFV colonoscopy for the right colon was significantly higher than that of the OFV, with a risk ratio (RR) of 1.25 (95% CI, 1.13-1.38 I2=0.0%). This result was statistically significant in three non-randomized trials (RR 1.19, 95% CI 1.06-1.34, I2=0.0%) with low heterogeneity. The right-sided polyp detection rate (RR 1.19, 95% CI 1.06-1.34, I2=61.6%) and the ADR of the whole colon (RR 1.10, 95% CI 1.01-1.20, I2=0.0%) were also significantly higher than those of OFV colonoscopy. Conclusions SFV colonoscopy is an effective method to improve the ADR of the right colon.
Collapse
Affiliation(s)
- Hyun Jung Kim
- Institute for Evidence-based Medicine, College of Medicine, Korea University, Seoul, Korea
| | - Hyuk Yoon
- Department of Internal, Seoul National University Bundang Hospital, Seongnam, Korea
| | - Jung Won Lee
- Department of Internal Medicine, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon, Korea
| |
Collapse
|
47
|
Chung GE, Lee J, Lim SH, Kang HY, Kim J, Song JH, Yang SY, Choi JM, Seo JY, Bae JH. A prospective comparison of two computer aided detection systems with different false positive rates in colonoscopy. NPJ Digit Med 2024; 7:366. [PMID: 39702474 DOI: 10.1038/s41746-024-01334-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2024] [Accepted: 11/08/2024] [Indexed: 12/21/2024] Open
Abstract
This study evaluated the impact of differing false positive (FP) rates in two computer-aided detection (CADe) systems on the clinical effectiveness of artificial intelligence (AI)-assisted colonoscopy. The primary outcomes were adenoma detection rate (ADR) and adenomas per colonoscopy (APC). The ADR in the control, system A (3.2% FP rate), and system B (0.6% FP rate) groups were 44.3%, 43.4%, and 50.4%, respectively, with system B showing a significantly higher ADR than the control group. The APC for the control, A, and B groups were 0.75, 0.83, and 0.90, respectively, with system B also showing a higher APC than the control. The non-true lesion resection rates were 23.8%, 29.2%, and 21.3%, with system B having the lowest. The system with lower FP rates demonstrated improved ADR and APC without increasing the resection of non-neoplastic lesions. These findings suggest that higher FP rates negatively affect the clinical performance of AI-assisted colonoscopy.
Collapse
Affiliation(s)
- Goh Eun Chung
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
| | - Jooyoung Lee
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Seon Hee Lim
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Hae Yeon Kang
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Jung Kim
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Ji Hyun Song
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Sun Young Yang
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Ji Min Choi
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Ji Yeon Seo
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea
| | - Jung Ho Bae
- Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea.
| |
Collapse
|
48
|
Lee H, Chung JW, Kim KO, Kwon KA, Kim JH, Yun SC, Jung SW, Sheeraz A, Yoon YJ, Kim JH, Kayasseh MA. Validation of Artificial Intelligence Computer-Aided Detection of Colonic Neoplasm in Colonoscopy. Diagnostics (Basel) 2024; 14:2762. [PMID: 39682670 DOI: 10.3390/diagnostics14232762] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2024] [Revised: 12/02/2024] [Accepted: 12/04/2024] [Indexed: 12/18/2024] Open
Abstract
BACKGROUND/OBJECTIVES Controlling colonoscopic quality is important in the detection of colon polyps during colonoscopy as it reduces the overall long-term colorectal cancer risk. Artificial intelligence has recently been introduced in various medical fields. In this study, we aimed to validate a previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm called ALPHAON® and compare outcomes with previous studies that showed that AI outperformed and assisted endoscopists of diverse levels of expertise in detecting colon polyps. METHODS We used the retrospective data of 500 still images, including 100 polyp images and 400 healthy colon images. In addition, we validated the CADe algorithm and compared its diagnostic performance with that of two expert endoscopists and six trainees from Gachon University Gil Medical Center. After a washing-out period of over 2 weeks, endoscopists performed polyp detection on the same dataset with the assistance of ALPHAON®. RESULTS The CADe algorithm presented a high capability in detecting colon polyps, with an accuracy of 0.97 (95% CI: 0.96 to 0.99), sensitivity of 0.91 (95% CI: 0.85 to 0.97), specificity of 0.99 (95% CI: 0.97 to 0.99), and AUC of 0.967. When evaluating and comparing the polyp detection ability of ALPHAON® with that of endoscopists with different levels of expertise (regarding years of endoscopic experience), it was found that ALPHAON® outperformed the experts in accuracy (0.97, 95% CI: 0.96 to 0.99), sensitivity (0.91, 95% CI: 0.85 to 0.97), and specificity (0.99, 95% CI: 0.97 to 0.99). After a washing-out period of over 2 weeks, the overall capability significantly improved for both experts and trainees with the assistance of ALPHAON®. CONCLUSIONS The high performance of the CADe algorithm system in colon polyp detection during colonoscopy was verified. The sensitivity of ALPHAON® led to it outperforming the experts, and it demonstrated the ability to enhance the polyp detection ability of both experts and trainees, which suggests a significant possibility of ALPHAON® being able to provide endoscopic assistance.
Collapse
Affiliation(s)
- Hannah Lee
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea
| | - Jun-Won Chung
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea
| | - Kyoung Oh Kim
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea
| | - Kwang An Kwon
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea
| | - Jung Ho Kim
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea
| | - Sung-Cheol Yun
- Division of Biostatistics, Center for Medical Research and Information, University of Ulsan College of Medicine, Seoul 05505, Republic of Korea
| | - Sung Woo Jung
- Division of Gastroenterology, Department of Internal Medicine, Korea University College of Medicine, Ansan 15355, Republic of Korea
| | | | | | - Ji Hee Kim
- CAIMI Co., Ltd., Incheon 22004, Republic of Korea
| | - Mohd Azzam Kayasseh
- Division of Gastroenterology, Dr. Sulaiman AI Habib Medical Group, Dubai Healthcare City, Dubai 51431, United Arab Emirates
| |
Collapse
|
49
|
Tatar OC, Çubukçu A. Surgical Insight-guided Deep Learning for Colorectal Lesion Management. Surg Laparosc Endosc Percutan Tech 2024; 34:559-565. [PMID: 39632423 DOI: 10.1097/sle.0000000000001298] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Accepted: 05/16/2024] [Indexed: 12/07/2024]
Abstract
BACKGROUND Colonoscopy stands as a pivotal diagnostic tool in identifying gastrointestinal diseases, including potentially malignant tumors. The procedure, however, faces challenges in the precise identification of lesions during visual inspections. The recent strides in AI and machine learning technologies have opened avenues for enhanced medical imaging analysis, including in the field of colonoscopy. METHODS In this study, we developed and evaluated a deep learning (DL) model, ColoNet, for detecting lesions in colonoscopic images. We analyzed 1760 images from 306 patients who underwent colorectal surgery between 2009 and 2022, meeting specific inclusion criteria. These images were used to train and validate ColoNet, employing the YOLOv8 architecture and various data augmentation techniques. Deep learning metrics are assessed via YOLO architecture and trained model diagnostic accuracy was assessed via sensitivity, specifity, positive predictive value, and negative predictive value. RESULTS Our results from the validation dataset revealed a precision of 0.79604, a recall of 0.78086, an mAP50 of 0.83243, and an mAP50-95 of 0.4439. In addition, on a separate real-time dataset of 91 images consisting both healthy and suspect lesions, ColoNet achieved a sensitivity of 70.73%, specificity of 92.00%, positive predictive value (PPV) of 87.88%, and negative predictive value (NPV) of 79.31%. The positive and negative likelihood ratios were 8.84 and 0.32, respectively, with an overall accuracy of 82.42%. CONCLUSIONS In conclusion, our model has demonstrated promising results, indicating its potential as a valuable tool to assist surgeons during colonoscopy procedures. Its ability to detect suspicious lesions with potential malignancy offers a noteworthy advancement in the early diagnosis and management of colorectal cancers. Further multicentric, prospective research and validation are warranted to fully realize its clinical applicability and impact.
Collapse
Affiliation(s)
- Ozan Can Tatar
- Department of General Surgery, Faculty of Medicine
- Department of Information Systems Engineering, Faculty of Technology, Kocaeli University, Kocaeli, Turkey
| | - Anil Çubukçu
- Department of General Surgery, Faculty of Medicine
| |
Collapse
|
50
|
Shaukat A, Lichtenstein DR, Chung DC, Seidl C, Wang Y, Navajas EE, Colucci DR, Baxi S, Brugge WR. Patient and procedural factors associated with true histology rates in patients undergoing colonoscopy with computer-aided detection of polyps. Gastrointest Endosc 2024; 100:1090-1094.e3. [PMID: 38964478 DOI: 10.1016/j.gie.2024.06.040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/20/2024] [Revised: 06/14/2024] [Accepted: 06/30/2024] [Indexed: 07/06/2024]
Abstract
BACKGROUND AND AIMS Computer-aided detection (CADe) devices have been shown to increase adenoma detection rates and adenomas per colonoscopy compared to standard colonoscopies. Questions remain about whether CADe colonoscopies are mainly increasing the detection of small, nonneoplastic lesions or if they are detecting more pathologically meaningful polyps. In this analysis, we compare the true histology rate (defined as polyps with confirmation of clinically relevant histopathology) of CADe-identified polyps with polyps identified during standard colonoscopies. METHODS Using data from the SKOUT trial, we compared the true histology rate (THR) between CADe and standard colonoscopies. We also conducted a subgroup analysis by patient, procedural, and endoscopist factors. To account for multiple testing of comparisons, we used the false discovery rate. RESULTS A total of 1423 participants were included (CADe, n = 714; standard, n = 709). Overall, THR was similar between the CADe and standard colonoscopy arms for adenomas, sessile serrated lesions, and large hyperplastic polyps. Higher THR with CADe colonoscopy was observed in some subgroups for adenomas. Endoscopists with 11 to 20 years of experience and procedures occurring after 12 pm had significantly higher adenoma THRs in the CADe cohort. Patients younger than 65 years, male patients, and procedures with a withdrawal time of ≥8 minutes had borderline significance in the CADe device adenoma THR subgroup. CONCLUSIONS CADe colonoscopies may hold the key to improving endoscopic quality measures, provided that the polyps identified by the CADe device are those of clinical relevance. Although the benefit and significance in the CADe group were demonstrated in this analysis, further research is warranted to ensure that the true histology is maintained when applied in real-world applications.
Collapse
Affiliation(s)
- Aasma Shaukat
- Division of Gastroenterology and Hepatology, Department of Medicine, New York University Grossman School of Medicine, New York, New York, USA.
| | - David R Lichtenstein
- Division of Gastroenterology, Department of Medicine, Boston Medical Center, Boston University School of Medicine, Boston, Massachusetts, USA
| | - Daniel C Chung
- Division of Gastroenterology, Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | | | - Yeli Wang
- Iterative Health Inc, Cambridge, Massachusetts, USA
| | | | | | - Shrujal Baxi
- Iterative Health Inc, Cambridge, Massachusetts, USA
| | - William R Brugge
- Division of Gastroenterology, Department of Medicine, Mount Auburn Hospital, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|