With the rapid advancement of artificial intelligence (AI) technologies, including deep learning, large language models, and neural networks, these methodologies are increasingly being developed and integrated into cancer research. Gastrointestinal tumors are characterized by complexity and heterogeneity, posing significant challenges for early detection, diagnostic accuracy, and the development of personalized treatment strategies. The application of AI in digestive oncology has demonstrated its transformative potential. AI not only alleviates the diagnostic burden on clinicians, but it improves tumor screening sensitivity, specificity, and accuracy. Additionally, AI aids the detection of biomarkers such as microsatellite instability and mismatch repair, supports intraoperative assessments of tumor invasion depth, predicts treatment responses, and facilitates the design of personalized treatment plans to potentially significantly enhance patient outcomes. Moreover, the integration of AI with multiomics analyses and imaging technologies has led to substantial advancements in foundational research on the tumor microenvironment. This review highlights the progress of AI in gastrointestinal oncology over the past 5 years with focus on early tumor screening, diagnosis, molecular marker identification, treatment planning, and prognosis predictions. We also explored the potential of AI to enhance medical imaging analyses to aid tumor detection and characterization as well as its role in automating and refining histopathological assessments.

Real-time endoscopic rectal lesion characterization employing artificial intelligence (AI) and near-infrared (NIR) imaging of the fluorescence perfusion indicator agent Indocyanine Green (ICG) has demonstrated promise. However, commercially available fluorescence endoscopes do not possess the flexibility and anatomical reach capabilities of colonoscopy while commercial flexible scopes do not yet provide beyond visible spectral imaging. This limits the application of this AI-NIR classification technology. Here, to close this technical gap, we present our development of a colonoscope-compatible flexible imaging probe for NIR-ICG visualization combined with a full field of view machine learning (ML) algorithm for fluorescence quantification and perfusion pattern cross-correlation (including first in human testing). The imaging probe is capable of 133µm minimum object resolution, with a maximum working distance of 50mm and an excitation illumination power of 52mW with 75o average field of illumination (meaning minimum device tip distance from target is 13 mm for a 2 cm polyp). The system demonstrated ex-vivo and in-vivo NIR visualization of clinically relevant concentrations of ICG in both resected and in situ (extracorporeally) colon in patients undergoing colorectal resection. A previously developed AI-NIR perfusion quantification algorithm was applied to videos of a bench model of varying ICG flow captured with the developed flexible system with added ML features generated full field of view pixel-level fluorescence time-series measurements capable of distinguishing distinct ICG flow regions in the image via correlative dynamic fluorescence intensity profiles. Jaccard Index comparison of the AI -generated flow regions against manually delineated flow regions resulted in 79% accuracy. While further clinical validation of the AI-NIR polyp classification method is on-going (in the Horizon Europe Awarded CLASSICA project), other use case applications of NIR colonoscopy include simpler perioperative perfusion assessment in patients undergoing colorectal resection and combination with targeted agents in development thus encouraging continuing development and design optimization of this flexible NIR imaging probe to enable clinical and commercial translation.

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.

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.

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%).

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".

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.

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.

Investigate the different variables possibly affecting the impact of CADe-assisted colonoscopy and its effect on ADR.

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.

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.

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.

Machine learning and its specialized forms, such as Artificial Neural Networks and Convolutional Neural Networks, are increasingly being used for detecting and managing gastrointestinal conditions. Recent advancements involve using Artificial Neural Network models to enhance predictive accuracy for severe lower gastrointestinal (LGI) bleeding outcomes, including the need for surgery. To this end, artificial intelligence (AI)-guided predictive models have shown promise in improving management outcomes. While much literature focuses on AI in early neoplasia detection, this review highlights AI's role in managing LGI and small bowel disorders, including risk stratification for LGI bleeding, quality control, evaluation of inflammatory bowel disease, and video capsule endoscopy reading. Overall, the integration of AI into routine clinical practice is still developing, with ongoing research aimed at addressing current limitations and gaps in patient care.

Colonoscopy is the gold standard for screening cancer and precancerous lesions in the large intestine. Recently, remarkable advances in artificial intelligence (AI) have led to the development of various computer-aided detection (CADe) systems for colonoscopy. This study aimed to evaluate the usefulness of AI for colonoscopy using CAD-EYEⓇ (Fujifilm, Tokyo, Japan) to calculate the adenoma miss rate (AMR).

This randomized, open-label, single-center, tandem study was conducted at Fukuoka University Chikushi Hospital from February 2022 to November 2022. Patients were randomly assigned to the CADe or non-CADe group. Immediately after the completion of the first endoscopy by an endoscopist, a new endoscopist was assigned to perform the second endoscopy. As a result, different endoscopists performed the examinations in a tandem fashion. A missed lesion was defined as a newly detected colorectal polyp by the second endoscopy. Finally, the AMR was compared between the two groups.

The study population comprised 48 patients in the CADe group and 46 patients in the non-CADe group. The AMR was 17.4% in the CADe group and 30.3% in the non-CADe group. Therefore, the AMR in the CADe group was statistically significantly lower than that in the non-CADe group (P=0.009).

The application of CAD-EYEⓇ to colonoscopy reduced the AMR. Overall, CAD-EYEⓇ might be useful for reducing missed colorectal adenomas.

High-quality colonoscopy reduces the risks of colorectal cancer by increasing the adenoma detection rate. Routine use of an automatic quality control system (AQCS) to assist in colorectal adenoma detection should be considered.

To evaluate the effect of an AQCS on the adenoma detection rate among colonoscopists who were moderate- and low-level detectors during routine colonoscopy.

This multicenter, single-blind, randomized clinical trial was conducted at 6 centers in China from August 1, 2021, to September 30, 2022. Data were analyzed from March 1 to June 30, 2023. Individuals aged 18 to 80 years were enrolled. Exclusion criteria were a history of inflammatory bowel disease, advanced colorectal cancer, and polyposis syndromes; known colorectal polyps without complete removal previously; a history of colorectal surgery; known stenosis or obstruction with contraindication for biopsy or prior failed colonoscopy; pregnancy or lactation; and refusal to participate. Intention-to-treat and per-protocol analysis was used.

Standard colonoscopy or AQCS-assisted colonoscopy.

Adenoma detection rate.

A total of 1254 participants (mean [SD] age, 51.21 [12.10] years; 674 [53.7%] male) were randomized (627 standard colonoscopy, 627 AQCS-assisted colonoscopy). Intention-to-treat analysis showed a significantly higher adenoma detection rate in the AQCS-assisted group vs standard colonoscopy group (32.7% vs 22.6%; relative risk [RR], 1.60; 95% CI, 1.23-2.09; P < .001). The adenoma detection rates were significantly higher in the AQCS group when considering pathology (nonadvanced adenomas, 30.1% vs 21.2%; RR, 1.52; 95% CI, 1.16-1.99; P = .002), and morphology (flat or sessile, 29.3% vs 20.4%, RR, 1.52; 95% CI, 1.16-2.00; P = .003). Use of AQCS significantly increased the adenoma detection rate of both the lower-level detectors (30.0% vs 20.0%; RR, 1.71; 95% CI, 1.24-2.35; P = .001) and the medium-level detectors (38.1% vs 27.7%; RR, 1.61; 95% CI, 1.07-2.43; P = .02). Similar increases were found for adenoma detection rates in the academic and nonacademic centers (academic: 29.3% vs 20.8%; RR, 1.58; 95% CI, 1.10-2.29; P = .01; nonacademic: 36.1% vs 24.5%; RR, 1.74; 95% CI, 1.23-2.46; P = .002). The number of adenomas per colonoscopy was significantly higher in the AQCS-assisted group (0.86 vs 0.48; RR, 1.50; 95% CI, 1.17-1.91; P = .001). The mean withdrawal time without intervention was slightly increased with AQCS assistance (6.78 vs 6.46 minutes; RR, 1.38; 95% CI, 1.26-1.52; P < .001). No serious adverse events were reported.

In this randomized clinical trial, AQCS assistance during routine colonoscopy increased adenoma detection rates and several related polyp parameters compared with standard colonoscopy in the lower- and medium-level detectors in academic and nonacademic settings. Routine use of AQCS to assist in colorectal adenoma detection and quality improvement should be considered.

ClinicalTrials.gov Identifier: NCT04901130.

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.

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).

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.

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.

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.

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.

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).

ENAD-assisted colonoscopy significantly improved the ADR, APC, and SSLDR in real-world clinical practice, particularly for smaller and nonpolypoid adenomas.

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.

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.

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).

AI-assisted colonoscopy significantly improved adenoma detection but not sessile serrated lesion detection irrespective of endoscopist experience, system type, or healthcare setting.

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.

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.

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.

Artificial intelligence (AI) has significantly impacted medical imaging, particularly in gastrointestinal endoscopy. Computer-aided detection and diagnosis systems (CADe and CADx) are thought to enhance the quality of colonoscopy procedures.

Colonoscopy is essential for colorectal cancer screening but often misses a significant percentage of adenomas. AI-assisted systems employing deep learning offer improved detection and differentiation of colorectal polyps, potentially increasing adenoma detection rates by 8%-10%. The main benefit of CADe is in detecting small adenomas, whereas it has a limited impact on advanced neoplasm detection. Recent advancements include real-time CADe systems and CADx for histopathological predictions, aiding in the differentiation of neoplastic and nonneoplastic lesions. Biases such as the Hawthorne effect and potential overdiagnosis necessitate large-scale clinical trials to validate the long-term benefits of AI. Additionally, novel concepts such as computer-aided quality improvement systems are emerging to address limitations facing current CADe systems.

Despite the potential of AI for enhancing colonoscopy outcomes, its effectiveness in reducing colorectal cancer incidence and mortality remains unproven. Further prospective studies are essential to establish the overall utility and clinical benefits of AI in colonoscopy.

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.

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®.

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®.

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.

Recent advancements in artificial intelligence (AI) have significantly impacted the field of gastrointestinal (GI) endoscopy, with applications spanning a wide range of clinical indications. The central goals for AI in GI endoscopy are to improve endoscopic procedural performance and quality assessment, optimize patient outcomes, and reduce administrative burden. Despite early progress, such as Food and Drug Administration approval of the first computer-aided polyp detection system in 2021, there are numerous important challenges to be faced on the path toward broader adoption of AI algorithms in clinical endoscopic practice.

Randomized clinical trials (RCTs) of computer-aided detection (CADe) system-enhanced colonoscopy compared with conventional colonoscopy suggest increased adenoma detection rate (ADR) and decreased adenoma miss rate (AMR), but the effect on detection of advanced colorectal neoplasia (ACN) is unclear.

To conduct a systematic review to compare performance of CADe-enhanced and conventional colonoscopy.

Cochrane Library, Google Scholar, Ovid EMBASE, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection databases were searched through February 2024.

Published RCTs comparing CADe-enhanced and conventional colonoscopy.

Average adenoma per colonoscopy (APC) and ACN per colonoscopy were primary outcomes. Adenoma detection rate, AMR, and ACN detection rate (ACN DR) were secondary outcomes. Balancing outcomes included withdrawal time and resection of nonneoplastic polyps (NNPs). Subgroup analyses were done by neural network architecture.

Forty-four RCTs with 36 201 cases were included. Computer-aided detection-enhanced colonoscopies have higher average APC (12 090 of 12 279 [0.98] vs. 9690 of 12 292 [0.78], incidence rate difference [IRD] = 0.22 [95% CI, 0.16 to 0.28]) and higher ADR (7098 of 16 253 [44.7%] vs. 5825 of 15 855 [36.7%], rate ratio [RR] = 1.21 [CI, 1.15 to 1.28]). Average ACN per colonoscopy was similar (1512 of 9296 [0.16] vs. 1392 of 9121 [0.15], IRD = 0.01 [CI, -0.01 to 0.02]), but ACN DR was higher with CADe system use (1260 of 9899 [12.7%] vs. 1119 of 9746 [11.5%], RR = 1.16 [CI, 1.02 to 1.32]). Using CADe systems resulted in resection of almost 2 extra NNPs per 10 colonoscopies and longer total withdrawal time (0.53 minutes [CI, 0.30 to 0.77]).

Statistically significant heterogeneity in quality and sample size and inability to blind endoscopists to the intervention in included studies may affect the performance estimates.

Computer-aided detection-enhanced colonoscopies have increased APC and detection rate but no difference in ACN per colonoscopy and a small increase in ACN DR. There is minimal increase in procedure time and no difference in performance across neural network architectures.

None. (PROSPERO: CRD42023422835).

Colon polyp detection and removal via colonoscopy are essential for colorectal cancer screening and prevention. This study aimed to develop a colon polyp detection program based on the RetinaNet algorithm and verify its clinical utility. To develop the AI-assisted program, the dataset was fully anonymized and divided into 10 folds for 10-fold cross-validation. Each fold consisted of 9,639 training images and 1,070 validation images. Video data from 56 patients were used for model training, and transfer learning was performed using the developed still image-based model. The final model was developed as a real-time polyp-detection program for endoscopy. To evaluate the model's performance, a prospective randomized controlled trial was conducted at six institutions to compare the polyp detection rates (PDR). A total of 805 patients were included. The group that utilized the AI model showed significantly higher PDR and adenoma detection rate (ADR) than the group that underwent colonoscopy without AI assistance. Multivariate analysis revealed an OR of 1.50 for cases where polyps were detected. The AI-assisted polyp-detection program is clinically beneficial for detecting polyps during colonoscopy. By utilizing this AI-assisted program, clinicians can improve adenoma detection rates, ultimately leading to enhanced cancer prevention.

Colorectal cancer (CRC) is a major concern because of its increasing incidence and mortality worldwide. Therefore, effective screening strategies are necessary to reduce its incidence.

In addition to fecal immunochemical tests and computed tomography colonography, screening colonoscopy is expected to significantly contribute to the reduction of CRC. However, the timing of colonoscopy for CRC screening is not well-defined because of the lack of sufficient data. Additionally, the effectiveness of colonoscopy is affected by various factors known as quality indicators (QIs), such as the performance of the endoscopist; therefore, there are concerns regarding quality assurance. The adenoma detection rate (ADR) is a well-known QI of colonoscopy. Substantial evidence has suggested that improving the ADR could reduce the incidence and mortality of postcolonoscopy CRC.

Recent technological advancements have led to the development of image-enhanced endoscopy and the incorporation of artificial intelligence, and their ability to improve the ADR has been assessed. This review focused on screening colonoscopies and QIs and their ability to improve the ADR and incidence and mortality of CRC.

Artificial intelligence (AI) has emerged as a transformative tool across several specialties, namely gastroenterology, where it has the potential to optimize both diagnosis and treatment as well as enhance patient care. Coloproctology, due to its highly prevalent pathologies and tremendous potential to cause significant mortality and morbidity, has drawn a lot of attention regarding AI applications. In fact, its application has yielded impressive outcomes in various domains, colonoscopy being one prominent example, where it aids in the detection of polyps and early signs of colorectal cancer with high accuracy and efficiency. With a less explored path but equivalent promise, AI-powered capsule endoscopy ensures accurate and time-efficient video readings, already detecting a wide spectrum of anomalies. High-resolution anoscopy is an area that has been growing in interest in recent years, with efforts being made to integrate AI. There are other areas, such as functional studies, that are currently in the early stages, but evidence is expected to emerge soon. According to the current state of research, AI is anticipated to empower gastroenterologists in the decision-making process, paving the way for a more precise approach to diagnosing and treating patients. This review aims to provide the state-of-the-art use of AI in coloproctology while also reflecting on future directions and perspectives.

We investigated how interactions between humans and computer-aided detection (CADe) systems are influenced by the user's experience and polyp characteristics.

We developed a CADe system using YOLOv4, trained on 16,996 polyp images from 1,914 patients and 1,800 synthesized sessile serrated lesion (SSL) images. The performance of polyp detection with CADe assistance was evaluated using a computerized test module. Eighteen participants were grouped by colonoscopy experience (nurses, fellows, and experts). The value added by CADe based on the histopathology and detection difficulty of polyps were analyzed.

The area under the curve for CADe was 0.87 (95% confidence interval [CI], 0.83 to 0.91). CADe assistance increased overall polyp detection accuracy from 69.7% to 77.7% (odds ratio [OR], 1.88; 95% CI, 1.69 to 2.09). However, accuracy decreased when CADe inaccurately detected a polyp (OR, 0.72; 95% CI, 0.58 to 0.87). The impact of CADe assistance was most and least prominent in the nurses (OR, 1.97; 95% CI, 1.71 to 2.27) and the experts (OR, 1.42; 95% CI, 1.15 to 1.74), respectively. Participants demonstrated better sensitivity with CADe assistance, achieving 81.7% for adenomas and 92.4% for easy-to-detect polyps, surpassing the standalone CADe performance of 79.7% and 89.8%, respectively. For SSLs and difficult-to-detect polyps, participants' sensitivities with CADe assistance (66.5% and 71.5%, respectively) were below those of standalone CADe (81.1% and 74.4%). Compared to the other two groups (56.1% and 61.7%), the expert group showed sensitivity closest to that of standalone CADe in detecting SSLs (79.7% vs 81.1%, respectively).

CADe assistance boosts polyp detection significantly, but its effectiveness depends on the user's experience, particularly for challenging lesions.

To investigate the effect of different working periods on missed diagnoses in patients with colorectal polyps in colonoscopy.

We conducted a retrospective analysis of patients who were diagnosed with colorectal polyps during colonoscopy in an outpatient department between July and December 2022. These patients were subsequently hospitalized for resection during this period. Patients with missed diagnoses were those who had newly discovered polyps in a second colonoscopy. The working periods were categorized as work, near the end of work, and delayed work, respectively, in the morning and afternoon.

A total of 482 patients were included, and the miss rate of diagnosis was 48.1% (232/482), mainly in the transverse colon (25%), and the ascending colon (23%). Patient age was a risk factor for the miss rate of diagnosis (OR = 1.025, 95%CI: 1.009-1.042, P = 0.003) and was also associated with the number of polyps detected for the first colonoscopy (χ2 = 18.196, P = 0.001). The different working periods had no statistical effect on the missed rate of diagnosis (χ2 = 1.998, P = 0.849). However, there was an increasing trend in miss rates towards the end of work and delayed work periods, both in the morning and afternoon. The highest miss rate (60.0%) was observed during delayed work in the afternoon. Additionally, poor bowel preparation was significantly more common during delayed work in the afternoon.

The increasing trend in miss rates towards the end of work and delayed work periods deserves clinical attention. Endoscopists cannot always stay in good condition under heavy workloads.

Artificial intelligence (AI) using deep learning systems has recently been utilized in various medical fields. In the field of gastroenterology, AI is primarily implemented in image recognition and utilized in the realm of gastrointestinal (GI) endoscopy. In GI endoscopy, computer-aided detection/diagnosis (CAD) systems assist endoscopists in GI neoplasm detection or differentiation of cancerous or noncancerous lesions. Several AI systems for colorectal polyps have already been applied in colonoscopy clinical practices. In esophagogastroduodenoscopy, a few CAD systems for upper GI neoplasms have been launched in Asian countries. The usefulness of these CAD systems in GI endoscopy has been gradually elucidated.

In this review, we outline recent articles on several studies of endoscopic AI systems for GI neoplasms, focusing on esophageal squamous cell carcinoma (ESCC), esophageal adenocarcinoma (EAC), gastric cancer (GC), and colorectal polyps. In ESCC and EAC, computer-aided detection (CADe) systems were mainly developed, and a recent meta-analysis study showed sensitivities of 91.2% and 93.1% and specificities of 80% and 86.9%, respectively. In GC, a recent meta-analysis study on CADe systems demonstrated that their sensitivity and specificity were as high as 90%. A randomized controlled trial (RCT) also showed that the use of the CADe system reduced the miss rate. Regarding computer-aided diagnosis (CADx) systems for GC, although RCTs have not yet been conducted, most studies have demonstrated expert-level performance. In colorectal polyps, multiple RCTs have shown the usefulness of the CADe system for improving the polyp detection rate, and several CADx systems have been shown to have high accuracy in colorectal polyp differentiation.

Most analyses of endoscopic AI systems suggested that their performance was better than that of nonexpert endoscopists and equivalent to that of expert endoscopists. Thus, endoscopic AI systems may be useful for reducing the risk of overlooking lesions and improving the diagnostic ability of endoscopists.

Diagnostic errors impact patient health and healthcare costs. Artificial Intelligence (AI) shows promise in mitigating this burden by supporting Medical Doctors in decision-making. However, the mere display of excellent or even superhuman performance by AI in specific tasks does not guarantee a positive impact on medical practice. Effective AI assistance should target the primary causes of human errors and foster effective collaborative decision-making with human experts who remain the ultimate decision-makers. In this narrative review, we apply these principles to the specific scenario of AI assistance during colonoscopy. By unraveling the neurocognitive foundations of the colonoscopy procedure, we identify multiple bottlenecks in perception, attention, and decision-making that contribute to diagnostic errors, shedding light on potential interventions to mitigate them. Furthermore, we explored how existing AI devices fare in clinical practice and whether they achieved an optimal integration with the human decision-maker. We argue that to foster optimal Human-AI collaboration, future research should expand our knowledge of factors influencing AI's impact, establish evidence-based cognitive models, and develop training programs based on them. These efforts will enhance human-AI collaboration, ultimately improving diagnostic accuracy and patient outcomes. The principles illuminated in this review hold more general value, extending their relevance to a wide array of medical procedures and beyond.

Both artificial intelligence (AI) and distal attachment devices have been shown to improve adenoma detection rate and reduce miss rate during colonoscopy. We studied the combined effect of Endocuff and AI on enhancing detection rates of various colonic lesions.

This was a 3-arm prospective randomized colonoscopy study involving patients aged 40 years or older. Participants were randomly assigned in a 1:1:1 ratio to undergo Endocuff with AI, AI alone, or standard high-definition (HD) colonoscopy. The primary outcome was adenoma detection rate (ADR) between the Endocuff-AI and AI groups while secondary outcomes included detection rates of polyp (PDR), sessile serrated lesion (sessile detection rate [SDR]), and advanced adenoma (advanced adenoma detection rate) between the 2 groups.

A total of 682 patients were included (mean age 65.4 years, 52.3% male), with 53.7% undergoing diagnostic colonoscopy. The ADR for the Endocuff-AI, AI, and HD groups was 58.7%, 53.8%, and 46.3%, respectively, while the corresponding PDR was 77.0%, 74.0%, and 61.2%. A significant increase in ADR, PDR, and SDR was observed between the Endocuff-AI and AI groups (ADR difference: 4.9%, 95% CI: 1.4%-8.2%, P = 0.03; PDR difference: 3.0%, 95% CI: 0.4%-5.8%, P = 0.04; SDR difference: 6.4%, 95% CI: 3.4%-9.7%, P < 0.01). Both Endocuff-AI and AI groups had a higher ADR, PDR, SDR, and advanced adenoma detection rate than the HD group (all P < 0.01).

Endocuff in combination with AI further improves various colonic lesion detection rates when compared with AI alone.

Colorectal cancer is a significant global health concern, necessitating effective screening strategies to reduce its incidence and mortality rates. Colonoscopy plays a crucial role in the detection and removal of colorectal neoplastic precursors. However, there are limitations and variations in the performance of endoscopists, leading to missed lesions and suboptimal outcomes. The emergence of artificial intelligence (AI) in endoscopy offers promising opportunities to improve the quality and efficacy of screening colonoscopies. In particular, AI applications, including computer-aided detection (CADe) and computer-aided characterization (CADx), have demonstrated the potential to enhance adenoma detection and optical diagnosis accuracy. Additionally, AI-assisted quality control systems aim to standardize the endoscopic examination process. This narrative review provides an overview of AI principles and discusses the current knowledge on AI-assisted endoscopy in the context of screening colonoscopies. It highlights the significant role of AI in improving lesion detection, characterization, and quality assurance during colonoscopy. However, further well-designed studies are needed to validate the clinical impact and cost-effectiveness of AI-assisted colonoscopy before its widespread implementation.

Precision endoscopy in the management of colorectal polyps and early colorectal cancer has emerged as the standard of care. It includes optical characterization of polyps and estimation of submucosal invasion depth of large nonpedunculated colorectal polyps to select the appropriate endoscopic resection modality. Over time, several imaging modalities have been implemented in endoscopic practice to improve optical performance. Among these, image-enhanced endoscopy systems and magnification endoscopy represent now well-established tools. New advanced technologies, such as endocytoscopy and confocal laser endomicroscopy, have recently shown promising results in predicting the histology of colorectal polyps. In recent years, artificial intelligence has continued to enhance endoscopic performance in the characterization of colorectal polyps, overcoming the limitations of other imaging modes. In this review we retrace the path of precision endoscopy, analyzing the yield of various endoscopic imaging techniques in personalizing management of colorectal polyps and early colorectal cancer.

Colorectal cancer is one of the top contributors to cancer-related deaths in the United States, with over 100,000 estimated cases in 2020 and over 50,000 deaths. The most common screening technique is minimally invasive colonoscopy using either reflected white light endoscopy or narrow-band imaging. However, current imaging modalities have only moderate sensitivity and specificity for lesion detection. We have developed a novel fluorescence excitation-scanning hyperspectral imaging (HSI) approach to sample image and spectroscopic data simultaneously on microscope and endoscope platforms for enhanced diagnostic potential. Unfortunately, fluorescence excitation-scanning HSI datasets pose major challenges for data processing, interpretability, and classification due to their high dimensionality. Here, we present an end-to-end scalable Artificial Intelligence (AI) framework built for classification of excitation-scanning HSI microscopy data that provides accurate image classification and interpretability of the AI decision-making process. The developed AI framework is able to perform real-time HSI classification with different speed/classification performance trade-offs by tailoring the dimensionality of the dataset, supporting different dimensions of deep learning models, and varying the architecture of deep learning models. We have also incorporated tools to visualize the exact location of the lesion detected by the AI decision-making process and to provide heatmap-based pixel-by-pixel interpretability. In addition, our deep learning framework provides wavelength-dependent impact as a heatmap, which allows visualization of the contributions of HSI wavelength bands during the AI decision-making process. This framework is well-suited for HSI microscope and endoscope platforms, where real-time analysis and visualization of classification results are required by clinicians.

The identification of early-stage colorectal cancers (CRC) and the resection of pre-cancerous neoplastic lesions through colonoscopy allows to decrease both CRC incidence and mortality. However, colonoscopy miss rates up to 26% for adenomas and 9% for advanced adenomas have been reported. In recent years, artificial intelligence (AI) systems have been emerging as easy-to-use tools, potentially lowering the risk of missing lesions.

This review paper focuses on GI Genius device (Medtronic Co. Minneapolis, MN, U.S.A.) a computer-assisted tool designed to assist endoscopists during standard white-light colonoscopies in detecting mucosal lesions.

Randomized controlled trials (RCTs) suggest that GI Genius is a safe and effective tool for improving adenoma detection, especially in CRC screening and surveillance colonoscopies. However, its impact seems to be less significant among experienced endoscopists and in real-world clinical scenarios compared to the controlled conditions of RCTs. Furthermore, it appears that GI Genius mainly enhances the detection of non-advanced, small polyps, but does not significantly impact the identification of advanced and difficult-to-detect adenoma. When using GI Genius, no complications were documented. Only a small number of studies reported an increased in withdrawal time or the removal of non-neoplastic lesions.

The aim of this study was to determine if utilization of artificial intelligence (AI) in the course of endoscopic procedures can significantly diminish both the adenoma miss rate (AMR) and the polyp miss rate (PMR) compared with standard endoscopy.

We performed an extensive search of various databases, encompassing PubMed, Embase, Cochrane Library, Web of Science, and Scopus, until June 2023. The search terms used were artificial intelligence, machine learning, deep learning, transfer machine learning, computer-assisted diagnosis, convolutional neural networks, gastrointestinal (GI) endoscopy, endoscopic image analysis, polyp, adenoma, and neoplasms. The main study aim was to explore the impact of AI on the AMR, PMR, and sessile serrated lesion miss rate.

A total of 7 randomized controlled trials were included in this meta-analysis. Pooled AMR was markedly lower in the AI group versus the non-AI group (pooled relative risk [RR], .46; 95% confidence interval [CI], .36-.59; P < .001). PMR was also reduced in the AI group in contrast with the non-AI control (pooled RR, .43; 95% CI, .27-.69; P < .001). The results showed that AI decreased the miss rate of sessile serrated lesions (pooled RR, .43; 95% CI, .20 to .92; P < .05) and diminutive adenomas (pooled RR, .49; 95% CI, .26-.93) during endoscopy, but no significant effect was observed for advanced adenomas (pooled RR, .48; 95% CI, .17-1.37; P = .17). The average number of polyps (Hedges' g = -.486; 95% CI, -.697 to -.274; P = .000) and adenomas (Hedges' g = -.312; 95% CI, -.551 to -.074; P = .01) detected during the second procedure also favored AI. However, AI implementation did not lead to a prolonged withdrawal time (P > .05).

This meta-analysis suggests that AI technology leads to significant reduction of miss rates for GI adenomas, polyps, and sessile serrated lesions during endoscopic surveillance. These results underscore the potential of AI to improve the accuracy and efficiency of GI endoscopic procedures.

Randomized controlled trials (RCTs) have reported that artificial intelligence (AI) improves endoscopic polyp detection. Different methodologies-namely, parallel and tandem designs-have been used to evaluate the efficacy of AI-assisted colonoscopy in RCTs. Systematic reviews and meta-analyses have reported a pooled effect that includes both study designs. However, it is unclear whether there are inconsistencies in the reported results of these 2 designs. Here, we aimed to determine whether study characteristics moderate between-trial differences in outcomes when evaluating the effectiveness of AI-assisted polyp detection.

A systematic search of Ovid MEDLINE, Embase, Cochrane Central, Web of Science, and IEEE Xplore was performed through March 1, 2023, for RCTs comparing AI-assisted colonoscopy with routine high-definition colonoscopy in polyp detection. The primary outcome of interest was the impact of study type on the adenoma detection rate (ADR). Secondary outcomes included the impact of the study type on adenomas per colonoscopy and withdrawal time, as well as the impact of geographic location, AI system, and endoscopist experience on ADR. Pooled event analysis was performed using a random-effects model.

Twenty-four RCTs involving 17,413 colonoscopies (AI assisted: 8680; non-AI assisted: 8733) were included. AI-assisted colonoscopy improved overall ADR (risk ratio [RR], 1.24; 95% confidence interval [CI], 1.17-1.31; I2 = 53%; P < .001). Tandem studies collectively demonstrated improved ADR in AI-aided colonoscopies (RR, 1.18; 95% CI, 1.08-1.30; I2 = 0%; P < .001), as did parallel studies (RR, 1.26; 95% CI, 1.17-1.35; I2 = 62%; P < .001), with no statistical subgroup difference between study design. Both tandem and parallel study designs revealed improvement in adenomas per colonoscopy in AI-aided colonoscopies, but this improvement was more marked among tandem studies (P < .001). AI assistance significantly increased withdrawal times for parallel (P = .002), but not tandem, studies. ADR improvement was more marked among studies conducted in Asia compared to Europe and North America in a subgroup analysis (P = .007). Type of AI system used or endoscopist experience did not affect overall improvement in ADR.

Either parallel or tandem study design can capture the improvement in ADR resulting from the use of AI-assisted polyp detection systems. Tandem studies powered to detect differences in endoscopic performance through paired comparison may be a resource-efficient method of evaluating new AI-assisted technologies.

The progress in Colorectal cancer (CRC) screening and management has resulted in an unprecedented caseload for histopathological diagnosis. While artificial intelligence (AI) presents a potential solution, the predominant emphasis on slide-level aggregation performance without thorough verification of cancer in each location, impedes both explainability and transparency. Effectively addressing these challenges is crucial to ensuring the reliability and efficacy of AI in histology applications.

In this study, we created an innovative AI algorithm using transfer learning from a polyp segmentation model in endoscopy. The algorithm precisely localized CRC targets within 0.25 mm² grids from whole slide imaging (WSI). We assessed the CRC detection capabilities at this fine granularity and examined the influence of AI on the diagnostic behavior of pathologists. The evaluation utilized an extensive dataset comprising 858 consecutive patient cases with 1418 WSIs obtained from an external center.

Our results underscore a notable sensitivity of 90.25% and specificity of 96.60% at the grid level, accompanied by a commendable area under the curve (AUC) of 0.962. This translates to an impressive 99.39% sensitivity at the slide level, coupled with a negative likelihood ratio of <0.01, signifying the dependability of the AI system to preclude diagnostic considerations. The positive likelihood ratio of 26.54, surpassing 10 at the grid level, underscores the imperative for meticulous scrutiny of any AI-generated highlights. Consequently, all four participating pathologists demonstrated statistically significant diagnostic improvements with AI assistance.

Our transfer learning approach has successfully yielded an algorithm that can be validated for CRC histological localizations in whole slide imaging. The outcome advocates for the integration of the AI system into histopathological diagnosis, serving either as a diagnostic exclusion application or a computer-aided detection (CADe) tool. This integration has the potential to alleviate the workload of pathologists and ultimately benefit patients.

Generative artificial intelligence tools and applications (GenAI) are being increasingly used in health care. Physicians, specialists, and other providers have started primarily using GenAI as an aid or tool to gather knowledge, provide information, train, or generate suggestive dialogue between physicians and patients or between physicians and patients' families or friends. However, unless the use of GenAI is oriented to be helpful in clinical service encounters that can improve the accuracy of diagnosis, treatment, and patient outcomes, the expected potential will not be achieved. As adoption continues, it is essential to validate the effectiveness of the infusion of GenAI as an intelligent technology in service encounters to understand the gap in actual clinical service use of GenAI.

This study synthesizes preliminary evidence on how GenAI assists, guides, and automates clinical service rendering and encounters in health care The review scope was limited to articles published in peer-reviewed medical journals.

We screened and selected 0.38% (161/42,459) of articles published between January 1, 2020, and May 31, 2023, identified from PubMed. We followed the protocols outlined in the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to select highly relevant studies with at least 1 element on clinical use, evaluation, and validation to provide evidence of GenAI use in clinical services. The articles were classified based on their relevance to clinical service functions or activities using the descriptive and analytical information presented in the articles.

Of 161 articles, 141 (87.6%) reported using GenAI to assist services through knowledge access, collation, and filtering. GenAI was used for disease detection (19/161, 11.8%), diagnosis (14/161, 8.7%), and screening processes (12/161, 7.5%) in the areas of radiology (17/161, 10.6%), cardiology (12/161, 7.5%), gastrointestinal medicine (4/161, 2.5%), and diabetes (6/161, 3.7%). The literature synthesis in this study suggests that GenAI is mainly used for diagnostic processes, improvement of diagnosis accuracy, and screening and diagnostic purposes using knowledge access. Although this solves the problem of knowledge access and may improve diagnostic accuracy, it is oriented toward higher value creation in health care.

GenAI informs rather than assisting or automating clinical service functions in health care. There is potential in clinical service, but it has yet to be actualized for GenAI. More clinical service-level evidence that GenAI is used to streamline some functions or provides more automated help than only information retrieval is needed. To transform health care as purported, more studies related to GenAI applications must automate and guide human-performed services and keep up with the optimism that forward-thinking health care organizations will take advantage of GenAI.

The effect of computer-aided polyp detection (CADe) on adenoma detection rate (ADR) among endoscopists-in-training remains unknown.

We performed a single-blind, parallel-group, randomized controlled trial in Hong Kong between April 2021 and July 2022 (NCT04838951). Eligible subjects undergoing screening/surveillance/diagnostic colonoscopies were randomized 1:1 to receive colonoscopies with CADe (ENDO-AID[OIP-1]) or not (control) during withdrawal. Procedures were performed by endoscopists-in-training with <500 procedures and <3 years' experience. Randomization was stratified by patient age, sex, and endoscopist experience (beginner vs intermediate level, <200 vs 200-500 procedures). Image enhancement and distal attachment devices were disallowed. Subjects with incomplete colonoscopies or inadequate bowel preparation were excluded. Treatment allocation was blinded to outcome assessors. The primary outcome was ADR. Secondary outcomes were ADR for different adenoma sizes and locations, mean number of adenomas, and non-neoplastic resection rate.

A total of 386 and 380 subjects were randomized to CADe and control groups, respectively. The overall ADR was significantly higher in the CADe group than in the control group (57.5% vs 44.5%; adjusted relative risk, 1.41; 95% CI, 1.17-1.72; P < .001). The ADRs for <5 mm (40.4% vs 25.0%) and 5- to 10-mm adenomas (36.8% vs 29.2%) were higher in the CADe group. The ADRs were higher in the CADe group in both the right colon (42.0% vs 30.8%) and left colon (34.5% vs 27.6%), but there was no significant difference in advanced ADR. The ADRs were higher in the CADe group among beginner (60.0% vs 41.9%) and intermediate-level (56.5% vs 45.5%) endoscopists. Mean number of adenomas (1.48 vs 0.86) and non-neoplastic resection rate (52.1% vs 35.0%) were higher in the CADe group.

Among endoscopists-in-training, the use of CADe during colonoscopies was associated with increased overall ADR. (ClinicalTrials.gov, Number: NCT04838951).

There are challenges for beginners to identify standard biliopancreatic system anatomical sites on endoscopic ultrasonography (EUS) images. Therefore, the authors aimed to develop a convolutional neural network (CNN)-based model to identify standard biliopancreatic system anatomical sites on EUS images.

The standard anatomical structures of the gastric and duodenal regions observed by EUS was divided into 14 sites. The authors used 6230 EUS images with standard anatomical sites selected from 1812 patients to train the CNN model, and then tested its diagnostic performance both in internal and external validations. Internal validation set tests were performed on 1569 EUS images of 47 patients from two centers. Externally validated datasets were retrospectively collected from 16 centers, and finally 131 patients with 85 322 EUS images were included. In the external validation, all EUS images were read by CNN model, beginners, and experts, respectively. The final decision made by the experts was considered as the gold standard, and the diagnostic performance between CNN model and beginners were compared.

In the internal test cohort, the accuracy of CNN model was 92.1-100.0% for 14 standard anatomical sites. In the external test cohort, the sensitivity and specificity of CNN model were 89.45-99.92% and 93.35-99.79%, respectively. Compared with beginners, CNN model had higher sensitivity and specificity for 11 sites, and was in good agreement with the experts (Kappa values 0.84-0.98).

The authors developed a CNN-based model to automatically identify standard anatomical sites on EUS images with excellent diagnostic performance, which may serve as a potentially powerful auxiliary tool in future clinical practice.

Studies on the effect of computer-aided detection (CAD) in a daily clinical screening and surveillance colonoscopy population practice are scarce. The aim of this study was to evaluate a novel CAD system in a screening and surveillance colonoscopy population.

This multicentre, randomised, controlled trial was done in ten hospitals in Europe, the USA, and Israel by 31 endoscopists. Patients referred for non-immunochemical faecal occult blood test (iFOBT) screening or surveillance colonoscopy were included. Patients were randomomly assigned to CAD-assisted colonoscopy or conventional colonoscopy; a subset was further randomly assigned to undergo tandem colonoscopy: CAD followed by conventional colonoscopy or conventional colonoscopy followed by CAD. Primary objectives included adenoma per colonoscopy (APC) and adenoma per extraction (APE). Secondary objectives included adenoma miss rate (AMR) in the tandem colonoscopies. The study was registered at ClinicalTrials.gov, NCT04640792.

A total of 916 patients were included in the modified intention-to-treat analysis: 449 in the CAD group and 467 in the conventional colonoscopy group. APC was higher with CAD compared with conventional colonoscopy (0·70 vs 0·51, p=0·015; 314 adenomas per 449 colonoscopies vs 238 adenomas per 467 colonoscopies; poisson effect ratio 1·372 [95% CI 1·068-1·769]), while showing non-inferiority of APE compared with conventional colonoscopy (0·59 vs 0·66; p<0·001 for non-inferiority; 314 of 536 extractions vs 238 of 360 extractions). AMR in the 127 (61 with CAD first, 66 with conventional colonoscopy first) patients completing tandem colonoscopy was 19% (11 of 59 detected during the second pass) in the CAD first group and 36% (16 of 45 detected during the second pass) in the conventional colonoscopy first group (p=0·024).

CAD increased adenoma detection in non-iFOBT screening and surveillance colonoscopies and reduced adenoma miss rates compared with conventional colonoscopy, without an increase in the resection of non-adenomatous lesions.

Magentiq Eye.