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.

In colorectal cancer screening with the fecal immunochemical test (FIT), the optimal follow-up after first-round colonoscopy for a positive FIT, particularly after negative colonoscopy, is unknown. Therefore, using Screening of Swedish Colons (SCREESCO) study data, we aimed to elucidate the risk factors for the detection of colorectal neoplasia in second-round colonoscopy, which can affect recommendations for the optimal follow-up.

We performed a cross-sectional analysis using data from SCREESCO participants undergoing colonoscopy after a positive 2-stool FIT, with a positivity cutoff value of ≥10 μg/g feces, in both the first and second rounds separated by a 2-year interval. We assessed the associations between colorectal neoplasia detection in second-round colonoscopy and participant characteristics, FIT concentrations, first-round colonoscopy results, and endoscopists' adenoma detection rates (ADRs), which were categorized as very low, low, intermediate, and high.

This study included 343 individuals. Despite negative first-round colonoscopies (n = 230), colorectal cancer and advanced colorectal neoplasia (ACN) were detected in 0.9% and 8.3% of participants in the second-round colonoscopy, respectively. An association was demonstrated between the first-round endoscopists' ADRs and the risk of second-round ACN detection. The multivariable odds ratios of the first-round intermediate and high ADRs, compared with the very low ADR, for second-round ACN detection were 0.17 (95% confidence interval [CI], 0.02-0.79) and 0.19 (95% CI, 0.04-0.86), respectively.

The impact of endoscopists' ADRs on ACN detection in subsequent-round colonoscopies underscores the importance of considering ADR for optimal follow-up after first-round colonoscopy in an FIT-based screening program.

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.

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).

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.

Computer-aided detection may help identify adenomas during surveillance colonoscopy for patients with untreated diminutive adenomas and those with a history of endoscopic resection.

The risk of colorectal cancer among fecal immunochemistry test-positive individuals who had undergone previous colonoscopies remains unclear. Therefore, this study aimed to determine the differences in the risk of colorectal cancer among fecal immunochemistry test-positive individuals according to the timing of their previous colonoscopies.

This multicenter, retrospective, observational study was conducted in Japan as a subgroup analysis of the J-SCOUT study (UMIN000040690), which integrated and analyzed a database comprising all colonoscopies performed at participating Japanese institutions between 2010 and 2020. This study used colonoscopy data of fecal immunochemistry test-positive individuals aged ≥ 20 years from three facilities that entered the timing of previous colonoscopies into the endoscopy database. Histologically confirmed advanced neoplasia was the study's primary outcome. Multivariate logistic regression analysis was used to calculate the odds ratios for each variable.

In total, 11,143 fecal immunochemistry test-positive patients underwent colonoscopy during the study period. Of these, 10,160 patients were included in the analysis after excluding those who met the exclusion criteria. The overall advanced neoplasia detection rate was 9.38% (953/10,160; 95% confidence interval: 8.82-9.96%). Compared with the first colonoscopy, the odds ratios for advanced neoplasia in individuals who underwent colonoscopies 1, 2, 3, 4, 5, > 5, and ≥ 10 years previously were 0.27, 0.15, 0.06, 0.10, 0.29, 0.31, and 0.31, respectively.

The detection rates of advanced neoplasia were low among the fecal immunochemistry test-positive individuals who had undergone colonoscopy, particularly in the past 5 years.

Data of long-term follow up for large non pedunculated colorectal polyps (LNPCPs) ≥4 cm removed with piecemeal wide field endoscopic mucosal resection (PWF-EMR) are limited. We primarily evaluated the recurrence rates and secondarily the rates of post colonoscopic polypectomy colorectal cancer (PCPCRC) on a long-term basis.

We retrospectively reviewed a prospectively-stored electronic database of all patients who underwent PWF-EMR for LNPCPs at the Venizeleion General Hospital, between 2009 and 2020. Eligible patients were those with LNPCPs ≥4 cm, deemed completely removed by endoscopic means and followed-up for a minimum of 36 months with at least two surveillance colonoscopies, the first one (SC1) (4-6) months after the initial PWF-EMR procedure and the second one (SC2) after (12-18) months. In 2023, all cases were checked for PCPCRC development.

Residual/early recurrent tissue was detected in 44 (31 %) cases among the 142 (82 males, 60 females) assessed during SC1. Late recurrent tissue was detected in 9 (6.6 %) cases among the 137 surveyed during SC2. Investigation did not reveal any case of PCPCRC .

This historical cohort shows that the PWF-EMR for LNPCPs ≥4 cm is a safe and definitive removal method while it is not associated with the appearance of PCPCRC.

Serrated polyps (SPs) with synchronous advanced adenoma (AA) may increase the incidence of colorectal cancer. However, current studies do not address this combination of SPs and AAs in detail with regard to their clinical characteristics in different age groups. The aim was to assess clinical characteristics and risk factors for SPs with synchronous AA in different age groups.

Retrospective cohort study.

Electronic medical record data from January 2011 to January 2022 at three grade III class A hospitals were enrolled in the study.

A total of 1605 patients with SPs with synchronous AA, including 484 patients in the elderly group and 1121 patients in the non-elderly group, were studied.

The elderly group and the non-elderly group.

Sex, smoking history, drinking history, body mass index (BMI), SP location, size, morphology and pathology.

The incidence of hyperplastic polyps (HPs) with synchronous AA in the elderly group was higher than that in the non-elderly group, while the incidence of sessile serrated adenomas/polyps (SSAs/Ps) with synchronous AA in the non-elderly group was higher than that in the elderly group. Male sex, drinking history and HP size (≤20 mm) were independent risk factors for HPs with synchronous AA in the non-elderly group, while drinking history and HP size (≤15 mm) were independent risk factors in the elderly group. For SSAs/Ps with synchronous AA, male sex, smoking history, drinking history, and SSA size (≥16 mm) were independent risk factors in the non-elderly group; high BMI was an independent risk factor in the elderly group.

SPs with synchronous AA showed different clinical characteristics and risk factors in different age groups.

Individuals with inflammatory bowel disease (IBC) and high-risk individuals are advised to discuss participation with their doctor and not to participate in colorectal cancer (CRC) screening. Yet a substantial proportion still participate in the Danish faecal immunochemical test (FIT) screening and have a higher positive FIT rate than the average-risk population. We estimated the risk of false-positive screening among individuals with inflammatory bowel disease and high-risk individuals to improve recommendations regarding screening participation. We included 71,871 FIT-positive participants (2014-2017) who had a subsequent colonoscopy within 3 months. Screening outcome within 180 days was established by using registers. We determined that 26,591 of the included participants had a false-positive screening. Participants with IBC or high CRC risk had a significantly higher risk of getting a false-positive screening than the average risk population, resulting in too many screening-related colonoscopies being performed among these individuals, indicating a need to update the screening protocols.

Screening colonoscopy, recommended every 10 years, reduces mortality from colorectal cancer (CRC) by early detection of prevalent but undiagnosed CRC, as well as by removal of precursor lesions. The aim of this study was to assess the relative contribution of both components to total CRC mortality reduction over time.

Using a validated multistate Markov model, we simulated hypothetical cohorts of 100,000 individuals aged 55 to 64 years with and without screening at baseline. Main outcomes included proportions of prevented CRC deaths arising from (asymptomatic) CRC already present at baseline and from newly developed CRC during 15 years of follow-up, and mortality rate ratios of screened versus nonscreened groups over time.

Early detection of prevalent cases accounted for 52%, 30%, and 18% of deaths prevented by screening colonoscopy within 5, 10, and 15 years, respectively. Relative reduction of mortality was estimated to be much larger for mortality from incident cancers than for mortality from cancers that were already present and detected early at screening endoscopy and for total CRC mortality (ie, 88% versus 67% and 79%, respectively, within 10 years from screening).

Reduction of CRC mortality mainly arises from early detection of prevalent cancers during the early years after screening colonoscopy, but prevention of incident cases accounts for the majority of prevented deaths in the longer run. Prevention of incident cases leads to sustained strong reduction of CRC mortality, possibly warranting an extension of screening intervals.

Colorectal cancer (CRC) is the second most deadly cancer globally. The rapidly rising incidence rate of CRC, coupled with increased diagnoses in individuals <50 years, indicates that early detection of CRC, and those at an increased risk of CRC development, is paramount to improve the survival rates of these patients. Here, we profile caspase-4 expression across 2 distinct CRC development pathways, sporadic CRC (sCRC) and inflammatory bowel disease-associated CRC (IBD-CRC), to examine its utility as a novel biomarker for CRC risk and diagnosis.

Tissue samples from patients with CRC, colonic polyps, IBD-CRC, and sCRC were assessed by immunohistochemistry for caspase-4 expression in epithelial and stromal compartments. RNAseq expression data for caspase-4 in CRC and normal tissue samples were mined from online databases.

Epithelial caspase-4 expression is selectively elevated in CRC tumor tissue compared to adjacent normal tissue, where it is not expressed. In the sCRC pathway, caspase-4 is expressed in the epithelial and stromal tissue of all histological subtypes of colonic polyps, with a significant increase in epithelial expression from low-grade dysplasia to high-grade dysplasia progression. For the IBD-CRC pathway, caspase-4 epithelial expression was specifically upregulated in dysplastic and neoplastic tissue of IBD-CRC but was not expressed in normal or inflamed tissue.

This study demonstrates that epithelial caspase-4 is selectively expressed in colon tissue during the development of dysplasia. As such, epithelial caspase-4 represents a promising novel tissue biomarker for CRC risk and diagnosis.

Guidelines now recommend patients with low-risk adenomas receive colonoscopy surveillance in 7-10 years and those with the previously recommended 5-year interval be re-evaluated. We tested 3 outreach approaches for transitioning patients to the 10-year interval recommendation.

This was a 3-arm pragmatic randomized trial comparing telephone, secure messaging, and mailed letter outreach. The setting was Kaiser Permanente Northern California, a large integrated healthcare system. Participants were patients 54-70 years of age with 1-2 small (<10 mm) tubular adenomas at baseline colonoscopy, due for 5-year surveillance in 2022, without high-risk conditions, and with access to all 3 outreach modalities. Patients were randomly assigned to the outreach arm (telephone [n = 200], secure message [n = 203], and mailed letter [n = 201]) stratified by age, sex, and race/ethnicity. Outreach in each arm was performed by trained medical assistants (unblinded) communicating in English with 1 reminder attempt at 2-4 weeks. Participants could change their assigned interval to 10 years or continue their planned 5-year interval.

Sixty-day response rates were higher for telephone (64.5%) and secure messaging outreach (51.7%) vs mailed letter (31.3%). Also, more patients adopted the 10-year surveillance interval in the telephone (37.0%) and secure messaging arms (32.0%) compared with mailed letter (18.9%) and rate differences were significant for telephone (18.1%; 97.5% confidence interval: 8.3%-27.9%) and secure message outreach (13.1%; 97.5% confidence interval: 3.5%-22.7%) vs mailed letter outreach.

Telephone and secure messaging were more effective than mailed letter outreach for de-implementing outdated colonoscopy surveillance recommendations among individuals with a history of low-risk adenomas in an integrated healthcare setting. (ClinicalTrials.gov, Number: NCT05389397).

To estimate the impact on clinical outcomes and healthcare resource use from recommending that patients with 1-2 low-risk adenomas (LRAs) return to routine fecal immunochemical test (FIT) screening instead of surveillance colonoscopy, from a Canadian provincial healthcare system perspective.

The OncoSim-Colorectal microsimulation model simulated average-risk individuals eligible for FIT-based colorectal cancer (CRC) screening in Alberta, Canada. We simulated two surveillance strategies that applied to individuals with 1-2 LRAs (<10 mm) removed as part of the average risk CRC screening program: (a) Surveillance colonoscopy (status quo) and (b) return to FIT screening (new strategy); both at 5 years after polypectomy. A 75 ng/mL FIT positivity threshold was used in the base case. The simulations projected average annual CRC outcomes and healthcare resource use from 2023 to 2042. We conducted alternative scenarios and sensitivity analyses on key variables.

Returning to FIT screening (versus surveillance colonoscopy) after polypectomy was projected to have minimal impact on long-term CRC incidence and deaths (not statistically significant). There was a projected decrease of one (4%) major bleeding event and seven (5%) perforation events per year. There was a projected increase of 4800 (1.5%) FIT screens, decrease of 3900 (5.1%) colonoscopies, and a decrease of $3.4 million (1.2%) in total healthcare costs per year, on average. The annual colonoscopies averted and healthcare cost savings increased over time. Results were similar in the alternative scenarios and sensitivity analyses.

Returning to FIT screening would have similar clinical outcomes as surveillance colonoscopy but could reduce colonoscopy demand and healthcare costs.

Prevalence of colonoscopy (CS) is an important countermeasure against colorectal cancer (CRC). In this study, we used large-scale data for a comparison of CS with esophagogastroduodenoscopy (EGD) in Japan.

This was a retrospective descriptive study. Commercially anonymized patient data were collected from various health insurance societies (JMDC, Inc. Tokyo, Japan) generated from the insurance registry, receipts (inpatient, outpatient, and prescription), and health checkup data. The data also included healthy subjects who had never been examined in a hospital. The data of 2,760,048 persons who were 50-75 years old during January 2012-December 2019 were extracted from the original data source. The annual rate, the prevalence rate (frequency of those undergoing at least one endoscopy during the period), and the percentage of repeaters (undergoing endoscopy at least twice during the period) of CS were calculated and compared to those of EGD.

The annual rates in 2012/2015/2019 were 3.4%/4.5%/5.3% for CS, respectively, and increased gradually from 2012 to 2019. Those rates were 7.0%/7.9%/7.4% for EGD, respectively, and did not increase. The prevalence rates of CS and EGD were 25.3% and 36.2%, respectively, among the 137,246 participants over 8 years. The prevalence rates of individuals in their 50 s/60 s/70 s were 23.0%/25.9%/31.4% for CS and 33.0%/37.6%/40.7% for EGD, respectively. The proportions of males/females were 27.9%/20.7% for CS, and 36.4%/35.8% for EGD, respectively. The repeat rates of CS and EGD were 40.3% and 44.8%, respectively, over 8 years.

Using large-scale data, we determined the status of CS and EGD in Japan.

Incidental colorectal fluorodeoxyglucose (FDG) uptake, observed during positron emission tomography/computed tomography (PET/CT) scans, attracts particular attention due to its potential to represent both benign and pre-malignant/malignant lesions. Early detection and excision of these lesions are crucial for preventing cancer development and reducing mortality. This research aims to evaluate the correlation between incidental colorectal FDG uptake on PET/CT with colonoscopic and histopathological results.

Retrospective analysis was performed on data from all patients who underwent PET/CT between December 2019 and December 2023 in our hospital. The study included 79 patients with incidental colonic FDG uptake who underwent endoscopy. Patient characteristics, imaging parameters, and the corresponding colonoscopy and histopathological results were studied. A comparative analysis was performed among the findings from each of these modalities. The optimal cut-off value of SUVmax for 18F-FDG PET/CT diagnosis of premalignant and malignant lesions was determined by receiver operating characteristic (ROC) curves. The area under the curve (AUC) of SUVmax and the combined parameters of SUVmax and colonic wall thickening (CWT) were analyzed.

Among the 79 patients with incidental colorectal FDG uptake, histopathology revealed malignancy in 22 (27.9%) patients and premalignant polyps in 22 (27.9%) patients. Compared to patients with benign lesions, patients with premalignant and malignant lesions were more likely to undergo a PET/CT scan for primary evaluation (p = 0.013), and more likely to have focal GIT uptake (p = 0.001) and CWT (p = 0.001). A ROC curve analysis was made and assesed a cut-off value of 7.66 SUVmax (sensitivity: 64.9% and specificity: 82.4%) to distinguish premalignant and malignant lesions from benign lesions. The AUCs of the SUVmax and the combined parameters of SUVmax and CWT were 0.758 and 0.832 respectively.

For patients undergo PET/CT for primary evaluation, imaging features of colorectal focal FDG uptake and CWT were more closely associated with premalignant and malignant lesions. The SUVmax helps determine benign and premalignant/malignant lesions of the colorectum. Moreover, the combination of SUVmax and CWT parameters have higher accuracy in estimating premalignant and malignant lesions than SUVmax.

One goal of colorectal cancer (CRC) screening is to prevent CRC incidence by removing precancerous colonic polyps, which are detected in up to 50% of screening examinations. Yet, the lifetime risk of CRC is 3.9%-4.3%, so it is clear that most of these individuals with polyps would not develop CRC in their lifetime. It is, therefore, a challenge to determine which individuals with polyps will benefit from follow-up, and at what intervals. There is some evidence that individuals with advanced polyps, based on size and histology, benefit from intensive surveillance. However, a large proportion of individuals will have small polyps without advanced histologic features (ie, "nonadvanced"), where the benefits of surveillance are uncertain and controversial. Demand for surveillance will further increase as more polyps are detected due to increased screening uptake, recent United States recommendations to expand screening to younger individuals, and emergence of polyp detection technology. We review the current understanding and clinical implications of the natural history, biology, and outcomes associated with various categories of colon polyps based on size, histology, and number. Our aims are to highlight key knowledge gaps, specifically focusing on certain categories of polyps that may not be associated with future CRC risk, and to provide insights to inform research priorities and potential management strategies. Optimization of CRC prevention programs based on updated knowledge about the future risks associated with various colon polyps is essential to ensure cost-effective screening and surveillance, wise use of resources, and inform efforts to personalize recommendations.

The World Endoscopy Organization (WEO) recommends that endoscopy units implement a process to identify postcolonoscopy colorectal cancer (PCCRC). The aims of this study were to assess the 3-year PCCRC rate and to perform root-cause analyses and categorization in accordance with the WEO recommendations.

Cases of colorectal cancers (CRCs) in a tertiary care center were retrospectively included from January 2018 to December 2019. The 3-year and 4-year PCCRC rates were calculated. A root-cause analysis and categorization of PCCRCs (interval and type A, B, C noninterval PCCRCs) were performed. The level of agreement between two expert endoscopists was assessed.

A total of 530 cases of CRC were included. A total of 33 were deemed PCCRCs (age 75.8±9.5 years; 51.5% women). The 3-year and 4-year PCCRC rates were 3.4% and 4.7%, respectively. The level of agreement between the two endoscopists was acceptable either for the root-cause analysis (k=0.958) or for the categorization (k=0.76). The most plausible explanations of the PCCRCs were 8 "likely new PCCRCs", 1 (4%) "detected, not resected", 3 (12%) "detected, incomplete resection", 8 (32%) "missed lesion, inadequate examination", and 13 (52%) "missed lesion, adequate examination". Most PCCRCs were deemed noninterval Type C PCCRCs (N=17, 51.5%).

WEO recommendations for root-cause analysis and categorization are useful to detect areas for improvement. Most PCCRCs were avoidable and were likely due to missed lesions during an otherwise adequate examination.

The English Bowel Cancer Screening Programme detects colorectal cancers and premalignant polyps in a faecal occult blood test-positive population. The aim of this work is to describe the detection rates and characteristics of adenomas within the programme, identify predictive factors influencing the presence or absence of carcinoma within adenomas and identify the factors predicting the presence of advanced colonic neoplasia in different colon segments.

The Bowel Cancer Screening System was retrospectively searched for polyps detected during colonoscopies between June 2006 and June 2012, at which time a guaiac test was being used. Data on size, location and histological features were collected, and described. Univariate and multivariate analyses were used to determine the significant factors influencing the development of carcinoma within an adenoma.

A total of 229 419 polyps were identified; after exclusions 136 973 adenomas from 58 334 patients were evaluated. Over half were in the rectum or sigmoid colon. Subcentimetre adenomas accounted for 69.8% of the total. The proportion of adenomas containing advanced histological features increased with increasing adenoma size up to 35 mm, then plateaued. A focus of carcinoma was found in 2282 (1.7%) adenomas, of which 95.6% were located distally. Carcinoma was identified even in diminutive adenomas (0.1%). The proportion of adenomas containing cancer was significantly higher in women than men (2.0% vs. 1.5%, p < 0.001).

This national, prospectively captured dataset adds robust information about histological features of adenomas that convey an increased risk for colorectal cancer, and identifies caecal adenomas, high-grade dysplasia, increasing adenoma size, distal location and female sex as independent risk factors associated with carcinoma.

Individuals with a family history of colorectal cancer (CRC) may benefit from early screening with colonoscopy or immunologic fecal occult blood testing (iFOBT). We systematically evaluated the benefit-harm trade-offs of various screening strategies differing by screening test (colonoscopy or iFOBT), interval (iFOBT: annual/biennial; colonoscopy: 10-yearly) and age at start (30, 35, 40, 45, 50 and 55 years) and end of screening (65, 70 and 75 years) offered to individuals identified with familial CRC risk in Germany. A Markov-state-transition model was developed and used to estimate health benefits (CRC-related deaths avoided, life-years gained [LYG]), potential harms (eg, associated with additional colonoscopies) and incremental harm-benefit ratios (IHBR) for each strategy. Both benefits and harms increased with earlier start and shorter intervals of screening. When screening started before age 50, 32-36 CRC-related deaths per 1000 persons were avoided with colonoscopy and 29-34 with iFOBT screening, compared to 29-31 (colonoscopy) and 28-30 (iFOBT) CRC-related deaths per 1000 persons when starting age 50 or older, respectively. For iFOBT screening, the IHBRs expressed as additional colonoscopies per LYG were one (biennial, age 45-65 vs no screening), four (biennial, age 35-65), six (biennial, age 30-70) and 34 (annual, age 30-54; biennial, age 55-75). Corresponding IHBRs for 10-yearly colonoscopy were four (age 55-65), 10 (age 45-65), 15 (age 35-65) and 29 (age 30-70). Offering screening with colonoscopy or iFOBT to individuals with familial CRC risk before age 50 is expected to be beneficial. Depending on the accepted IHBR threshold, 10-yearly colonoscopy or alternatively biennial iFOBT from age 30 to 70 should be recommended for this target group.

Data on post-colonoscopy colorectal cancers (PCCRCs) after fecal occult blood test (FOBT)-positive colonoscopies is scarce (guaiac-based (gFOBT) or fecal immunochemical test (FIT)).

Evaluate the prevalence and characteristics of PCCRCs in the French gFOBT CRC screening program.

Retrospective population-based cohort study of all gFOBT-positive colonoscopies performed among individuals aged 50-74 between 2003 and 2014 within the CRC screening program organized in the Haut-Rhin (Alsace, France). The main outcome was PCCRC-3y rate. Adenoma detection rates (ADRs) calculated on gFOBT-positive colonoscopies were compared to those calculated on FIT-positive colonoscopies performed by the same gastroenterologists.

Overall, 9106 gFOBT-positive colonoscopies performed by 36 gastroenterologists were included. Sixteen PCCRC-3y and 31 PCCRC-5y were diagnosed (68.8 % and 58.1 % were true interval PCCRCs respectively). The unadjusted PCCRC-3y rate was 2.4 % [95 % confidence interval (CI) 1.4 %-3.9 %]. The risk for PCCRC-5y was significantly higher when the gastroenterologist's ADR was <35 % compared to ≥35 % (HR 2.17 [95 %CI 1.19-3.93]). The mean absolute difference for ADR between gFOBT- and FIT-positive colonoscopies was 16.3 % in favor of FIT-positive colonoscopies.

PCCRC-3y prevalence was low, estimated at 2.4 %. We suggest that the minimum standard for ADR in gFOBT- and FIT-positive colonoscopies should be set at 35 % and 50 % to 55 % respectively, in the French screening program.

 In the Dutch colorectal (CRC) screening program, fecal immunochemical test (FIT)-positive individuals are referred for colonoscopy. If no relevant findings are detected at colonoscopy, individuals are reinvited for FIT screening after 10 years. We aimed to assess CRC risk after a negative colonoscopy in FIT-positive individuals.

 In this cross-sectional cohort study, data were extracted from the Dutch national screening information system. Participants with a positive FIT followed by a negative colonoscopy between 2014 and 2018 were included. A negative colonoscopy was defined as a colonoscopy during which no more than one nonvillous, nonproximal adenoma < 10 mm or serrated polyp < 10 mm was found. The main outcome was interval post-colonoscopy CRC (iPCCRC) risk. iPCCRC risk was reviewed against the risk of interval CRC after a negative FIT (FIT IC) with a 2-year screening interval.

 35 052 FIT-positive participants had a negative colonoscopy and 24 iPCCRCs were diagnosed, resulting in an iPCCRC risk of 6.85 (95 %CI 4.60-10.19) per 10 000 individuals after a median follow-up of 1.4 years. After 2.5 years of follow-up, age-adjusted iPCCRC risk was approximately equal to FIT IC risk at 2 years.

 Risk of iPCCRC within a FIT-based CRC screening program was low during the first years after colonos-copy but, after 2.5 years, was the same as the risk in FIT-negative individuals at 2 years, when they are reinvited for screening. Colonoscopy quality may therefore require further improvement and FIT screening interval may need to be reduced after negative colonoscopy.

Current clinical guidelines recommend that a baseline finding of advanced colorectal neoplasia (ACN) should be followed-up within 1-3 years.

We compared the recurrence rate of ACN at 1 year vs. 3 years among individuals with ACN detected and polypectomised at baseline colonoscopy.

We extracted data from eligible patients in a Chinese population database from 2008 to 2018. The outcome variables included recurrence of advanced adenoma and advanced neoplasia, respectively, at follow-up colonoscopy. Binary logistic regression modeling was constructed to examine the association between length of surveillance and the outcome variables, controlling for risk factors of colorectal cancer, including age, gender, smoking, alcohol drinking, body mass index and chronic diseases.

We included 147,270 subjects who have received a baseline colonoscopy from our dataset. They were aged 69.3 years and 59.7% of them were male subjects. The crude 1-year and 3-year recurrence rate of ACN was 7.57% and 7.74%. From a binary logistic regression model, individuals with surveillance colonoscopy performed at 3 years did not have significantly higher recurrence rate of ACN than those followed-up at 1 year.

No statistically significantly difference in recurrence of ACN between individuals who received workup at 1vs. 3 years. These findings support a 3-year surveillance period after baseline ACN was polypectomised.

Current morphologic features defining advanced adenomas (size ≥10 mm, high-grade dysplasia or ≥25% villous component) cannot optimally distinguish individuals at high risk or low risk of metachronous colorectal cancer (me-CRC), which may result in suboptimal surveillance. Certain DNA copy-number alterations (CNAs) are associated with adenoma-to-carcinoma progression. We aimed to evaluate whether these molecular features can better predict an individual's risk of me-CRC than the morphologic advanced adenoma features.In this nested case-control study, 529 individuals with a single adenoma at first colonoscopy were selected from a Norwegian adenoma cohort. DNA copy-number profiles were determined, by low-coverage whole-genome sequencing. Prevalence of CNAs in advanced and non-advanced adenomas and its association (OR) with me-CRC was assessed. For the latter, cases (with me-CRC) were matched to controls (without me-CRC) on follow-up, age and sex.CNAs associated with adenoma-to-carcinoma progression were observed in 85/267 (32%) of advanced adenomas and in 27/262 (10%) of non-advanced adenomas. me-CRC was statistically significantly associated, also after adjustment for other variables, with age at baseline [OR, 1.14; 95% confidence interval CI), 1.03-1.26; P = 0.012], advanced adenomas (OR, 2.46; 95% CI, 1.50-4.01; P < 0.001) and with the presence of ≥3 DNA copy-number losses (OR, 1.90; 95% CI. 1.02-3.54; P = 0.043).Molecularly-defined high-risk adenomas were associated with me-CRC, but the association of advanced adenoma with me-CRC was stronger.

Identifying new biomarkers may improve prediction of me-CRC for individuals with adenomas and optimize surveillance intervals to reduce risk of colorectal cancer and reduce oversurveillance of patients with low risk of colorectal cancer. Use of DNA CNAs alone does not improve prediction of me-CRC. Further research to improve risk classification is required.

Recently, updated guidelines for post-polypectomy surveillance have been published by the U.S. Multi-Society Task Force (USMSTF), the British Society of Gastroenterology/Association of Coloproctology of Great Britain and Ireland/Public Health England (BSG/ACPGBI/PHE), the European Society of Gastrointestinal Endoscopy (ESGE), the Japan Gastroenterological Endoscopy Society (JGES), and the Korean Multi-Society Taskforce Committee. This review summarizes and compares the updated recommendations of these 5 guidelines. There are some differences between the guidelines for the recommended post-polypectomy surveillance intervals. In particular, there are prominent differences between the guidelines for 1-4 tubular adenomas < 10 mm with low-grade dysplasia (nonadvanced adenomas [NAAs]) and tubulovillous or villous adenomas. The USMSTF, JGES, and Korean guidelines recommend colonoscopic surveillance for patients with 1-4 NAAs and those with tubulovillous or villous adenomas, whereas the BSG/ACPGBI/PHE and ESGE guidelines do not recommend endoscopic surveillance for such patients. Surveillance recommendations for patients with serrated polyps (SPs) are limited. Although the USMSTF guidelines provide specific recommendations for patients who have undergone SPs removal, these are weak and based on very lowquality evidence. Future studies should examine this topic to better guide the surveillance recommendations for patients with SPs. For countries that do not have separate guidelines, we hope that this review article will help select the most appropriate guidelines as per each country's healthcare environment.

Colorectal cancer is a significant global health concern, ranking as the second most deadly and third most common cancer worldwide. Early detection and removal of precancerous lesions play a crucial role in preventing cancer development and reducing mortality. Since FDG uptake is not specific for malignancy, incidental increased FDG uptake in the gastrointestinal tract may be challenging to interpret and may require further colonoscopic examination. This study aimed to investigate the features associated with malignant and premalignant pathology in patients with incidental colonic FDG uptake and determine the necessity of colonoscopy for each FDG uptake.

Retrospective analysis was performed on data from patients who underwent colonoscopies between January 2016 and December 2021. Patients with FDG uptake in known colorectal malignancy regions were excluded. The study included 56 patients with incidental colonic FDG uptake. PET/CT images were visually and quantitatively analyzed, and the corresponding colonoscopy and histopathological results were recorded. Statistical analyses were conducted to evaluate the relationship between FDG uptake patterns, SUVmax values, and histopathological diagnoses. Colonoscopic findings were categorized as malignancy, polyps, and non-neoplastic lesions.

Among the 56 patients with incidental colonic FDG uptake, 36 lesions were identified, and histopathology revealed malignancy in 10 (17.9%) patients and premalignant polyps in the 26 (46.4%) cases. Focal FDG uptake with corresponding wall thickening or soft tissue density on CT was associated with a higher likelihood of premalignant or malignant lesions. The SUVmax values demonstrated a significant difference between negative findings and polyps/malignancies. However, no significant difference was observed between malignant and premalignant lesions. A ROC curve analysis was made and assesed a cut-off value of 11.1 SUVmax (sensitivity: 83.3% and specificity: 90%) to distinguish premalignant or malignant lesions from non-malignant lesions.

Incidental colonic FDG uptake with a focal pattern and corresponding CT findings were more likely to indicate premalignant or malignant lesions. SUVmax values were helpful in predicting the presence of pathological findings, but histopathological verification remains necessary for a definitive diagnosis. These findings contribute to our understanding of the clinical implications of incidental colonic FDG uptake and highlight the importance of follow-up colonoscopy for further evaluation.

The virtual scale endoscope (VSE) is a newly introduced endoscope that helps endoscopists in measuring colorectal polyp size (CPS) during colonoscopy by displaying a virtual scale. This study aimed to determine the usefulness of the VSE for CPS measurement and the educational benefit of using VSE images to improve CPS estimation accuracy.

This study included 42 colorectal polyps in 26 patients treated at Hiroshima University Hospital. In study 1, CPS measured using a VSE before endoscopic mucosal resection was compared with CPS measured on resected specimens, and the agreement between the two measurement methods was evaluated via Bland-Altman analysis. In study 2, 14 endoscopists (5 beginners, 5 intermediates, and 4 experts) took a pre-test to determine the size of 42 polyps. After the pre-test, a lecture on CPS measurement using VSE images was given. One month later, the endoscopists took a post-test to compare CPS accuracy before and after the lecture.

In study 1, Bland-Altman analysis revealed no fixed or proportional errors. The mean bias ±95% limits of agreement (±1.96 standard deviations) of the measurement error was -0.05 ± 0.21 mm, indicating that the agreement between two measurement methods was sufficient. In study 2, the accuracy of CPS measurement was significantly higher among beginners (59.5% vs. 26.7%, p < 0.01) and intermediates (65.2% vs. 44.3%, p < 0.05) in the post-test than in the pre-test.

The VSE accurately measures CPS before resection, and its images are useful teaching tools for beginner and intermediate endoscopists.

Measurement of colorectal polyp size during endoscopy is mainly performed visually. In this work, we propose a novel polyp size measurement system (Poseidon) based on artificial intelligence (AI) using the auxiliary waterjet as a measurement reference.

Visual estimation, biopsy forceps-based estimation, and Poseidon were compared using a computed tomography colonography-based silicone model with 28 polyps of defined sizes. Four experienced gastroenterologists estimated polyp sizes visually and with biopsy forceps. Furthermore, the gastroenterologists recorded images of each polyp with the waterjet in proximity for the application of Poseidon. Additionally, Poseidon's measurements of 29 colorectal polyps during routine clinical practice were compared with visual estimates.

In the silicone model, visual estimation had the largest median percentage error of 25.1 % (95 %CI 19.1 %-30.4 %), followed by biopsy forceps-based estimation: median 20.0 % (95 %CI 14.4 %-25.6 %). Poseidon gave a significantly lower median percentage error of 7.4 % (95 %CI 5.0 %-9.4 %) compared with other methods. During routine colonoscopies, Poseidon presented a significantly lower median percentage error (7.7 %, 95 %CI 6.1 %-9.3 %) than visual estimation (22.1 %, 95 %CI 15.1 %-26.9 %).

In this work, we present a novel AI-based method for measuring colorectal polyp size with significantly higher accuracy than other common sizing methods.

BACKGROUND : Serrated lesions are potential colorectal cancer precursors. This study evaluated the presence of total metachronous advanced neoplasia (T-MAN) at follow-up in patients with index serrated lesions compared with a matched cohort without serrated lesions. METHODS : Patients aged 45-74 years with serrated lesions were matched 2:1 by sex, age, synchronous polyps, and timing of index colonoscopy, to patients without serrated lesions. The primary outcome was T-MAN (advanced adenoma or high-risk serrated lesion) at follow-up. Secondary outcomes included presence of T-MAN stratified by synchronous polyps and serrated lesion characteristics. RESULTS : 1425 patients were included (475 patients, 642 serrated lesions; 950 controls; median follow-up 2.9 versus 3.6 years). Patients with serrated lesions had greater risk of T-MAN than those without (hazard ratio [HR] 6.1, 95 %CI 3.9-9.6). Patients with serrated lesions and high-risk adenoma (HRA) had higher risk of T-MAN than those with HRA alone (HR 2.6, 95 %CI 1.4-4.7); similarly, patients with serrated lesions plus low-risk adenoma (LRA) had higher risk than those with LRA alone (HR 7.0, 95 %CI 2.8-18.4), as did patients with serrated lesions without adenoma compared with no adenoma (HR 14.9, 95 %CI 6.5-34.0). Presence of proximal sessile serrated lesion (SSL; HR 9.3, 95 %CI 5.4-15.9), large SSL (HR 17.8, 95 %CI 7.4-43.3), and proximal large SSL (HR 25.0, 95 %CI 8.8-71.3), but not distal SSL, were associated with greater risk for T-MAN. CONCLUSION : Patients with serrated lesions had higher risk for T-MAN regardless of synchronous adenomas. Patients with serrated lesions and HRA, and those with large or proximal SSLs, were at greatest risk.

The serrated neoplasia pathway constitutes an "alternative route" to colorectal cancer (CRC), and sessile serrated lesions with dysplasia (SSLDs) are an intermediate step between sessile serrated lesions (SSLs) and invasive CRC in this pathway. While SSLs show indolent growth before becoming dysplastic (> 10-15 years), SSLDs are considered to rapidly progress to either immunogenic microsatellite instable-high (MSI-H) CRC (presumably 75% of cases) or mesenchymal microsatellite stable (MSS) CRC. Their flat shapes and the relatively short window of this intermediate state make it difficult to detect and diagnose SSLDs; thus, these lesions are potent precursors of post-colonoscopy/interval cancers. Confusing terminology and the lack of longitudinal observation data of serrated polyps have hampered the accumulation of knowledge about SSLDs; however, a growing body of evidence has started to clarify their characteristics and biology. Together with recent efforts to incorporate terminology, histological studies of SSLDs have identified distinct dysplastic patterns and revealed alterations in the tumor microenvironment (TME). Molecular studies at the single-cell level have identified distinct gene alterations in both the epithelium and the TME. Mouse serrated tumor models have demonstrated the importance of TME in disease progression. Advances in colonoscopy provide clues to distinguish pre-malignant from non-malignant-SSLs. Recent progress in all aspects of the field has enhanced our understanding of the biology of SSLDs. The aim of this review article was to assess the current knowledge of SSLDs and highlight their clinical implications.

Because post-polypectomy surveillance uses a growing proportion of colonoscopy capacity, more targeted surveillance is warranted. We therefore compared surveillance burden and cancer detection using 3 different adenoma classification systems.

In a case-cohort study among individuals who had adenomas removed between 1993 and 2007, we included 675 individuals with colorectal cancer (cases) diagnosed a median of 5.6 years after adenoma removal and 906 randomly selected individuals (subcohort). We compared colorectal cancer incidence among high- and low-risk individuals defined according to the traditional (high-risk: diameter ≥10 mm, high-grade dysplasia, villous growth pattern, or 3 or more adenomas), European Society of Gastrointestinal Endoscopy (ESGE) 2020 (high-risk: diameter ≥10 mm, high-grade dysplasia, or 5 or more adenomas), and novel (high-risk: diameter ≥20 mm or high-grade dysplasia) classification systems. For the different classification systems, we calculated the number of individuals recommended frequent surveillance colonoscopy and estimated number of delayed cancer diagnoses.

Four hundred and thirty individuals with adenomas (52.7%) were high risk based on the traditional classification, 369 (45.2%) were high risk based on the ESGE 2020 classification, and 220 (27.0%) were high risk based on the novel classification. Using the traditional, ESGE 2020, and novel classifications, the colorectal cancer incidences per 100,000 person-years were 479, 552, and 690 among high-risk individuals, and 123, 124, and 179 among low-risk individuals, respectively. Compared with the traditional classification, the number of individuals who needed frequent surveillance was reduced by 13.9% and 44.2%, respectively, and 1 (3.4%) and 7 (24.1%) cancer diagnoses were delayed using the ESGE 2020 and novel classifications.

Using the ESGE 2020 and novel risk classifications will substantially reduce resources needed for colonoscopy surveillance after adenoma removal.

There is increasing demand for colorectal cancer (CRC) surveillance, but healthcare capacity is limited. The burden on colonoscopy resources could be reduced by personalizing surveillance frequency using the fecal immunochemical test (FIT). This study will determine the safety, cost-effectiveness, and patient acceptance of using FIT to extend surveillance colonoscopy intervals for individuals at elevated risk of CRC.

This multicenter, prospective, randomized controlled trial will invite participants who are scheduled for surveillance colonoscopy (due to a personal history of adenomas or a family history of CRC) and who have returned a low fecal hemoglobin (< 2 μg Hb/g feces; F-Hb) using a two-sample FIT (OC Sensor, Eiken Chemical Company) in the prior 3 years. A total of 1344 individuals will be randomized to either surveillance colonoscopy as scheduled or delayed by 1 or 2 years for individuals originally recommended a 3- or 5-year surveillance interval, respectively. The primary endpoint is incidence of advanced neoplasia (advanced adenoma and/or CRC). Secondary endpoints include cost-effectiveness and consumer acceptability of extending surveillance intervals, determined using surveys and discrete choice experiments.

This study will establish the safety, cost-effectiveness, and acceptability of utilizing a low FIT Hb result to extend colonoscopy surveillance intervals in a cohort at elevated risk for CRC. This personalized approach to CRC surveillance will lead to a reduction in unnecessary colonoscopies, increases in healthcare savings, and a better patient experience.  TRIAL REGISTRATION: Registration was approved on December 9, 2019 with the Australian New Zealand Clinical Trials Registry ANZCTR 12619001743156.

Limited data exist regarding the role of meat consumption in early-stage colorectal carcinogenesis. We examined associations of red and processed meat intake with screen-detected colorectal lesions in immunochemical fecal occult blood test (FIT)-positive participants, enrolled in the Norwegian CRCbiome study during 2017-2021, aged 55-77 years. Absolute and energy-adjusted intakes of red and processed meat (combined and individually) were assessed using a validated, semi-quantitative FFQ. Associations between meat intake and screen-detected colorectal lesions were examined using multinomial logistic regression analyses with adjustment for key covariates. Of 1162 participants, 319 presented with advanced colorectal lesions at colonoscopy. High v. low energy-adjusted intakes of red and processed meat combined, as well as red meat alone, were borderline to significantly positively associated with advanced colorectal lesions (OR of 1·24 (95 % CI 0·98, 1·57) and 1·34 (95 % CI 1·07, 1·69), respectively). A significant dose-response relationship was also observed for absolute intake levels (OR of 1·32 (95 % CI 1·09, 1·60) per 100 g/d increase in red and processed meat). For processed meat, no association was observed between energy-adjusted intakes and advanced colorectal lesions. A significant positive association was, however, observed for participants with absolute intake levels ≥ 100 v. < 50 g/d (OR of 1·19 (95 % CI 1·09, 1·31)). In summary, high intakes of red and processed meat were associated with presence of advanced colorectal lesions at colonoscopy in FIT-positive participants. The study demonstrates a potential role of dietary data to improve the performance of FIT-based screening.

Serrated lesions (SL) have been associated with significant risks of developing colorectal cancer (CRC). Data on synchronous findings after SL detection during colonoscopy is limited. Study aim was to evaluate the rate of synchronous advanced neoplasia (S-AN) and synchronous CRC (S-CRC) in colonoscopies where SLs were detected.

We conducted a retrospective study of screening aged patients 45-74year with colorectal SL (sessile serrated polyp [SSP] or traditional serrated adenoma [TSA]) detected during an elective colonoscopy. Primary outcome was risk of S-AN in patients with SL. Secondary outcomes included risk of S-AN or S-CRC stratified by SL characteristics.

The study included 1262 patients with 1649 SLs (1214 with SSPs and 48 with TSAs). 47.2% were female and 22.9% of exams were screening colonoscopies, 48.2% surveillance, 28.9% diagnostic. The overall rates of S-AN and S-CRC were 15.1% and 1.3%, respectively. Presence of SSPs ≥ 10 mm was associated with higher rates of S-AN, (18.1 vs. 12.2%, Odds-Ratio [OR] = 1.61 [95% Confidence Interval [CI] 1.17-2.23], p = 0.004). SSP dysplasia was predictive of S-AN, (30.3 vs 14.1%, OR = 2.68 [95%CI 1.24-5.78], p = 0.012) but not S-CRC. SSP number (≥ 3) and location (proximal) were not predictors of S-AN or S-CRC.

Patients with SLs are at high-risk of S-AN and S-CRC. Findings of SSPs ≥ 10 mm and SSP dysplasia are associated with high-risk of S-AN. Endoscopists should exercise heightened vigilance for synchronous findings when SLs are detected, especially SSPs ≥ 10 mm or when bowel preparation is suboptimal. Studies contrasting synchronous risk of other polyp types are needed to confirm these results.

Among the characteristics of high-risk adenomas (HRAs), some may predict a higher risk of metachronous advanced lesions. Our aim was to assess which HRA characteristics are associated with high risk of metachronous colorectal cancer (CRC) or advanced adenomas (AAs).

We systematically searched Pubmed, EMBASE, and Cochrane for cohort studies and clinical trials of CRC or AA incidence at surveillance stratified by baseline lesion size, histology, and multiplicity. We calculated pooled relative risks (RRs) using a random-effects model. Heterogeneity was assessed with the I² statistic.

Fifty-five studies were included, with 936,540 patients with mean follow-up 5.4 ± 2.9 years. CRC incidence per 1000 person-years was 2.6 (2.1-3.0) for adenomas ≥20 mm, 2.7 (2.2-3.2) for high-grade dysplasia (HGD), 2.0 (1.8-2.3) for villous component, 0.8 (0.1-1.4) for ≥5 adenomas, 1.0 (0.7-1.2) for ≥3 adenomas. Metachronous CRC risk was higher in adenomas ≥20 mm vs 10 to 19 mm (RR, 2.08; 95% confidence interval [CI], 1.20-3.61), HGD vs low-grade dysplasia (RR, 2.89; 95% CI, 1.88-4.44), villous vs tubular (RR, 1.75; 95% CI, 1.33-2.31). No significant differences in CRC risk were found in ≥3 adenomas vs 1 to 2 (RR, 1.24; 95% CI, 0.84-1.83), nor in ≥5 adenomas vs 3 to 4 (RR, 0.79; 95% CI, 0.30-2.11). Compared with normal colonoscopy, RR for CRC risk was 2.61 (95% CI, 2.06-3.32) for ≥10mm, 6.62 (95% CI, 4.60-9.52) for HGD, 3.58 (95% CI, 2.24-5.73) for villous component, and 2.03 (95% CI, 1.40-2.94) for ≥3 adenomas. Similar trends were seen for metachronous AAs.

Metachronous CRC risk is highest in patients with baseline adenomas with ≥20 mm or HGD. Multiplicity does not seem to be associated with substantially higher CRC risk in the near term.

Measuring adenoma detection rates (ADRs) at the population level is challenging because pathology reports are often reported in an unstructured format; further, there is significant variation in reporting methods across institutions. Natural language processing (NLP) can be used to extract relevant information from text-based records. We aimed to develop and validate an NLP algorithm to identify colorectal adenomas that could be used to report ADR at the population level in Ontario, Canada.

The sampling frame included pathology reports from all colonoscopies performed in Ontario in 2015 and 2016. Two random samples of 450 and 1000 reports were selected as the training and validation sets, respectively. Expert clinicians reviewed and classified reports as adenoma or other. The training set was used to develop an NLP algorithm (to identify adenomas) that was evaluated using the validation set. The NLP algorithm test characteristics were calculated using expert review as the reference. We used the algorithm to measure ADR for all endoscopists in Ontario in 2019.

The 1450 pathology reports were derived from 62 laboratories, 266 pathologists, and 532 endoscopists. In the training set, the NLP algorithm for any adenoma had a sensitivity of 99.60% (95% confidence interval (CI), 97.77-99.99), specificity of 99.01% (95% CI, 96.49-99.88), positive predictive value of 99.19% (95% CI, 97.12-99.90), and F1 score of .99. Similar results were obtained for the validation set. The median ADR was 33% (interquartile range, 26%-40%).

When we used a population-based sample from Ontario, our NLP algorithm was highly accurate and was used at the system level to measure ADR.

Assessment of the anatomical colorectal segment of polyps during colonoscopy is important for treatment and follow-up strategies, but is largely operator dependent. This feasibility study aimed to assess whether, using images of a magnetic endoscope imaging (MEI) positioning device, a deep learning approach can be useful to objectively divide the colorectum into anatomical segments.

Models based on the VGG-16 based convolutional neural network architecture were developed to classify the colorectum into anatomical segments. These models were pre-trained on ImageNet data and further trained using prospectively collected data of the POLAR study in which endoscopists were using MEI (3930 still images and 90,151 video frames). Five-fold cross validation with multiple runs was used to evaluate the overall diagnostic accuracies of the models for colorectal segment classification (divided into a 5-class and 2-class colorectal segment division). The colorectal segment assignment by endoscopists was used as the reference standard.

For the 5-class colorectal segment division, the best performing model correctly classified the colorectal segment in 753 of the 1196 polyps, corresponding to an overall accuracy of 63%, sensitivity of 63%, specificity of 89% and kappa of 0.47. For the 2-class colorectal segment division, 1112 of the 1196 polyps were correctly classified, corresponding to an accuracy of 93%, sensitivity of 93%, specificity of 90% and kappa of 0.82.

The diagnostic performance of a deep learning approach for colorectal segment classification based on images of a MEI device is yet suboptimal (clinicaltrials.gov: NCT03822390).