Comprehensive review of publicly available colonoscopic imaging databases for artificial intelligence research: availability, accessibility, and usability.

BACKGROUND AND AIMS: Publicly available databases containing colonoscopic imaging data are valuable resources for artificial intelligence (AI) research. Currently, little is known regarding the available number and content of these databases. This review aimed to describe the availability, accessibility, and usability of publicly available colonoscopic imaging databases, focusing on polyp detection, polyp characterization, and quality of colonoscopy. METHODS: A systematic literature search was performed in MEDLINE and Embase to identify AI studies describing publicly available colonoscopic imaging databases published after 2010. Second, a targeted search using Google's Dataset Search, Google Search, GitHub, and Figshare was done to identify databases directly. Databases were included if they contained data about polyp detection, polyp characterization, or quality of colonoscopy. To assess accessibility of databases, the following categories were defined: open access, open access with barriers, and regulated access. To assess the potential usability of the included databases, essential details of each database were extracted using a checklist derived from the Checklist for Artificial Intelligence in Medical Imaging. RESULTS: We identified 22 databases with open access, 3 databases with open access with barriers, and 15 databases with regulated access. The 22 open access databases contained 19,463 images and 952 videos. Nineteen of these databases focused on polyp detection, localization, and/or segmentation; 6 on polyp characterization, and 3 on quality of colonoscopy. Only half of these databases have been used by other researcher to develop, train, or benchmark their AI system. Although technical details were in general well reported, important details such as polyp and patient demographics and the annotation process were under-reported in almost all databases. CONCLUSIONS: This review provides greater insight on public availability of colonoscopic imaging databases for AI research. Incomplete reporting of important details limits the ability of researchers to assess the usability of current databases.

Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists.

BACKGROUND : We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. METHODS : We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. RESULTS : During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). CONCLUSIONS : We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.

Computer-aided classification of colorectal segments during colonoscopy: a deep learning approach based on images of a magnetic endoscopic positioning device.

OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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).

Linked Colour imaging for the detection of polyps in patients with Lynch syndrome: a multicentre, parallel randomised controlled trial.

OBJECTIVE: Despite regular colonoscopy surveillance, colorectal cancers still occur in patients with Lynch syndrome. Thus, detection of all relevant precancerous lesions remains very important. The present study investigates Linked Colour imaging (LCI), an image-enhancing technique, as compared with high-definition white light endoscopy (HD-WLE) for the detection of polyps in this patient group. DESIGN: This prospective, randomised controlled trial was performed by 22 experienced endoscopists from eight centres in six countries. Consecutive Lynch syndrome patients ≥18 years undergoing surveillance colonoscopy were randomised (1:1) and stratified by centre for inspection with either LCI or HD-WLE. Primary outcome was the polyp detection rate (PDR). RESULTS: Between January 2018 and March 2020, 357 patients were randomised and 332 patients analysed (160 LCI, 172 HD-WLE; 6 excluded due to incomplete colonoscopies and 19 due to insufficient bowel cleanliness). No significant difference was observed in PDR with LCI (44.4%; 95% CI 36.5% to 52.4%) compared with HD-WLE (36.0%; 95% CI 28.9% to 43.7%) (p=0.12). Of the secondary outcome parameters, more adenomas were found on a patient (adenoma detection rate 36.3%; vs 25.6%; p=0.04) and a colonoscopy basis (mean adenomas per colonoscopy 0.65 vs 0.42; p=0.04). The median withdrawal time was not statistically different between LCI and HD-WLE (12 vs 11 min; p=0.16). CONCLUSION: LCI did not improve the PDR compared with HD-WLE in patients with Lynch syndrome undergoing surveillance. The relevance of findings more adenomas by LCI has to be examined further. TRIAL REGISTRATION NUMBER: NCT03344289.

Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement.

BACKGROUND : The European Society of Gastrointestinal Endoscopy (ESGE) has developed a core curriculum for high quality optical diagnosis training for practice across Europe. The development of easy-to-measure competence standards for optical diagnosis can optimize clinical decision-making in endoscopy. This manuscript represents an official Position Statement of the ESGE aiming to define simple, safe, and easy-to-measure competence standards for endoscopists and artificial intelligence systems performing optical diagnosis of diminutive colorectal polyps (1 - 5 mm). METHODS : A panel of European experts in optical diagnosis participated in a modified Delphi process to reach consensus on Simple Optical Diagnosis Accuracy (SODA) competence standards for implementation of the optical diagnosis strategy for diminutive colorectal polyps. In order to assess the clinical benefits and harms of implementing optical diagnosis with different competence standards, a systematic literature search was performed. This was complemented with the results from a recently performed simulation study that provides guidance for setting alternative competence standards for optical diagnosis. Proposed competence standards were based on literature search and simulation study results. Competence standards were accepted if at least 80 % agreement was reached after a maximum of three voting rounds. RECOMMENDATION 1: In order to implement the leave-in-situ strategy for diminutive colorectal lesions (1-5 mm), it is clinically acceptable if, during real-time colonoscopy, at least 90 % sensitivity and 80 % specificity is achieved for high confidence endoscopic characterization of colorectal neoplasia of 1-5 mm in the rectosigmoid. Histopathology is used as the gold standard.Level of agreement 95 %. RECOMMENDATION 2: In order to implement the resect-and-discard strategy for diminutive colorectal lesions (1-5 mm), it is clinically acceptable if, during real-time colonoscopy, at least 80 % sensitivity and 80 % specificity is achieved for high confidence endoscopic characterization of colorectal neoplasia of 1-5 mm. Histopathology is used as the gold standard.Level of agreement 100 %. CONCLUSION : The developed SODA competence standards define diagnostic performance thresholds in relation to clinical consequences, for training and for use when auditing the optical diagnosis of diminutive colorectal polyps.

Endoscopic full-thickness resection of T1 colorectal cancers: a retrospective analysis from a multicenter Dutch eFTR registry.

BACKGROUND: Complete endoscopic resection and accurate histological evaluation for T1 colorectal cancer (CRC) are critical in determining subsequent treatment. Endoscopic full-thickness resection (eFTR) is a new treatment option for T1 CRC < 2 cm. We aimed to report clinical outcomes and short-term results. METHODS: Consecutive eFTR procedures for T1 CRC, prospectively recorded in our national registry between November 2015 and April 2020, were retrospectively analyzed. Primary outcomes were technical success and R0 resection. Secondary outcomes were histological risk assessment, curative resection, adverse events, and short-term outcomes. RESULTS: We included 330 procedures: 132 primary resections and 198 secondary scar resections after incomplete T1 CRC resection. Overall technical success, R0 resection, and curative resection rates were 87.0 % (95 % confidence interval [CI] 82.7 %-90.3 %), 85.6 % (95 %CI 81.2 %-89.2 %), and 60.3 % (95 %CI 54.7 %-65.7 %). Curative resection rate was 23.7 % (95 %CI 15.9 %-33.6 %) for primary resection of T1 CRC and 60.8 % (95 %CI 50.4 %-70.4 %) after excluding deep submucosal invasion as a risk factor. Risk stratification was possible in 99.3 %. The severe adverse event rate was 2.2 %. Additional oncological surgery was performed in 49/320 (15.3 %), with residual cancer in 11/49 (22.4 %). Endoscopic follow-up was available in 200/242 (82.6 %), with a median of 4 months and residual cancer in 1 (0.5 %) following an incomplete resection. CONCLUSIONS: eFTR is relatively safe and effective for resection of small T1 CRC, both as primary and secondary treatment. eFTR can expand endoscopic treatment options for T1 CRC and could help to reduce surgical overtreatment. Future studies should focus on long-term outcomes.

Dye-Based Chromoendoscopy in Patients With Lynch Syndrome: An Individual Patient Data Meta-Analysis of Randomized Trials.

INTRODUCTION: The additional diagnostic value of dye-based chromoendosocpy (CE) for surveillance of patients with Lynch syndrome is subject of debate. METHODS: To clarify this debate, we performed an individual patient data meta-analysis of randomized studies that compared CE with WLE for the detection of adenomas in patients with Lynch syndrome. RESULTS: Three randomized studies comprising 533 patients were included. The adenoma detection rate was 74/265 (28%) in patients randomized to WLE compared with 83/266 (31%) in patients randomized to CE (odds ratio 1.17; 95% confidence interval 0.81-1.70). DISCUSSION: Based on low-quality evidence, CE showed no apparent increase in adenoma detection compared to WLE during surveillance of patients with Lynch syndrome.

Guidance for setting easy-to-adopt competence criteria for optical diagnosis of diminutive colorectal polyps: a simulation approach.

BACKGROUND AND AIMS: One reason the optical diagnosis strategy for diminutive colorectal polyps has not yet been implemented is that the current competence criteria (Preservation and Incorporation of Valuable Endoscopic Innovation [PIVI] initiative) are difficult to use in daily practice. To provide guidance for setting alternative easy-to-adopt competence criteria, we determined the lowest proportion of diminutive polyps that should have a correct optical diagnosis to meet the PIVI. METHODS: For this simulation study, we used datasets from 2 prospectively collected cohorts of patients who underwent colonoscopy in either a primary colonoscopy or fecal immunochemical test (FIT) screening setting. In the simulation approach, virtual endoscopists or computer-aided diagnosis systems performed optical diagnosis of diminutive polyps with a fixed diagnostic performance level (strategy) on all individuals in the cohort who had ≥1 diminutive polyp. Strategies were defined by systematically varying the proportion of correct optical diagnoses for each polyp subtype (ie, adenomas, hyperplastic polyps, sessile serrated lesions). For each strategy, we determined whether PIVI-1 (≥90% agreement with U.S. or European Society for Gastrointestinal Endoscopy [ESGE] surveillance guidelines) and PIVI-2 (≥90% negative predictive value [NPV] for neoplastic lesions in the rectosigmoid) were met using Monte Carlo sampling with 1000 repetitions, with histology as reference. RESULTS: The level of overall diagnostic accuracy to achieve the PIVI differed significantly depending on the clinical setting and guidelines used. In the colonoscopy screening setting, all diagnostic strategies in which 92% of all diminutive polyps (regardless of histology) were diagnosed correctly led to 90% or more agreement with U.S. surveillance intervals (ie, PIVI-1). For all diagnostic strategies in which ≥89% of all diminutive polyps were correctly diagnosed, at least 90% NPV was achieved (ie, PIVI-2). For the FIT screening setting, values were respectively ≥77% and ≥94%. When using ESGE guidelines, PIVI-1 was in both settings already met when 40% of all diminutive polyps were diagnosed correctly. CONCLUSIONS: In contrast to the fixed PIVI criteria, our simulation study shows that different thresholds for the proportion of correctly diagnosed diminutive polyps lead to different clinical consequences depending on guidelines and clinical setting. However, this target proportion of diminutive colorectal polyps correctly diagnosed with optical diagnosis represents easier-to-adopt competence criteria.

The long-term outcomes and natural disease course of serrated polyposis syndrome: over 10 years of prospective follow-up in a specialized center.

BACKGROUND AND AIMS: Serrated polyposis syndrome (SPS) is the most prevalent colonic polyposis syndrome known and is associated with a high risk of colorectal cancer (CRC) if left untreated. Treatment consists of clearance of the initial polyp burden, followed by lifelong stringent endoscopic surveillance. However, the long-term safety and efficacy of surveillance and the natural disease course after initial clearance have not been described in detail. METHODS: We analyzed a single-center cohort of patients with SPS with over 10 years of prospective follow-up. Outcome measures were (1) CRC incidence, (2) postcolonoscopy adverse event rates, and (3) trends in polyp recurrence during endoscopic surveillance. RESULTS: The cohort included 142 patients who underwent a median of 6 colonoscopies with a median of 47 months of prospective follow-up after initial polyp clearance. During surveillance (every 1-2 years), 1 case of CRC occurred (5-year CRC incidence, 1.0%; 95% confidence interval, 0%-2.9%). During 447 surveillance colonoscopies with 1308 polypectomies, 1 episode of postpolypectomy bleeding, 1 postpolypectomy syndrome, and no perforations occurred (adverse event rate, 0.45% per colonoscopy). During up to 9 rounds of surveillance, no upward or downward trend in polyp recurrence was observed. CONCLUSIONS: In this prospective cohort with over 10 years of follow-up, endoscopic surveillance was effective and safe, with a low risk of CRC and colonoscopy-related adverse events. Furthermore, we show that the disease course of SPS is such that the polyp burden remains more or less equal during long-term surveillance, which advocates lifelong adherence to (personalized) surveillance guidelines and discourages de-intensifying surveillance intervals after multiple rounds of surveillance.

Effects of Training and Feedback on Accuracy of Predicting Rectosigmoid Neoplastic Lesions and Selection of Surveillance Intervals by Endoscopists Performing Optical Diagnosis of Diminutive Polyps.

BACKGROUND & AIMS: Real-time differentiation of diminutive polyps (1-5 mm) during endoscopy could replace histopathology analysis. According to guidelines, implementation of optical diagnosis into routine practice would require it to identify rectosigmoid neoplastic lesions with a negative predictive value (NPV) of more than 90%, using histologic findings as a reference, and agreement with histology-based surveillance intervals for more than 90% of cases. METHODS: We performed a prospective study with 39 endoscopists accredited to perform colonoscopies on participants with positive results from fecal immunochemical tests in the Bowel Cancer Screening Program at 13 centers in the Netherlands. Endoscopists were trained in optical diagnosis using a validated module (Workgroup serrAted polypS and Polyposis). After meeting predefined performance thresholds in the training program, the endoscopists started a 1-year program (continuation phase) in which they performed narrow band imaging analyses during colonoscopies of participants in the screening program and predicted histological findings with confidence levels. The endoscopists were randomly assigned to groups that received feedback or no feedback on the accuracy of their predictions. Primary outcome measures were endoscopists' abilities to identify rectosigmoid neoplastic lesions (using histology as a reference) with NPVs of 90% or more, and selecting surveillance intervals that agreed with those determined by histology for at least 90% of cases. RESULTS: Of 39 endoscopists initially trained, 27 (69%) completed the training program. During the continuation phase, these 27 endoscopists performed 3144 colonoscopies in which 4504 diminutive polyps were removed. The endoscopists identified neoplastic lesions with a pooled NPV of 90.8% (95% confidence interval 88.6-92.6); their proposed surveillance intervals agreed with those determined by histologic analysis for 95.4% of cases (95% confidence interval 94.0-96.6). Findings did not differ between the group that did vs did not receive feedback. Sixteen endoscopists (59%) identified rectosigmoid neoplastic lesions with NPVs greater than 90% and selected surveillance intervals in agreement with those determined from histology for more than 90% of patients. CONCLUSIONS: In a prospective study following a validated training module, we found that a selected group of endoscopists identified rectosigmoid neoplastic lesions with pooled NPVs greater than 90% and accurately selected surveillance intervals for more than 90% of patients over the course of 1 year. Providing regular interim feedback on the accuracy of neoplastic lesion prediction and surveillance interval selection did not lead to differences in those endpoints. Monitoring is suggested, as individual performance varied. ClinicalTrials.gov no: NCT02516748; Netherland Trial Register: NTR4635.

Optical diagnosis expanded to small polyps: post-hoc analysis of diagnostic performance in a prospective multicenter study.

BACKGROUND: Optical diagnosis can replace histopathology of diminutive (1 - 5 mm) polyps if surveillance intervals based on optical diagnosis of polyps have ≥ 90 % agreement with intervals based on polyp histology and if the negative predictive value (NPV) for predicting neoplastic histology in the rectosigmoid is ≥ 90 %. This study aims to assess whether small (6 - 9 mm) polyps can be included in optical diagnosis strategies. METHOD: This is a post-hoc analysis of a prospective multicenter study in which 27 endoscopists, all performing endoscopies for the Dutch screening program, were trained in optical diagnosis. For 1 year, endoscopists recorded the predicted histology for all lesions detected using narrow-band imaging during 3144 consecutive colonoscopies after a positive fecal immunochemical test, along with confidence levels. Surveillance interval agreement and NPV were calculated for high confidence predictions for polyps of 1 - 9 mm and compared with histopathology. Surveillance interval agreement was calculated using the European Society of Gastrointestinal Endoscopy surveillance guideline. RESULTS: Surveillance interval agreement was 95.4 % (confidence interval [CI] 94.2 % - 96.4 %), and NPV for predicting neoplastic histology in the rectosigmoid 90.0 % (CI 87.3 % - 92.2 %). The reduction in histology (45.9 % vs. 30.5 %) and the proportion of patients who could have received direct surveillance advice (15.6 % vs. 7.3 %) was higher when small polyps were included (P < 0.001). T1 cancer was found in seven small polyps (0.33 %), five of which would have been discarded without histopathology. CONCLUSION: Including small polyps in the optical diagnosis strategy improves its efficacy while maintaining performance thresholds. However, there is a small risk of missing T1 cancers when small polyps are included in the optical diagnosis strategy.

Advanced imaging for detection and differentiation of colorectal neoplasia: European Society of Gastrointestinal Endoscopy (ESGE) Guideline - Update 2019.

1:  ESGE suggests that high definition endoscopy, and dye or virtual chromoendoscopy, as well as add-on devices, can be used in average risk patients to increase the endoscopist's adenoma detection rate. However, their routine use must be balanced against costs and practical considerations.Weak recommendation, high quality evidence. 2:  ESGE recommends the routine use of high definition systems in individuals with Lynch syndrome.Strong recommendation, high quality evidence. 3:  ESGE recommends the routine use, with targeted biopsies, of dye-based pancolonic chromoendoscopy or virtual chromoendoscopy for neoplasia surveillance in patients with long-standing colitis.Strong recommendation, moderate quality evidence. 4:  ESGE suggests that virtual chromoendoscopy and dye-based chromoendoscopy can be used, under strictly controlled conditions, for real-time optical diagnosis of diminutive (≤ 5 mm) colorectal polyps and can replace histopathological diagnosis. The optical diagnosis has to be reported using validated scales, must be adequately photodocumented, and can be performed only by experienced endoscopists who are adequately trained, as defined in the ESGE curriculum, and audited.Weak recommendation, high quality evidence. 5:  ESGE recommends the use of high definition white-light endoscopy in combination with (virtual) chromoendoscopy to predict the presence and depth of any submucosal invasion in nonpedunculated colorectal polyps prior to any treatment. Strong recommendation, moderate quality evidence. 6:  ESGE recommends the use of virtual or dye-based chromoendoscopy in addition to white-light endoscopy for the detection of residual neoplasia at a piecemeal polypectomy scar site. Strong recommendation, moderate quality evidence. 7:  ESGE suggests the possible incorporation of computer-aided diagnosis (detection and characterization of lesions) to colonoscopy, if acceptable and reproducible accuracy for colorectal neoplasia is demonstrated in high quality multicenter in vivo clinical studies. Possible significant risks with implementation, specifically endoscopist deskilling and over-reliance on artificial intelligence, unrepresentative training datasets, and hacking, need to be considered. Weak recommendation, low quality evidence.

Endoscopic detection rate of sessile serrated lesions in Lynch syndrome patients is comparable with an age- and gender-matched control population: case-control study with expert pathology review.

BACKGROUND AND AIMS: Carcinogenesis in Lynch syndrome involves fast progression of adenomas to colorectal cancer (CRC) because of microsatellite instability. The role of sessile serrated lesions (SSLs) and the serrated neoplasia pathway in these patients is unknown. The aim of this matched case-control study was to compare endoscopic detection rates and distribution of SSLs in Lynch syndrome patients with a matched control population. METHODS: We collected data of Lynch syndrome patients with a proven germline mutation who underwent colonoscopy between January 2011 and April 2016 in 2 tertiary referral hospitals. Control subjects undergoing elective colonoscopy from 2011 and onward for symptoms or surveillance were selected from a prospectively collected database. Patients were matched 1:1 for age, gender, and index versus surveillance colonoscopy. An expert pathology review of serrated polyps was performed. The primary outcomes included the detection rates and distribution of SSLs. RESULTS: We identified 321 patients with Lynch syndrome who underwent at least 1 colonoscopy. Of these, 223 Lynch syndrome patients (mean age, 49.3; 59% women; index colonoscopy, 56%) were matched to 223 control subjects. SSLs were detected in 7.6% (95% confidence interval, 4.8-11.9) of colonoscopies performed in Lynch syndrome patients and in 6.7% (95% confidence interval, 4.1-10.8) of control subjects (P = .86). None of the detected SSLs in Lynch syndrome patients contained dysplasia. CONCLUSIONS: The detection rate of SSLs in Lynch syndrome patients undergoing colonoscopy is comparable with a matched population. These findings suggest that the role of the serrated neoplasia pathway in CRC development in Lynch syndrome seems to be comparable with that in the general population.

Natural history of diminutive and small colorectal polyps: a systematic literature review.

BACKGROUND AND AIMS: Diminutive (1-5 mm) and small (6-9 mm) polyps comprise 90% of detected lesions during colonoscopy and rarely contain advanced histology or colorectal cancer (CRC). Routine removal of these lesions results in a significant burden to colonoscopy programs. At the same time, the risk for progression of these polyps to CRC is unclear. We performed a systematic review to explore the natural history of diminutive and small colorectal polyps. METHODS: We searched MEDLINE and EMBASE for studies investigating the natural history of colorectal polyps. Studies were considered eligible when they assessed patients with 1- to 9-mm polyps that were not treated with polypectomy and that underwent follow-up. We excluded studies in patients with inflammatory bowel disease, polyposis syndromes, and previously diagnosed CRC. We independently extracted study characteristics and evaluated CRC and advanced adenoma (size ≥ 10 mm, containing high-grade dysplasia or villous features) as outcome parameters. RESULTS: Of 8775 retrieved studies, 9 studies with 721 patients were included that prospectively evaluated the evolution of 1- to 9-mm polyps. In 7 studies the average duration of observation was 2 to 3 years. There was only 1 study in which 1 small polyp might have progressed to cancer. Of 1034 adenomas sized 1 to 9 mm in those studies, 6% progressed to advanced adenomas over time. CONCLUSIONS: Based on this systematic review, it appears that some 1- to 9-mm adenomas progress to advanced adenomas within 2 to 3 years. No information on long-term CRC transition rates was found. Defining the biologic significance of these polyps is needed to balance between benefits and harm of polypectomy. (PROSPERO database registration number: CRD42016036577.).

Optical Diagnosis of Sessile Serrated Polyps: Bottleneck for the Optical Diagnosis Paradigm?

BACKGROUND: Optical diagnosis of diminutive (1 to 5 mm) polyps could result in a more cost-effective colonoscopy practice. Previous optical diagnosis studies did not incorporate the differentiation of sessile serrated polyps (SSPs). This study aimed to evaluate the impact of optical diagnosis of diminutive SSPs on the overall performance of endoscopic polyp differentiation in daily colonoscopy practice. METHODS: Endoscopy data were prospectively collected between 2011 and 2014 in a colonoscopy center. Each endoscopist reported a real-time optical diagnosis (SSP, adenoma or hyperplastic polyp) for all lesions in a structured colonoscopy reporting system, using narrow band imaging at their discretion. Study outcomes were accuracy of optical diagnosis, surveillance interval agreement and negative predictive value for diminutive rectosigmoid neoplastic histology based on the optical diagnosis of diminutive polyps compared to histopathology. RESULTS: Of 2853 removed diminutive polyps, 202 (7.1%) were histologically proven SSPs. Optical diagnosis of diminutive SSPs was accurate in 24.4%. Diminutive SSPs determined 6.9% of postpolypectomy surveillance assignments. Inaccurate optical diagnosis of diminutive SSPs led to lower surveillance interval agreement (78.1% vs. 53.3%, P<0.01) and pooled negative predictive value per polyp (84.3% vs. 50.0%; P<0.01) in patients with diminutive SSPs when compared to patients without diminutive SSPs. Accurate endoscopic identification of diminutive SSPs improved from 0% in 2011 to 47% in 2014 (P=0.02). CONCLUSIONS: Endoscopic characterization of diminutive SSPs is difficult, impairing overall performance of optical diagnosis in patients with diminutive SSPs. Future optical diagnosis studies should use validated trainings and classification algorithms that include differentiation of SSPs.

Incidence of colonic neoplasia in patients with serrated polyposis syndrome who undergo annual endoscopic surveillance.

BACKGROUND & AIMS: Patients with serrated polyposis syndrome (SPS) are advised to undergo endoscopic surveillance for early detection of polyps and prevention of colorectal cancer (CRC). The optimal surveillance and treatment regimen is unknown. We performed a prospective study to evaluate a standardized endoscopic treatment protocol in a large cohort of patients with SPS. METHODS: We followed a cohort of patients with SPS who received annual endoscopic surveillance at the Academic Medical Centre in Amsterdam, The Netherlands from January 2007 through December 2012. All patients underwent clearing colonoscopy with removal of all polyps ≥3 mm. After clearance, subsequent follow-up colonoscopies were scheduled annually. The primary outcomes measure was the incidence of CRC and polyps. Secondary outcomes were the incidence of complications and the rate of preventive surgery. RESULTS: Successful endoscopic clearance of all polyps ≥3 mm was achieved in 41 of 50 (82%) patients. During subsequent annual surveillance, with a median follow-up time of 3.1 years (interquartile range, 1.5-4.3 years), CRC was not detected. The cumulative risks of detecting CRC, advanced adenomas, or large (≥10 mm) serrated polyps after 3 surveillance colonoscopies were 0%, 9%, 34%, respectively. Twelve patients (24%) were referred for preventive surgery; 9 at initial colonoscopy and 3 during surveillance. Perforations or severe bleeding did not occur. CONCLUSIONS: Annual surveillance with complete removal of all polyps ≥3 mm with timely referral of selected high-risk patients for prophylactic surgery prevents development of CRC in SPS patients without significant morbidity. Considering the substantial risk of polyp recurrence, close endoscopic surveillance in SPS seems warranted. www.trialregister.nl ID NTR2757.

Adenoma detection rate varies greatly during colonoscopy training.

BACKGROUND: The adenoma detection rate (ADR) is considered the most important quality indicator for colonoscopy and varies widely among colonoscopists. It is unknown whether the ADR of gastroenterology consultants can already be predicted during their colonoscopy training. OBJECTIVE: To evaluate the ADR of fellows in gastroenterology and evaluate whether this predicts their ADR as gastroenterology consultants. DESIGN: Retrospective observational study. SETTING: Academic and regional centers. PATIENTS: Symptomatic patients undergoing colonoscopy. MAIN OUTCOME MEASUREMENTS: The variance in ADR among 7 gastroenterology fellows during their training (between May 2004 and March 2012) and of the same fellows after they registered as consultants (between October 2011 and April 2014) was evaluated. Multivariate logistic regression was performed to compare the highest detector (endoscopist with highest ADR) with the individual fellows and to evaluate whether an ADR of 20% or higher during the training was predictive of a high ADR as a consultant. RESULTS: During training, ADRs ranged from 14% to 36% (P < .001). Compared with the highest detector, the OR for detecting an adenoma ranged from 0.64 (95% CI, 0.40-1.03) to 0.29 (95% CI, 0.17-0.48). After registration, ADR ranged from 19.8% to 40.2% (P = .066). Compared with the highest detector during consultancy, the OR ranged from 0.64 (95% CI, 0.34-1.21) to 0.26 (95% CI, 0.13-0.52). Only 2 fellows significantly improved their ADR after completing their training. An ADR lower than 20% during training was associated with a lower ADR as a consultant (OR 0.51; 95% CI, 0.30-0.87). LIMITATIONS: Retrospective study. CONCLUSIONS: Variance in ADR is already present during the endoscopy training of gastroenterology fellows. Most fellows do not improve their ADR after completing their training. These findings suggest that the ADR can be predicted during colonoscopy training, and we suggest that feedback and benchmarking should be implemented early during training of fellows in an effort to improve ADR in future daily practice as a consultant.