Improving the endoscopic recognition of early colorectal carcinoma using artificial intelligence: current evidence and future directions.

Background and study aims Artificial intelligence (AI) has great potential to improve endoscopic recognition of early stage colorectal carcinoma (CRC). This scoping review aimed to summarize current evidence on this topic, provide an overview of the methodologies currently used, and guide future research. Methods A systematic search was performed following the PRISMA-Scr guideline. PubMed (including Medline), Scopus, Embase, IEEE Xplore, and ACM Digital Library were searched up to January 2024. Studies were eligible for inclusion when using AI for distinguishing CRC from colorectal polyps on endoscopic imaging, using histopathology as gold standard, reporting sensitivity, specificity, or accuracy as outcomes. Results Of 5024 screened articles, 26 were included. Computer-aided diagnosis (CADx) system classification categories ranged from two categories, such as lesions suitable or unsuitable for endoscopic resection, to five categories, such as hyperplastic polyp, sessile serrated lesion, adenoma, cancer, and other. The number of images used in testing databases varied from 69 to 84,585. Diagnostic performances were divergent, with sensitivities varying from 55.0% to 99.2%, specificities from 67.5% to 100% and accuracies from 74.4% to 94.4%. Conclusions This review highlights that using AI to improve endoscopic recognition of early stage CRC is an upcoming research field. We introduced a suggestions list of essential subjects to report in research regarding the development of endoscopy CADx systems, aiming to facilitate more complete reporting and better comparability between studies. There is a knowledge gap regarding real-time CADx system performance during multicenter external validation. Future research should focus on development of CADx systems that can differentiate CRC from premalignant lesions, while providing an indication of invasion depth.

Effect of optical diagnosis training on recognition and treatment of submucosal invasive colorectal cancer in community hospitals: a prospective multicenter intervention study.

BACKGROUND: Recognition of submucosal invasive colorectal cancer (T1 CRC) is difficult, with sensitivities of 35 %-60 % in Western countries. We evaluated the real-life effects of training in the OPTICAL model, a recently developed structured and validated prediction model, in Dutch community hospitals. METHODS: In this prospective multicenter study (OPTICAL II), 383 endoscopists from 40 hospitals were invited to follow an e-learning program on the OPTICAL model, to increase sensitivity in detecting T1 CRC in nonpedunculated polyps. Real-life recognition of T1 CRC was then evaluated in 25 hospitals. Endoscopic and pathologic reports of T1 CRCs detected during the next year were collected retrospectively, with endoscopists unaware of this evaluation. Sensitivity for T1 CRC recognition, R0 resection rate, and treatment modality were compared for trained vs. untrained endoscopists. RESULTS: 1 year after e-learning, 528 nonpedunculated T1 CRCs were recorded for endoscopies performed by 251 endoscopists (118 [47 %] trained). Median T1 CRC size was 20 mm. Lesions were mainly located in the distal colorectum (66 %). Trained endoscopists recognized T1 CRCs more frequently than untrained endoscopists (sensitivity 74 % vs. 62 %; mixed model analysis odds ratio [OR] 2.90, 95 %CI 1.54-5.45). R0 resection rate was higher for T1 CRCs detected by trained endoscopists (69 % vs. 56 %; OR 1.73, 95 %CI 1.03-2.91). CONCLUSION: Training in optical recognition of T1 CRCs in community hospitals was associated with increased recognition of T1 CRCs, leading to higher en bloc and R0 resection rates. This may be an important step toward more organ-preserving strategies.

Oncologic outcomes of screen-detected and non-screen-detected T1 colorectal cancers.

BACKGROUND: The incidence of T1 colorectal cancer (CRC) has increased with the implementation of CRC screening programs. It is unknown whether the outcomes and risk models for T1 CRC based on non-screen-detected patients can be extrapolated to screen-detected T1 CRC. This study aimed to compare the stage distribution and oncologic outcomes of T1 CRC patients within and outside the screening program. METHODS: Data from T1 CRC patients diagnosed between 2014 and 2017 were collected from 12 hospitals in the Netherlands. The presence of lymph node metastasis (LNM) at diagnosis was compared between screen-detected and non-screen-detected patients using multivariable logistic regression. Cox proportional hazard regression was used to analyze differences in the time to recurrence (TTR), metastasis-free survival (MFS), cancer-specific survival (CSS), and overall survival. Additionally, the performance of conventional risk factors for LNM was evaluated across the groups. RESULTS: 1803 patients were included (1114 [62%] screen-detected), with median follow-up of 51 months (interquartile range 30). The proportion of LNM did not significantly differ between screen- and non-screen-detected patients (12.6% vs. 8.9%; odds ratio 1.41; 95%CI 0.89-2.23); a prediction model for LNM performed equally in both groups. The 3- and 5-year TTR, MFS, and CSS were similar for patients within and outside the screening program. However, overall survival was significantly longer in screen-detected T1 CRC patients (adjusted hazard ratio 0.51; 95%CI 0.38-0.68). CONCLUSIONS: Screen-detected and non-screen-detected T1 CRCs have similar stage distributions and oncologic outcomes and can therefore be treated equally. However, screen-detected T1 CRC patients exhibit a lower rate of non-CRC-related mortality, resulting in longer overall survival.

Recurrences of advanced sessile and lateral spreading colorectal adenoma after endoscopic mucosal resection (EMR) thermal ablation versus no adjuvant therapy (RESPECT): a protocol of an international randomized controlled trial.

BACKGROUND: Nowadays, large benign lateral spreading lesions (LSLs) and sessile polyps in the colorectum are mostly resected by endoscopic mucosal resection (EMR). A major drawback of EMR is the polyp recurrence rate of up to 20%. Snare tip soft coagulation (STSC) is considered an effective technique to reduce recurrence rates. However, clinical trials on STSC have mainly been conducted in expert referral centers. In these studies, polyp recurrence was assessed optically, and additional adjunctive techniques were excluded. In the current trial, we will evaluate the efficacy and safety of STSC in daily practice, by allowing adjunctive techniques during EMR and the use of both optical and histological polyp recurrence to assess recurrences during follow-up. METHODS: The RESPECT study is a multicenter, parallel-group, international single blinded randomized controlled superiority trial performed in the Netherlands and Germany. A total of 306 patients undergoing piecemeal EMR for LSLs or sessile colorectal polyps sized 20-60 mm will be randomized during the procedure after endoscopic complete polyp resection to the intervention or control group. Post-EMR defects allocated to the intervention group will be treated with thermal ablation with STSC of the entire resection margin. Primary outcome will be polyp recurrence by optical and histological confirmation at the first surveillance colonoscopy after 6 months. Secondary outcomes include technical success and complication rates. DISCUSSION: The RESPECT study will evaluate if STSC is effective in reducing recurrence rates after piecemeal EMR of large colorectal lesions in daily clinical practice performed by expert and non-expert endoscopists. Moreover, endoscopists will be allowed to use adjunctive techniques to remove remaining adenomatous tissue during the procedure. Finally, adenomatous polyp recurrence during follow-up will be defined by histologic identification. TRIAL REGISTRATION: ClinicalTrials.gov NCT05121805. Registered on 16 November 2021. Start recruitment: 17 March 2022. Planned completion of recruitment: 31 April 2025.

Endoscopic full-thickness resection of a solitary ovarian carcinoma colorectal metastasis.

A woman in her 70s with a medical history of recurrent ovarian carcinoma was referred to the gastroenterologist because of rectal blood loss. Colonoscopy revealed a spontaneously bleeding lesion, which was not a typical colorectal carcinoma by optical diagnosis. Biopsies confirmed the diagnosis of recurrence of the former ovarian carcinoma. The patient was not eligible for surgical resection due to former abdominal surgery and she declined chemotherapy due to severe side effects earlier. After a multidisciplinary team consultation, she was treated with endoscopic full-thickness resection (eFTR). This is a minimally invasive resection technique for removal of challenging colorectal lesions. The patient has recovered well and 2 years after the metastasis resection with eFTR there still have been no signs of recurrent malignancy.

Standardised training for endoscopic mucosal resection of large non-pedunculated colorectal polyps to reduce recurrence (*STAR-LNPCP study): a multicentre cluster randomised trial.

OBJECTIVE: Endoscopic mucosal resection (EMR) is the preferred treatment for non-invasive large (≥20 mm) non-pedunculated colorectal polyps (LNPCPs) but is associated with an early recurrence rate of up to 30%. We evaluated whether standardised EMR training could reduce recurrence rates in Dutch community hospitals. DESIGN: In this multicentre cluster randomised trial, 59 endoscopists from 30 hospitals were randomly assigned to the intervention group (e-learning and 2-day training including hands-on session) or control group. From April 2019 to August 2021, all consecutive EMR-treated LNPCPs were included. Primary endpoint was recurrence rate after 6 months. RESULTS: A total of 1412 LNPCPs were included; 699 in the intervention group and 713 in the control group (median size 30 mm vs 30 mm, 45% vs 52% size, morphology, site and access (SMSA) score IV, 64% vs 64% proximal location). Recurrence rates were lower in the intervention group compared with controls (13% vs 25%, OR 0.43; 95% CI 0.23 to 0.78; p=0.005) with similar complication rates (8% vs 9%, OR 0.93; 95% CI 0.64 to 1.36; p=0.720). Recurrences were more often unifocal in the intervention group (92% vs 76%; p=0.006). In sensitivity analysis, the benefit of the intervention on recurrence rate was only observed in the 20-40 mm LNPCPs (5% vs 20% in 20-29 mm, p=0.001; 10% vs 21% in 30-39 mm, p=0.013) but less evident in ≥40 mm LNPCPs (24% vs 31%; p=0.151). In a post hoc analysis, the training effect was maintained in the study group, while in the control group the recurrence rate remained high. CONCLUSION: A compact standardised EMR training for LNPCPs significantly reduced recurrences in community hospitals. This strongly argues for a national dedicated training programme for endoscopists performing EMR of ≥20 mm LNPCPs. Interestingly, in sensitivity analysis, this benefit was limited for LNPCPs ≥40 mm. TRIAL REGISTRATION NUMBER: NTR7477.

Erratum: Automatic textual description of colorectal polyp features: explainable artificial intelligence.

[This corrects the article DOI: 10.1055/a-2071-6652.].

Limited wedge resection for T1 colon cancer (LIMERIC-II trial) - rationale and study protocol of a prospective multicenter clinical trial.

BACKGROUND: The sole presence of deep submucosal invasion is shown to be associated with a limited risk of lymph node metastasis. This justifies a local excision of suspected deep submucosal invasive colon carcinomas (T1 CCs) as a first step treatment strategy. Recently Colonoscopy-Assisted Laparoscopic Wedge Resection (CAL-WR) has been shown to be able to resect pT1 CRCs with a high R0 resection rate, but the long term outcomes are lacking. The aim of this study is to evaluate the safety, effectiveness and long-term oncological outcomes of CAL-WR as primary treatment for patients with suspected superficial and also deeply-invasive T1 CCs. METHODS: In this prospective multicenter clinical trial, patients with a macroscopic and/or histologically suspected T1 CCs will receive CAL-WR as primary treatment in order to prevent unnecessary major surgery for low-risk T1 CCs. To make a CAL-WR technically feasible, the tumor may not include > 50% of the circumference and has to be localized at least 25 cm proximal from the anus. Also, there should be sufficient distance to the ileocecal valve to place a linear stapler. Before inclusion, all eligible patients will be assessed by an expert panel to confirm suspicion of T1 CC, estimate invasion depth and subsequent advise which local resection techniques are possible for removal of the lesion. The primary outcome of this study is the proportion of patients with pT1 CC that is curatively treated with CAL-WR only and in whom thus organ-preservation could be achieved. Secondary outcomes are 1) CAL-WR's technical success and R0 resection rate for T1 CC, 2) procedure-related morbidity and mortality, 3) 5-year overall and disease free survival, 4) 3-year metastasis free survival, 5) procedure-related costs and 6) impact on quality of life. A sample size of 143 patients was calculated. DISCUSSION: CAL-WR is a full-thickness local resection technique that could also be effective in removing pT1 colon cancer. With the lack of current endoscopic local resection techniques for > 15 mm pT1 CCs with deep submucosal invasion, CAL-WR could fill the gap between endoscopy and major oncologic surgery. The present study is the first to provide insight in the long-term oncological outcomes of CAL-WR. TRIAL REGISTRATION: CCMO register (ToetsingOnline), NL81497.075.22, protocol version 2.3 (October 2022).

Automatic textual description of colorectal polyp features: explainable artificial intelligence.

Computer-aided diagnosis systems (CADx) can improve colorectal polyp (CRP) optical diagnosis. For integration into clinical practice, better understanding of artificial intelligence (AI) by endoscopists is needed. We aimed to develop an explainable AI CADx capable of automatically generating textual descriptions of CRPs. For training and testing of this CADx, textual descriptions of CRP size and features according to the Blue Light Imaging (BLI) Adenoma Serrated International Classification (BASIC) were used, describing CRP surface, pit pattern, and vessels. CADx was tested using BLI images of 55 CRPs. Reference descriptions with agreement by at least five out of six expert endoscopists were used as gold standard. CADx performance was analyzed by calculating agreement between the CADx generated descriptions and reference descriptions. CADx development for automatic textual description of CRP features succeeded. Gwet's AC1 values comparing the reference and generated descriptions per CRP feature were: size 0.496, surface-mucus 0.930, surface-regularity 0.926, surface-depression 0.940, pits-features 0.921, pits-type 0.957, pits-distribution 0.167, and vessels 0.778. CADx performance differed per CRP feature and was particularly high for surface descriptors while size and pits-distribution description need improvement. Explainable AI can help comprehend reasoning behind CADx diagnoses and therefore facilitate integration into clinical practice and increase trust in AI.

Relapse rates after withdrawal versus maintaining biologic therapy in IBD patients with prolonged remission.

Biologic treatment withdrawal in inflammatory bowel disease patients with prolonged remission may lead to benefits but also increases the risk of getting a relapse. The risk of relapse after biologic withdrawal according to the Dutch STOP-criteria is still unknown. The aim of this study was to compare the cumulative incidence of relapse in inflammatory bowel disease patients that discontinued biologic therapy after applying the STOP-criteria with patients who maintained biologic therapy. We performed a mono-centre, observational, retrospective study by evaluating relapse risk of patients treated with biologic agents who discontinued this treatment according to the STOP-criteria (STOP-group) compared to patients who were in remission for more than 3 years before withdrawal (LATERSTOP-group) and patients who continued their biologic (MAINTAIN-group). The cumulative risk was calculated at 12 and 36 months using the log-rank test to compare Kaplan-Meier curves. Eighty-three of 398 patients that used biologics between 1 January 2010 and 1 January 2020 were included. The cumulative relapse incidences in the STOP-group and the LATERSTOP-group were, respectively, 29% and 42% at 12 months and 47% versus 58% at 36 months. Patients in the MAINTAIN-group showed a lower (p = 0.03) cumulative relapse incidence of 10% at 12 months and 18% at 36 months. Patients who discontinued their biologic therapy according to the STOP-criteria had significantly more relapses at 12 and 36 months than patients who maintained biologic treatment.

Impact of ≥ 0.1-mm free resection margins on local intramural residual cancer after local excision of T1 colorectal cancer.

Background and study aims A free resection margin (FRM) > 1 mm after local excision of a T1 colorectal cancer (CRC) is known to be associated with a low risk of local intramural residual cancer (LIRC). The risk is unclear, however, for FRMs between 0.1 to 1 mm. This study evaluated the risk of LIRC after local excision of T1 CRC with FRMs between 0.1 and 1 mm in the absence of lymphovascular invasion (LVI), poor differentiation and high-grade tumor budding (Bd2-3). Patients and methods Data from all consecutive patients with local excision of T1 CRC between 2014 and 2017 were collected from 11 hospitals. Patients with a FRM ≥ 0.1 mm without LVI and poor differentiation were included. The main outcome was risk of LIRC (composite of residual cancer in the local excision scar in adjuvant resection specimens or local recurrence during follow-up). Tumor budding was also assessed for cases with a FRM between 0.1 and 1mm. Results A total of 171 patients with a FRM between 0.1 and 1 mm and 351 patients with a FRM > 1 mm were included. LIRC occurred in five patients (2.9 %; 95 % confidence interval [CI] 1.0-6.7 %) and two patients (0.6 %; 95 % CI 0.1-2.1 %), respectively. Assessment of tumor budding showed Bd2-3 in 80 % of cases with LIRC and in 16 % of control cases. Accordingly, in patients with a FRM between 0.1 and 1 mm without Bd2-3, LIRC was detected in one patient (0.8%; 95 % CI 0.1-4.4 %). Conclusions In this study, risks of LIRC were comparable for FRMs between 0.1 and 1 mm and > 1 mm in the absence of other histological risk factors.

A Multidisciplinary Approach for the Personalised Non-Operative Management of Elderly and Frail Rectal Cancer Patients Unable to Undergo TME Surgery.

Despite it being the optimal curative approach, elderly and frail rectal cancer patients may not be able to undergo a total mesorectal excision. Frequently, no treatment is offered at all and the natural course of the disease is allowed to unfold. These patients are at risk for developing debilitating symptoms that impair quality of life and require palliative treatment. Recent advancements in non-operative treatment modalities have enhanced the toolbox of alternative treatment strategies in patients unable to undergo surgery. Therefore, a proposed strategy is to aim for the maximal non-operative treatment, in an effort to avoid the onset of debilitating symptoms, improve quality of life, and prolong survival. The complexity of treating elderly and frail patients requires a patient-centred approach to personalise treatment. The main challenge is to optimise the balance between local control of disease, patient preferences, and the burden of treatment. A comprehensive geriatric assessment is a crucial element within the multidisciplinary dialogue. Since limited knowledge is available on the optimal non-operative treatment strategy, these patients should be treated by dedicated multidisciplinary rectal cancer experts with special interest in the elderly and frail. The aim of this narrative review was to discuss a multidisciplinary patient-centred treatment approach and provide a practical suggestion of a successfully implemented clinical care pathway.

Full-Thickness Scar Resection After R1/Rx Excised T1 Colorectal Cancers as an Alternative to Completion Surgery.

INTRODUCTION: Local full-thickness resections of the scar (FTRS) after local excision of a T1 colorectal cancer (CRC) with uncertain resection margins is proposed as an alternative strategy to completion surgery (CS), provided that no local intramural residual cancer (LIRC) is found. However, a comparison on long-term oncological outcome between both strategies is missing. METHODS: A large cohort of patients with consecutive T1 CRC between 2000 and 2017 was used. Patients were selected if they underwent a macroscopically complete local excision of a T1 CRC but positive or unassessable (R1/Rx) resection margins at histology and without lymphovascular invasion or poor differentiation. Patients treated with CS or FTRS were compared on the presence of CRC recurrence, a 5-year overall survival, disease-free survival, and metastasis-free survival. RESULTS: Of 3,697 patients with a T1 CRC, 434 met the inclusion criteria (mean age 66 years, 61% men). Three hundred thirty-four patients underwent CS, and 100 patients underwent FTRS. The median follow-up period was 64 months. CRC recurrence was seen in 7 patients who underwent CS (2.2%, 95% CI 0.9%-4.6%) and in 8 patients who underwent FTRS (9.0%, 95% CI 3.9%-17.7%). Disease-free survival was lower in FTRS strategy (96.8% vs 89.9%, P = 0.019), but 5 of the 8 FTRS recurrences could be treated with salvage surgery. The metastasis-free survival (CS 96.8% vs FTRS 92.1%, P = 0.10) and overall survival (CS 95.6% vs FTRS 94.4%, P = 0.55) did not differ significantly between both strategies. DISCUSSION: FTRS after local excision of a T1 CRC with R1/Rx resection margins as a sole risk factor, followed by surveillance and salvage surgery in case of CRC recurrence, could be a valid alternative strategy to CS.

Real-time diagnostic accuracy of blue light imaging, linked color imaging and white-light endoscopy for colorectal polyp characterization.

Background and study aims Fujifilm has developed a novel ELUXEO 7000 endoscope system that employs light-emitting diodes (LEDs) at four different wavelengths as light sources that enable blue light imaging (BLI), linked color imaging (LCI), and high-definition white-light endoscopy (HD-WLE). The aim of this study was to address the diagnostic accuracy of real-time polyp characterization using BLI, LCI and HD-WLE (ELUXEO 7000 endoscopy system). Patients methods This is a prespecified post-hoc analysis of a prospective study in which 22 experienced endoscopists (> 2,000 colonoscopies) from eight international centers participated. Using a combination of BLI, LCI, and HD-WLE, lesions were endoscopically characterized including a high- or low-confidence statement. Per protocol, digital images were created from all three imaging modalities. Histopathology was the reference standard. Endoscopists were familiar with polyp characterization, but did not take dedicated training for purposes of this study. Results Overall, 341 lesions were detected in 332 patients. Of the lesions, 269 histologically confirmed polyps with an optical diagnosis were included for analysis (165 adenomas, 27 sessile serrated lesions, and 77 hyperplastic polyps). Overall, polyp characterization was performed with high confidence in 82.9 %. The overall accuracy for polyp characterization was 75.1 % (95 % confidence interval [CI] 69.5-80.1 %), compared with an accuracy of 78.0 % (95 % CI 72.0-83.2 %) for high confidence assignments. The accuracy for endoscopic characterization for diminutive polyps was 74.7 % (95 %CI 68.4-80.3 %), compared with an accuracy of 78.2 % (95 % CI 71.4-84.0 %) for high-confidence assignments. Conclusions The diagnostic accuracy of BLI, LCI, and HD-WLE by experienced endoscopist for real-time polyp characterization seems limited (NCT03344289).

Neither inflammatory bowel disease nor immunosuppressants are associated with an increased risk of severe COVID-19: an observational Dutch cohort study.

Conflicting data about inflammatory bowel disease [IBD] and immunosuppressants are risk factors for severe COVID-19 confuse patients and healthcare providers. Clinical reports with longer follow-up are lacking. A retrospective search was performed for severe COVID-19 (hospital admission and/or mortality) one year after the SARS-CoV-2 outbreak in an IBD cohort from one of the most affected Dutch regions. Cohort characteristics were explored by value-based healthcare data, including immunotherapy. COVID-19 cases were detected by ICD-10 codes and further examined for IBD determinants (including medication) and COVID-19 characteristics (intensive care admission, respiratory support, treatment, mortality). The national mortality register was consulted, ensuring detection of patients that died without admission. Results were compared with regional and national general population registries. The IBD cohort consisted of 1453 patients (51% Crohn's disease, 54% women, 39.9% using immunotherapy), including children. Biologics use increased during the study. Eight cases (0.55%) had severe COVID-19: seven were hospitalized (0.48%, 95% confidence interval [CI] 0.21-1.04), and two died (0.14%, CI 0.002-0.55). Six patients had comorbidity, one used immunotherapy, and four had no medication. Both deceased patients were older than 80 years, had severe comorbidity, but used no immunotherapy. Hospitalization occurred significantly more in the IBD cohort than regionally (0.18%, CI 0.17-0.19, p = 0.015), but not significantly more than nationally (0.28%, CI 0.279-0.284). Mortality was equal in IBD patients, regionally (0.11%, CI 0.10-0.12) and nationally (0.13%, CI 0.125-0.128). Neither IBD nor immunosuppressants are associated with increased risks of severe COVID-19 in an observational study with one-year follow-up.

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.

Algorithm combining virtual chromoendoscopy features for colorectal polyp classification.

Background and study aims Colonoscopy is considered the gold standard for decreasing colorectal cancer incidence and mortality. Optical diagnosis of colorectal polyps (CRPs) is an ongoing challenge in clinical colonoscopy and its accuracy among endoscopists varies widely. Computer-aided diagnosis (CAD) for CRP characterization may help to improve this accuracy. In this study, we investigated the diagnostic accuracy of a novel algorithm for polyp malignancy classification by exploiting the complementary information revealed by three specific modalities. Methods We developed a CAD algorithm for CRP characterization based on high-definition, non-magnified white light (HDWL), Blue light imaging (BLI) and linked color imaging (LCI) still images from routine exams. All CRPs were collected prospectively and classified into benign or premalignant using histopathology as gold standard. Images and data were used to train the CAD algorithm using triplet network architecture. Our training dataset was validated using a threefold cross validation. Results In total 609 colonoscopy images of 203 CRPs of 154 consecutive patients were collected. A total of 174 CRPs were found to be premalignant and 29 were benign. Combining the triplet network features with all three image enhancement modalities resulted in an accuracy of 90.6 %, 89.7 % sensitivity, 96.6 % specificity, a positive predictive value of 99.4 %, and a negative predictive value of 60.9 % for CRP malignancy classification. The classification time for our CAD algorithm was approximately 90 ms per image. Conclusions Our novel approach and algorithm for CRP classification differentiates accurately between benign and premalignant polyps in non-magnified endoscopic images. This is the first algorithm combining three optical modalities (HDWL/BLI/LCI) exploiting the triplet network approach.

Clip placement to prevent delayed bleeding after colonic endoscopic mucosal resection (CLIPPER): study protocol for a randomized controlled trial.

BACKGROUND: Endoscopic mucosal resection (EMR) for large colorectal polyps is in most cases the preferred treatment to prevent progression to colorectal carcinoma. The most common complication after EMR is delayed bleeding, occurring in 7% overall and in approximately 10% of polyps ≥ 2 cm in the proximal colon. Previous research has suggested that prophylactic clipping of the mucosal defect after EMR may reduce the incidence of delayed bleeding in polyps with a high bleeding risk. METHODS: The CLIPPER trial is a multicenter, parallel-group, single blinded, randomized controlled superiority study. A total of 356 patients undergoing EMR for large (≥ 2 cm) non-pedunculated polyps in the proximal colon will be included and randomized to the clip group or the control group. Prophylactic clipping will be performed in the intervention group to close the resection defect after the EMR with a distance of < 1 cm between the clips. Primary outcome is delayed bleeding within 30 days after EMR. Secondary outcomes are recurrent or residual polyps and clip artifacts during surveillance colonoscopy after 6 months, as well as cost-effectiveness of prophylactic clipping and severity of delayed bleeding. DISCUSSION: The CLIPPER trial is a pragmatic study performed in the Netherlands and is powered to determine the real-time efficacy and cost-effectiveness of prophylactic clipping after EMR of proximal colon polyps ≥ 2 cm in the Netherlands. This study will also generate new data on the achievability of complete closure and the effects of clip placement on scar surveillance after EMR, in order to further promote the debate on the role of prophylactic clipping in everyday clinical practice. TRIAL REGISTRATION: ClinicalTrials.gov NCT03309683 . Registered on 13 October 2017. Start recruitment: 05 March 2018. Planned completion of recruitment: 31 August 2021.