Endoscopic management of benign biliary strictures: Looking for the best stent to place.

Benign biliary strictures (BBS) might occur due to different pancreaticobiliary conditions. The etiology and location of biliary strictures are responsible of a wide array of clinical manifestations. The endoscopic approach endoscopic retrograde cholangiopancreatography represents the first-line treatment for BBS, considering interventional radiology and surgery when endoscopic treatment fails or it is not suitable. The purpose of this review is to provide an overview of possible endoscopic treatments for the optimal management of this subset of patients.

Peroral Endoscopic Myotomy for Achalasia after Bariatric Surgery: A Case Report and Review of the Literature.

INTRODUCTION: Achalasia following bariatric surgery is a rare phenomenon with diverse potential physiopathological origins. AIMS: This article aims to explore the hypothetical physiopathological connection between bariatric surgery and the subsequent onset of achalasia. MATERIAL AND METHODS: A review was conducted to identify studies reporting cases of peroral endoscopic myotomy (POEM) after bariatric procedures and detailing the outcomes in terms of the technical and clinical success. Additionally, a case of a successful POEM performed on a patient two years after undergoing laparoscopic sleeve gastrectomy (LSG) is presented. RESULTS: The selection criteria yielded eight studies encompassing 40 patients treated with POEM for achalasia after bariatric surgery: 34 after Roux-en-Y gastric bypass (RYGB) and 6 after LSG. The studies reported an overall technical success rate of 97.5%, with clinical success achieved in 85% of cases. Adverse events were minimal, with only one case of esophageal leak treated endoscopically. However, a postprocedural symptomatic evaluation was notably lacking in most of the included studies. CONCLUSIONS: Achalasia poses a considerable challenge within the bariatric surgery population. POEM has emerged as a technically viable and safe intervention for this patient demographic, providing an effective treatment option where surgical alternatives for achalasia are limited. Our findings highlight the promising outcomes of POEM in these patients, but the existing data remain limited. Hence, prospective studies are needed to elucidate the optimal pre-surgical assessment and timing of endoscopic procedures for optimizing outcomes.

Pilot study on a new endoscopic platform for colorectal endoscopic submucosal dissection.

Background: The endoscopic submucosal dissection (ESD) is a technically demanding and time-consuming procedure, with an increased risk of adverse events compared to standard endoscopic resection techniques. The main difficulties are related to the instability of the operating field and to the loss of traction. We aimed to evaluate in a pilot trial a new endoscopic platform [tissue retractor system (TRS); ORISE, Boston scientific Co., Marlborough, MA, USA], designed to stabilize the intraluminal space, and to provide tissue retraction and counter traction. Method: We prospectively enrolled all consecutive patients who underwent an ESD for sigmoid/rectal lesions. The primary outcome was the rate of technical feasibility. Further technical aspects such as en-bloc and R0 resection rate, number of graspers used, circumferential incision time, TRS assemblage time, submucosal dissection time, and submucosal dissection speed were provided. Clinical outcomes (recurrence rate and adverse events) were recorded as well. Results: In all, 10 patients (M/F 4/6, age: 70.4 ± 11.0 years old) were enrolled. Eight out of 10 lesions were located in the rectum. Average lesion size was 31.2 ± 2.7 mm, and mean lesion area was 1628.88 ± 205.3 mm2. The two sigmoid lesions were removed through standard ESD, because the platform assemblage failed after several attempts. All rectal lesions were removed in an en-bloc fashion. R0 resection was achieved in 7/8 (87.5%) patients in an average procedure time of 60.5 ± 23.3 min. None of the patients developed neither intraprocedural nor postprocedural adverse events. Conclusion: TRS-assisted ESD is a feasible option when used in the rectum, with promising result in terms of efficacy and safety outcomes. Nevertheless, our pilot study underlines few technical limitations of the present platform that need to be overcome before the system could be widely and routinely used.

Predictors of long-term outcomes of endoscopic submucosal dissection of early gastric neoplasia in the West: a multicenter study.

BACKGROUND: This study aimed to determine long-term outcomes of gastric endoscopic submucosal dissection (ESD) in Western settings based on the latest Japanese indication criteria, and to examine predictors of outcomes and complications. METHODS: Data were collected from consecutive patients undergoing gastric ESD at four participating centers from 2009 to 2021. Retrospective analysis using logistic regression and survival analysis was performed. RESULTS: 415 patients were included (mean age 71.7 years; 56.4 % male). Absolute indication criteria (2018 guideline) were met in 75.3 % of patients. Median follow-up was 52 months. Post-resection histology was adenocarcinoma, high grade dysplasia, and low grade dysplasia in 49.9 %, 22.7 %, and 17.1 %, respectively. Perforation, early and delayed bleeding occurred in 2.4 %, 4.3 %, and 3.4 %, respectively. Rates of en bloc and R0 resection, and recurrence on first endoscopic follow-up were 94.7 %, 83.4 %, and 2.7 %, respectively. Relative indication (2018 guideline) for ESD was associated with R1 outcome (P = 0.02). Distal location (P = 0.002) and increased procedure time (P = 0.04) were associated with bleeding, and scarring (P = 0.009) and increased procedure duration (P = 0.003) were associated with perforation. Recurrence-free survival at 2 and 5 years was 94 % and 83 %, respectively. CONCLUSION: This is the largest Western multicenter cohort and suggests that gastric ESD is safe and effective in the Western setting. A quarter of patients fell outside the new absolute indications for ESD, suggesting that Western practice involves more advanced lesions. We identified the predictors of complications, which should help to inform future Western practice and research.

Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study.

BACKGROUND: Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs). METHODS: Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations [PIVI-1] threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines. RESULTS: Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %-93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %-98.9 %) and 92.6 % (95 %CI 90.0 %-95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %-87.3 %) than for experts (91.9 %, 95 %CI 88.5 %-94.5 %); however, nonexperts quickly approached the performance levels of experts over time. CONCLUSION: AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopists' high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.

Long-term outcomes of peroral endoscopic myotomy for achalasia: a systematic review and meta-analysis.

BACKGROUND: The long-term outcomes of esophageal peroral endoscopic myotomy (POEM) are still unknown. METHODS: We searched electronic databases (MEDLINE/PubMed, EMBASE, Scopus) for studies assessing outcomes after POEM for esophageal achalasia with a minimum median follow-up duration of 36 months. Pooled rates of clinical success and postoperative reflux were calculated and compared with the same values at 12/24/36 months when available. Subgroup analyses were performed to explore the interstudy heterogeneity. RESULTS: From 1528 initial records, 11 studies (2017-2021) were included. A total of 2342 patients (age 48.1 [SD 6.8] years; 50.1 % males) with a median follow-up of 48 months (interquartile range 45-60) were analyzed. The pooled clinical success rate was 87.3 % (95 %CI 83.6 %-91.0 %; I2  = 73.1 %). The symptomatic reflux pooled rate was 22.0 % (95 %CI 14.4 %-29.5 %; I2  = 92.7 %). Three cases of peptic strictures and one Barrett's esophagus were reported. The pooled rate of severe adverse events was 1.5 % (95 %CI 0.5 %-2.5 %; I2  = 52.8 %). CONCLUSIONS: Long-term clinical efficacy of POEM persisted in 87 % of patients with achalasia. Post-POEM symptomatic reflux remained stable over time. The risk for Barrett's esophagus and peptic strictures appeared minimal.

Feasibility and safety of a new dedicated biliary stent for EUS-guided hepaticogastrostomy: The FIT study (with video).

Background and Objectives: EUS-guided biliary drainage (BD) through hepaticogastrostomy (HGS) is an option in case of ERCP failure. Available data suggest that this procedure may be challenging with possible severe adverse events (AEs) mainly due to stent migration. The aim of our pilot study was to prospectively assess the technical and clinical outcomes of EUS-HGS using a new dedicated partially covered self-expandable metal stent with anti-migratory systems. Methods: This is a single-center prospective study enrolling patients with malignant biliary obstruction undergoing EUS-HGS after failed ERCP, between June 2020 and March 2021. The primary endpoint was the technical success rate. Evaluation of specific stent-related technical features as compared with commonly used self-expandable metal stent, clinical success rate, and procedure-related AEs was also assessed. Results: Twenty-two patients (15%-68.2%, female; mean age, 66.0 ± 10.0) were enrolled in the study analysis. Different causes of ERCP failure were infiltration of papilla by neoplastic tissue (4, 18.2%), unreachable papilla for duodenal stricture (9, 40.9%), surgically altered anatomy with Roux-en-Y reconstruction (4, 18.2%), and incomplete BD after transpapillary stent placement (5, 22.7%). Technical success was achieved in all patients, in a mean procedural time of 43.3 ± 26.8 min. Technical features were graded as high or medium in all cases. The clinical success rate was 91% (20/22, mean follow-up: 10.8 ± 3.1 months). There were no cases of stent misplacement or stent migration. Three (13.6%) cases of a hepatic abscess requiring percutaneous drainage and systemic antibiotics were reported, with no impact on clinical success and following oncologic treatments. No deaths occurred. Conclusion: EUS-HGS with a new dedicated stent with anti-migratory systems is feasible and effective, preventing stent migration, and misplacement. Although the persistent procedural challenges, dedicated devices may contribute to outcomes improvement and procedure diffusion.

Artificial intelligence in gastroenterology: Where are we heading?

Background and study aims Artificial intelligence (AI) is set to impact several fields within gastroenterology. In gastrointestinal endoscopy, AI-based tools have translated into clinical practice faster than expected. We aimed to evaluate the status of research for AI in gastroenterology while predicting its future applications. Methods All studies registered on Clinicaltrials.gov up to November 2021 were analyzed. The studies included used AI in gastrointestinal endoscopy, inflammatory bowel disease (IBD), hepatology, and pancreatobiliary diseases. Data regarding the study field, methodology, endpoints, and publication status were retrieved, pooled, and analyzed to observe underlying temporal and geographical trends. Results Of the 103 study entries retrieved according to our inclusion/exclusion criteria, 76 (74 %) were based on AI application to gastrointestinal endoscopy, mainly for detection and characterization of colorectal neoplasia (52/103, 50 %). Image analysis was also more frequently reported than data analysis for pancreaticobiliary (six of 10 [60 %]), liver diseases (eight of nine [89 %]), and IBD (six of eight [75 %]). Overall, 48 of 103 study entries (47 %) were interventional and 55 (53 %) observational. In 2018, one of eight studies (12.5 %) were interventional, while in 2021, 21 of 34 (61.8 %) were interventional, with an inverse ratio between observational and interventional studies during the study period. The majority of the studies were planned as single-center (74 of 103 [72 %]) and more were in Asia (45 of 103 [44 %]) and Europe (44 of 103 [43 %]). Conclusions AI implementation in gastroenterology is dominated by computer-aided detection and characterization of colorectal neoplasia. The timeframe for translational research is characterized by a swift conversion of observational into interventional studies.

Rectal band ligation as a treatment for chronic radiation proctitis: a feasibility study.

Background and study aims Chronic radiation proctitis (CRP) occurs in 5 % to 20 % of patients undergoing pelvic radiation therapy and frequently manifests with rectal bleeding. Endoscopic management of more severe and refractory cases can be challenging. Rectal band ligation (RBL) has been shown to be a feasible alternative to current available techniques, especially in extensive CRP. Our aim is to evaluate clinical and technical success of RBL. Patients and methods We enrolled all consecutive patients treated with RBL for severe or recurrent hemorrhagic CRP. Success was defined as endoscopic evidence of complete rectal healing and/or cessation of bleeding not requiring further treatment or blood transfusion. Results We enrolled 10 patients (7 males, mean age 75.6 years). Median length of the CRP from the anal verge was 4.5 cm and mean surface area involved was 89 %. Eight patients (80 %) were naïve to endoscopic treatment, while two had undergone argon plasma coagulation (APC). Median follow-up was 136.5 days. Success was achieved in 100 % of patients after a mean number of 1.8 RBL sessions. A mean number of 4.7 bands were released in the first session while a mean of 3.1 and 2 bands were placed in the second and third sessions, respectively. As for adverse events, only one patient reported mild tenesmus and pelvic pain after the procedure. Conclusions RBL is a safe and effective therapeutic modality for the treatment of hemorrhagic CRP. It could be considered a valid first-line option in case of extensive rectal involvement as well as a viable rescue treatment after failed APC.

Percutaneous endoscopic gastrostomy and jejunostomy: Indications and techniques.

Nutritional support is essential in patients who have a limited capability to maintain their body weight. Therefore, oral feeding is the main approach for such patients. When physiological nutrition is not possible, positioning of a nasogastric, nasojejunal tube, or other percutaneous devices may be feasible alternatives. Creating a percutaneous endoscopic gastrostomy (PEG) is a suitable option to be evaluated for patients that need nutritional support for more than 4 wk. Many diseases require nutritional support by PEG, with neurological, oncological, and catabolic diseases being the most common. PEG can be performed endoscopically by various techniques, radiologically or surgically, with different outcomes and related adverse events (AEs). Moreover, some patients that need a PEG placement are fragile and are unable to express their will or sign a written informed consent. These conditions highlight many ethical problems that become difficult to manage as treatment progresses. The aim of this manuscript is to review all current endoscopic techniques for percutaneous access, their indications, postprocedural follow-up, and AEs.

Endoscopic ultrasound-guided ablation of solid pancreatic lesions: A systematic review of early outcomes with pooled analysis.

BACKGROUND: Endoscopic ultrasound-guided radiofrequency ablation (EUS-RFA) is emerging as a complementary therapeutic approach for pancreatic solid masses. However, results of published data are difficult to interpret because of a retrospective design and small sample size. AIM: To systematically review data on EUS-RFA for solid lesions and to pool the results of the different experiences in order to provide more consistent evidence in terms of safety and efficacy. METHODS: A comprehensive systematic literature search on the main databases was performed to identify articles in which patients with pancreatic solid lesions underwent EUS-RFA. The primary outcomes were procedure-related adverse events (AEs) and mortality. Secondary outcomes were the technical success rate and the effects on primary tumor growth. Statistical analyses were performed using Stata version 14.0. RESULTS: In total, 14 studies were included, with 120 patients undergoing 153 ablations of 129 solid pancreatic lesions. The STARmed technology was used in seven studies, the Habib system in six studies, and the HybridTherm probe in one study. The pooled technical success rate was 99.0% (I 2: 25.82%). The pooled overall AE rate was 8.0% (I 2: 11.46%). Excluding mild AEs, the pooled rates of serious AEs was 1.0% (I 2: 0%). No mortality related to the procedure was reported. CONCLUSION: The present pooled analysis confirms the safety and feasibility of EUS-RFA.

Endoscopic submucosal dissection for colorectal neoplasia: outcomes and predictors of recurrence.

Background and study aims The role of endoscopic submucosal dissection (ESD) for colorectal lesions in Western communities is unclear and its adoption is still limited. The aim of this study is to assess the long-term outcomes of a large cohort of patients treated with colorectal ESD in a tertiary Western center. Patients and methods A retrospective analysis was conducted on patients treated by ESD for superficial colorectal lesions between February 2011 and November 2019. The primary outcome was the recurrence rate. Secondary outcomes were en-bloc and R0 resection rates, procedural time, adverse events (AEs), and need for surgery. The curative resection rate was assessed for submucosal invasive lesions. Results A total of 327 consecutive patients, median age 69 years (IQR 60-76); 201 men (61.5 %) were included in the analysis. Of the lesions, 90.8 % were resected in an en-bloc fashion. The rate of R0 resection was 83.1 % (217/261) and 44.0 % (29/66) for standard and hybrid ESD techniques, respectively. Submucosal invasion and piecemeal resection independently predicted R1 resections. A total of 18(5.5 %) intra-procedural AEs (perforation:11, bleeding:7) and 12(3.7 %) post-procedural AEs occurred (perforation:2, bleeding: 10). Eighteen adenoma recurrences per 1,000 person-years (15cases, 5.6 %) were detected after a median follow-up time of 36 months. All recurrences were detected within 12 months. No carcinoma recurrences were observed. R1 resection status and intra-procedural AEs independently predicted recurrences with seven vs 150 recurrences per 1,000 person-years in the R0 vs R1 group, respectively. Conclusions Colorectal ESD is a safe and effective option for managing superficial colorectal neoplasia in a Western setting, with short and long-terms outcomes comparable to Eastern studies. En-bloc R0 resection and absence of intra-procedural AEs are associated with reduced risk of recurrence.

Sporadic non-ampullary duodenal adenomas: efficacy and outcomes of endoscopic resection.

BACKGROUND AND AIMS: Sporadic non-ampullary duodenal adenomas (SNDAs) are often referred to tertiary centers because of the challenges in endoscopic resection. There is a paucity of data on both technical and clinical outcomes. The aim of our study was to evaluate the efficacy and safety of endoscopic resection for the treatment of SNDA in two western centers. METHODS: This is a retrospective study reporting data of a cohort of patients referred for resection of SNDA between 2013 and 2017. Patients with familial adenomatous polyposis or ampullary lesions were excluded from present analysis. Outcomes considered for this study were technical success, adverse events, recurrence and need for surgery. RESULTS: 120 patients (mean age 66 ± 11.9 years, 64male) were enrolled in the study. Mean size of the lesions was 23.3 mm (range 5-80). Fifty-six en-bloc endoscopic mucosal resection (EMR) (46.6%), 41 piecemeal EMR (pEMR) and 23 endoscopic submucosal dissection were performed. Intra-procedural perforation was observed in 4 patients (3.3%). Fourteen post-procedural (11.6%) adverse events were recorded. All post-procedural perforations occurred in lesions > 30 mm. Recurrence was observed in 11 patients (9.5%) during a mean follow-up of 29 months. All recurrences were successfully managed endoscopically. 119 patients were still alive at last follow-up. CONCLUSION: Endoscopic resection can be successfully carried out in majority of patients. Size > 30 mm seems to be the predictor of high adverse events risk.

Comparing the number and relevance of false activations between 2 artificial intelligence computer-aided detection systems: the NOISE study.

BACKGROUND AND AIMS: Artificial intelligence has been shown to be effective in polyp detection, and multiple computer-aided detection (CADe) systems have been developed. False-positive (FP) activation emerged as a possible way to benchmark CADe performance in clinical practice. The aim of this study was to validate a previously developed classification of FPs comparing the performances of different brands of approved CADe systems. METHODS: We compared 2 different consecutive video libraries (40 video per arm) collected at Humanitas Research Hospital with 2 different CADe system brands (CADe A and CADe B). For each video, the number of CADe false activations, cause, and time spent by the endoscopist to examine the area erroneously highlighted were reported. The FP activations were classified according to the previously developed classification of FPs (the NOISE classification) according to their cause and relevance. RESULTS: In CADe A 1021 FP activations were registered across the 40 videos (25.5 ± 12.2 FPs per colonoscopy), whereas in CADe B 1028 were identified (25.7 ± 13.2 FPs per colonoscopy; P = .53). Among them, 22.9 ± 9.9 (89.8% in CADe A) and 22.1 ± 10.0 (86.0% in CADe B) were because of artifacts from the bowel wall. Conversely, 2.6 ± 1.9 (10.2% in CADe A) and 3.5 ± 2.1 (14% in CADe B) were caused by bowel content (P = .45). Within CADe A each false activation required .2 ± .9 seconds, with 1.6 ± 1.0 FPs (6.3%) requiring additional time for endoscopic assessment. Comparable results were reported within CADe B with .2 ± .8 seconds spent per false activation and 1.8 ± 1.2 FPs per colonoscopy requiring additional inspection. CONCLUSIONS: The use of a standardized nomenclature provided comparable results with either of the 2 recently approved CADe systems. (Clinical trial registration number: NCT04399590.).

Artificial intelligence and colonoscopy experience: lessons from two randomised trials.

BACKGROUND AND AIMS: Artificial intelligence has been shown to increase adenoma detection rate (ADR) as the main surrogate outcome parameter of colonoscopy quality. To which extent this effect may be related to physician experience is not known. We performed a randomised trial with colonoscopists in their qualification period (AID-2) and compared these data with a previously published randomised trial in expert endoscopists (AID-1). METHODS: In this prospective, randomised controlled non-inferiority trial (AID-2), 10 non-expert endoscopists (<2000 colonoscopies) performed screening/surveillance/diagnostic colonoscopies in consecutive 40-80 year-old subjects using high-definition colonoscopy with or without a real-time deep-learning computer-aided detection (CADe) (GI Genius, Medtronic). The primary outcome was ADR in both groups with histology of resected lesions as reference. In a post-hoc analysis, data from this randomised controlled trial (RCT) were compared with data from the previous AID-1 RCT involving six experienced endoscopists in an otherwise similar setting. RESULTS: In 660 patients (62.3±10 years; men/women: 330/330) with equal distribution of study parameters, overall ADR was higher in the CADe than in the control group (53.3% vs 44.5%; relative risk (RR): 1.22; 95% CI: 1.04 to 1.40; p<0.01 for non-inferiority and p=0.02 for superiority). Similar increases were seen in adenoma numbers per colonoscopy and in small and distal lesions. No differences were observed with regards to detection of non-neoplastic lesions. When pooling these data with those from the AID-1 study, use of CADe (RR 1.29; 95% CI: 1.16 to 1.42) and colonoscopy indication, but not the level of examiner experience (RR 1.02; 95% CI: 0.89 to 1.16) were associated with ADR differences in a multivariate analysis. CONCLUSIONS: In less experienced examiners, CADe assistance during colonoscopy increased ADR and a number of related polyp parameters as compared with the control group. Experience appears to play a minor role as determining factor for ADR. TRIAL REGISTRATION NUMBER: NCT:04260321.

Submucosal tunnelling techniques for Zenker's diverticulum: a systematic review of early outcomes with pooled analysis.

In the last decade, flexible endoscopic septotomy has been reported as a well-tolerated and effective treatment for Zenker's diverticulum. More recently, novel endoscopic submucosal tunneling techniques, namely Zenker-PerOral Endoscopic Myotomy (Z-POEM) and PerOral Endoscopic Septotomy (POES) have been proposed to obtain complete muscular septum exposure and deeper myotomy. The aim of this study is to provide a systematic review with a meta-analysis of the first experiences of third space approaches for Zenker's diverticulum. Electronic databases (Medline, Scopus, EMBASE) were searched up to October 2020. Studies including patients with symptomatic Zenker's diverticulum who underwent endoscopic treatment by submucosal tunneling technique were eligible. Procedural, clinical and safety outcomes were assessed by pooling data with a random-effect model to obtain a proportion with a 95% confidence interval. Nine retrospective studies were eligible for inclusion (196 patients). Five studies were performed in the USA, two in Europe and two in Asia. Endoscopic treatment was feasible in 96.9% (I2 = 0%) of patients. The mean procedure duration was 36.4 ± 14.3 minutes. Clinical success was achieved after 93.4% (I2 = 0%) of procedures. The overall adverse events rate was 4.9% (I2 = 0%). No differences between the two approaches (Z-POEM vs POES) have been shown in terms of both efficacy and safety. Submucosal tunneling techniques appear to be feasible for symptomatic Zenker's diverticulum, with promising results in terms of efficacy and safety outcomes.

Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis.

BACKGROUND: Computer-aided detection (CADe) techniques based on artificial intelligence algorithms can assist endoscopists in detecting colorectal neoplasia. CADe has been associated with an increased adenoma detection rate, a key quality indicator, but the utility of CADe compared with existing advanced imaging techniques and distal attachment devices is unclear. METHODS: For this systematic review and network meta-analysis, we did a comprehensive search of PubMed/Medline, Embase, and Scopus databases from inception to Nov 30, 2020, for randomised controlled trials investigating the effectiveness of the following endoscopic techniques in detecting colorectal neoplasia: CADe, high definition (HD) white-light endoscopy, chromoendoscopy, or add-on devices (ie, systems that increase mucosal visualisation, such as full spectrum endoscopy [FUSE] or G-EYE balloon endoscopy). We collected data on adenoma detection rates, sessile serrated lesion detection rates, the proportion of large adenomas detected per colonoscopy, and withdrawal times. A frequentist framework, random-effects network meta-analysis was done to compare artificial intelligence with chromoendoscopy, increased mucosal visualisation systems, and HD white-light endoscopy (the control group). We estimated odds ratios (ORs) for the adenoma detection rate, sessile serrated lesion detection rate, and proportion of large adenomas detected per colonoscopy, and calculated mean differences for withdrawal time, with 95% CIs. Risk of bias and certainty of evidence were assessed with the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. FINDINGS: 50 randomised controlled trials, comprising 34 445 participants, were included in our main analysis (six trials of CADe, 18 of chromoendoscopy, and 26 of increased mucosal visualisation systems). HD white-light endoscopy was the control technique in all 50 studies. Compared with the control technique, the adenoma detection rate was 7·4% higher with CADe (OR 1·78 [95% CI 1·44-2·18]), 4·4% higher with chromoendoscopy (1·22 [1·08-1·39]), and 4·1% higher with increased mucosal visualisation systems (1·16 [1·04-1·28]). CADe ranked as the superior technique for adenoma detection (with moderate confidence in hierarchical ranking); cross-comparisons of CADe with other imaging techniques showed a significant increase in the adenoma detection rate with CADe versus increased mucosal visualisation systems (OR 1·54 [95% CI 1·22-1·94]; low certainty of evidence) and with CADe versus chromoendoscopy (1·45 [1·14-1·85]; moderate certainty of evidence). When focusing on large adenomas (≥10 mm) there was a significant increase in the detection of large adenomas only with CADe (OR 1·69 [95% CI 1·10-2·60], moderate certainty of evidence) when compared to HD white-light endoscopy; CADe ranked as the superior strategy for detection of large adenomas. CADe also seemed to be the superior strategy for detection of sessile serrated lesions (with moderate confidence in hierarchical ranking), although no significant increase in the sessile serrated lesion detection rate was shown (OR 1·37 [95% CI 0·65-2·88]). No significant difference in withdrawal time was reported for CADe compared with the other techniques. INTERPRETATION: Based on the published literature, detection rates of colorectal neoplasia are higher with CADe than with other techniques such as chromoendoscopy or tools that increase mucosal visualisation, supporting wider incorporation of CADe strategies into community endoscopy services. FUNDING: None.

How to trick artificial intelligence: rectal heterotopic gastric lateral spreading tumor.

Video 1.