One-fourth of colorectal neoplasias are missed during screening colonoscopies; these can develop into colorectal cancer (CRC). Deep learning systems allow for real-time computer-aided detection ...(CADe) of polyps with high accuracy. We performed a multicenter, randomized trial to assess the safety and efficacy of a CADe system in detection of colorectal neoplasias during real-time colonoscopy.
We analyzed data from 685 subjects (61.32 ± 10.2 years old; 337 men) undergoing screening colonoscopies for CRC, post-polypectomy surveillance, or workup due to positive results from a fecal immunochemical test or signs or symptoms of CRC, at 3 centers in Italy from September through November 2019. Patients were randomly assigned (1:1) to groups who underwent high-definition colonoscopies with the CADe system or without (controls). The CADe system included an artificial intelligence–based medical device (GI-Genius, Medtronic) trained to process colonoscopy images and superimpose them, in real time, on the endoscopy display a green box over suspected lesions. A minimum withdrawal time of 6 minutes was required. Lesions were collected and histopathology findings were used as the reference standard. The primary outcome was adenoma detection rate (ADR, the percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, non-neoplastic resection rate, and withdrawal time.
The ADR was significantly higher in the CADe group (54.8%) than in the control group (40.4%) (relative risk RR, 1.30; 95% confidence interval CI, 1.14–1.45). Adenomas detected per colonoscopy were significantly higher in the CADe group (mean, 1.07 ±1.54) than in the control group (mean 0.71 ± 1.20) (incidence rate ratio, 1.46; 95% CI, 1.15–1.86). Adenomas 5 mm or smaller were detected in a significantly higher proportion of subjects in the CADe group (33.7%) than in the control group (26.5%; RR, 1.26; 95% CI, 1.01–1.52), as were adenomas of 6 to 9 mm (detected in 10.6% of subjects in the CADe group vs 5.8% in the control group; RR, 1.78; 95% CI, 1.09–2.86), regardless of morphology or location. There was no significant difference between groups in withdrawal time (417 ± 101 seconds for the CADe group vs 435 ± 149 for controls; P = .1) or proportion of subjects with resection of non-neoplastic lesions (26.0% in the CADe group vs 28.7% of controls; RR, 1.00; 95% CI, 0.90–1.12).
In a multicenter, randomized trial, we found that including CADe in real-time colonoscopy significantly increases ADR and adenomas detected per colonoscopy without increasing withdrawal time. ClinicalTrials.gov no: 04079478
Display omitted
Background and aimsArtificial 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).MethodsIn 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.ResultsIn 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.ConclusionsIn 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 numberNCT:04260321.
Abstract
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 endoscopistsʼ high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.
False positive (FP) results by computer-aided detection (CADe) hamper the efficiency of colonoscopy by extending examination time. Our aim was to develop a classification of the causes and clinical ...relevance of CADe FPs, and to assess the relative distribution of FPs in a real-life setting.
In a post-hoc analysis of a randomized trial comparing colonoscopy with and without CADe (NCT: 04079478), we extracted 40 CADe colonoscopy videos. Using a modified Delphi process, 4 expert endoscopists identified the main domains for the reasons and clinical relevance of FPs. Then, 2 expert endoscopists manually examined each FP and classified it according to the proposed domains. The analysis was limited to the withdrawal phase.
The 2 main domains for the causes of CADe FPs were identified as artifacts due to either the mucosal wall or bowel content, and clinical relevance was defined as the time spent on FPs and the FP rate per minute. The mean number of FPs per colonoscopy was 27.3 ± 13.1, of which 24 ± 12 (88%) and 3.2 ± 2.6 (12%) were due to artifacts in the bowel wall and bowel content, respectively. Of the 27.3 FPs per colonoscopy, 1.6 (5.7%) required additional exploration time of 4.8 ± 6.2 seconds per FP (ie, 0.7% of the mean withdrawal time). In detail, 15 (24.2%), 33 (53.2%), and 14 (22.6%) FPs were classified as being of mild, moderate, or severe clinical relevance. The rate of FPs per minute of withdrawal time was 2.4 ± 1.2, and was higher for FPs due to artifacts from the bowel wall than for those from bowel content (2.4 ± 0.6 vs 0.3 ± 0.2, P < .001).
FPs by CADe are primarily due to artifacts from the bowel wall. Despite a high frequency, FPs result in a negligible 1% increase in the total withdrawal time because most of them are immediately discarded by the endoscopist.
In recent years, the feasibility and safety of endoscopic placement of different biodegradable biliary stents have been investigated. New, helicoidally shaped, biliary and pancreatic biodegradable ...stents have been developed for endoscopic use. Stents are provided in different sizes and with 3 expected speeds of degradation: slow (11 weeks), medium (20 days), and fast (12 days). The aim of this study was to evaluate degradation time, technical outcomes, and safety of these stents.
This was a single-center, prospective, pilot study (August 2018 to January 2019) of consecutive patients with indication for biliary or pancreatic plastic stent positioning during ERCP. The primary outcome was the evaluation of degradation time of the stents, which was controlled by abdominal radiograph. Secondary outcomes were the evaluation of specific stent-related technical features (loadability, pushability, and fluoroscopic visibility) as compared with commonly used plastic stents and adverse events (AEs).
Thirty-eight patients (11 women 28.9%; median age, 68.05 ± 10.74 years) who received 53 biodegradable stents (34 64.2% biliary and 19 35.8% pancreatic stents) were enrolled in the study. Thirty-five (66%) slow-degrading stents, 6 (11.3%) medium-degrading stents, and 12 (22.6%) fast-degrading stents were used. At time 1, partial degradation of the stents was present in 48 cases (90.6%). Five stents (9.4%) prematurely migrated. At the subsequent time 2 evaluation, complete degradation occurred in 100% of cases. Stent loadability was defined as excellent in all cases. Pushability of the stent was scored as excellent in 48 cases (90.5%), good in 4 cases (7.5%), and fair in 1 case (1.9%). Fluoroscopic visualization was excellent in 11 cases (20.8%), good in 39 cases (73.6%), and fair in 3 (5.6%). Only 1 AE of mild post-ERCP pancreatitis occurred.
The results of our study suggest that the biodegradation of the new biliary and pancreatic stents is reliable and in line with expected times and technically successful in a variety of indications. Further randomized multicenter studies are required to validate our preliminary findings. (Clinical trial registration number: NCT03767166.)
AimsESD is a minimally invasive therapeutic option for early oesophageal neoplasia, however is not without risk. In Europe, the complication profile is most established for Barrett’s neoplasia, being ...the predominant pathology, and stricture risk has been shown to be related to lesion circumference. Our aim was to compare the safety of ESD between Barrett’s and squamous neoplasia in a Western population.MethodsThis was a retrospective analysis of all oesophageal ESDs performed within 3 tertiary referral centres in Europe. The primary outcome was post procedure stricture rate.Results226 oesophageal ESDs from 201 patients were included, consisting of 167 Barrett’s and 59 squamous neoplasia. Average age was 70.7 in Barrett’s and 68.5 in squamous neoplasia, with lesion size 34.6 mm and 34.2 mm and en bloc resection rate 96.6 and 94.6% respectively. The complication rate was 3/167 perforations or delayed bleeds and 7/167 strictures in Barrett’s, with 1/58 perforations or delayed bleeds and 15/58 strictures in squamous (1 patient lost to follow up). Circumferential lesion involvement did increase stricture risk, but did not account for the difference between the two groups (table 1).Abstract P227 Table 1Stricture Risk Stratified by Circumferential Lesion Involvement Lesion circumference (%) Strictures in Barrett’s ESD (n,%) Strictures in Squamous ESD (n,%) p-value ≤1/3 0/98 (0.0%) 3/23 (13.0%) <0.001 >1/3–2/3 1/56 (1.8%) 6/26 (23.1%) 0.001 >2/3 6/13 (46.2%) 6/9 (66.7%) 0.354 ConclusionsESD remains a low risk therapeutic option for early oesophageal neoplasia, however the stricture risk is higher in squamous neoplasia, irrespective of circumferential lesion involvement. We would suggest counselling patients with squamous neoplasia for a higher risk of stricture and having a lower threshold for steroid injection or prophylactic dilatation in these patients.
IntroductionEndoscopic submucosal dissection is considered the first line treatment for early gastric neoplasia, and extensive data is reported from the Far East demonstrating its efficacy and safety ...even in expanded criteria in the Japanese guidelines. Data from the west is still limited to mostly small series from single centres. In this study, we describe a large multicentre, European cohort and review outcome and safety of gastric ESD in the hands of western experts in the light of the latest Japanese indication criteria.MethodsThis is a prospective observational cohort study conducted in four large endoscopy referral centres in four European countries. Study included patients referred for gastric ESD in participating centres in the period from 2009 to 2020. Data was prospectively collected on patient demographics, lesion characteristics, procedure details and outcomes of endoscopic treatment. Indications for endoscopic resection were categorised according to the latest Japanese guidelines. Patients were followed up clinically and endoscopically as per standard protocols. Statistical analysis using logistic regression was performed.ResultsA total of 340 patients were included. Mean age was 72 years and 55.6% were males. Absolute criteria were fulfilled in 74.4% of patients. Median follow up duration was 39 months. Post resection histology was adenocarcinoma, HGD, LGD and other in 52.5%, 20.7%, 16.8% and 10.0% respectively. Poor differentiation was reported in 14.6% of adenocarcinoma. Early bleeding, delayed bleeding and perforation occurred in 5.3%, 3.2% and 2.1% respectively. En bloc, R0 and recurrence rates were 93.8%, 82.9% and 6.7%. Relative indication was independently associated with R1 outcome (OR 3.90, 95% CI 1.64, 9.24, P value 0.002). Table (1) below summarises the outcomes and complications.Abstract O1 Table 1Outcomes and complications of endoscopic resection of early gastric neoplasia n=340 Outcome N Category Number (%) En-bloc 340 Yes 319 (93.8%) Margins 340 R0 282 (82.9%) Recurrence (3–6 months) 340 Yes 14 (4.1%) Delayed Recurrence 340 Yes 9 (2.6%) Bleeding 340 Early 18 (5.3%) Delayed 11 (3.2%) Management of bleeding 29 Conservative-PPI 4 (13.8%) Endoscopic 23 (79.3%) Radiologic 1 (3.5%) Surgical 1 (3.5%) Transfusion required 29 Yes 9 (31.0%) Perforation 340 Yes 7 (2.1%) Management ofPerforation 7 Conservative 1 (14.3%) Endoscopic 5 (71.4%) Surgery 1 (14.3%) ConclusionThis is the largest, multicentre, European cohort suggesting ESD is safe and effective treatment of early gastric neoplasia in the western setting. Our data suggests the Japanese expanded and relative criteria for gastric ESD may be safe in the western practice; however more data is needed to fully characterise this group and inform future selection and surveillance guidelines.
Multiple therapeutic modalities including surgery and rigid and flexible endoscopy have been adopted to manage Zenker's diverticulum (ZD). Minimally invasive flexible endoscopic septotomy (FES) ...techniques have been increasingly favored over the past 20 years; however, long-term data are still scanty. The aim of this study is to evaluate early and long-term outcomes of FES for naive ZD in a single-center setting.
From 2010 to 2017, ZD patients treated with FES were included in a prospectively maintained database (NCT03948438). Those who had already been treated surgically or endoscopically were excluded from the analysis. The Dakkak and Bennett dysphagia scale was used to rate the dysphagia. Persistent complete or near-complete resolution of symptoms (Dakkak and Bennett 0 or 1) was defined as clinical success. Postprocedural adverse events were reported according to ASGE lexicon.
Overall, 256 consecutive patients were treated. Mean pouch size was 29.8 ± 11.3 mm. The procedure was successfully completed in all scheduled patients, with an early clinical success of 96.1%. Adverse events occurred in 3.5% (9/256) of patients. Eight of them were mild/moderate with no fatal events, whereas one patient required surgery. Recurrences occurred in 31.3% (80/256) of treated patients after a mean time of 9 ± 3 months and 95% of recurrences were treated by a second FES. At an average follow-up of 5.5 years, 95.3% of patients were asymptomatic after a mean number of 1.3 procedures.
FES is a safe and effective treatment modality for patients with ZD. Recurrence rate is significant; however, endoscopic reintervention is associated with long-term relief of dysphagia.
