Computer-Aided Diagnosis for Leaving Colorectal Polyps In Situ : A Systematic Review and Meta-analysis.

BACKGROUND: Computer-aided diagnosis (CADx) allows prediction of polyp histology during colonoscopy, which may reduce unnecessary removal of nonneoplastic polyps. However, the potential benefits and harms of CADx are still unclear. PURPOSE: To quantify the benefit and harm of using CADx in colonoscopy for the optical diagnosis of small (≤5-mm) rectosigmoid polyps. DATA SOURCES: Medline, Embase, and Scopus were searched for articles published before 22 December 2023. STUDY SELECTION: Histologically verified diagnostic accuracy studies that evaluated the real-time performance of physicians in predicting neoplastic change of small rectosigmoid polyps without or with CADx assistance during colonoscopy. DATA EXTRACTION: The clinical benefit and harm were estimated on the basis of accuracy values of the endoscopist before and after CADx assistance. The certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. The outcome measure for benefit was the proportion of polyps predicted to be nonneoplastic that would avoid removal with the use of CADx. The outcome measure for harm was the proportion of neoplastic polyps that would be not resected and left in situ due to an incorrect diagnosis with the use of CADx. Histology served as the reference standard for both outcomes. DATA SYNTHESIS: Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed. The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change. In the studies that compared histology prediction performance before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; risk ratio [RR], 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence) or in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence). LIMITATION: The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator. CONCLUSION: Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy. PRIMARY FUNDING SOURCE: European Commission. (PROSPERO: CRD42023402197).

Real-Time Computer-Aided Detection of Colorectal Neoplasia During Colonoscopy : A Systematic Review and Meta-analysis.

BACKGROUND: Artificial intelligence computer-aided detection (CADe) of colorectal neoplasia during colonoscopy may increase adenoma detection rates (ADRs) and reduce adenoma miss rates, but it may increase overdiagnosis and overtreatment of nonneoplastic polyps. PURPOSE: To quantify the benefits and harms of CADe in randomized trials. DESIGN: Systematic review and meta-analysis. (PROSPERO: CRD42022293181). DATA SOURCES: Medline, Embase, and Scopus databases through February 2023. STUDY SELECTION: Randomized trials comparing CADe-assisted with standard colonoscopy for polyp and cancer detection. DATA EXTRACTION: Adenoma detection rate (proportion of patients with ≥1 adenoma), number of adenomas detected per colonoscopy, advanced adenoma (≥10 mm with high-grade dysplasia and villous histology), number of serrated lesions per colonoscopy, and adenoma miss rate were extracted as benefit outcomes. Number of polypectomies for nonneoplastic lesions and withdrawal time were extracted as harm outcomes. For each outcome, studies were pooled using a random-effects model. Certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. DATA SYNTHESIS: Twenty-one randomized trials on 18 232 patients were included. The ADR was higher in the CADe group than in the standard colonoscopy group (44.0% vs. 35.9%; relative risk, 1.24 [95% CI, 1.16 to 1.33]; low-certainty evidence), corresponding to a 55% (risk ratio, 0.45 [CI, 0.35 to 0.58]) relative reduction in miss rate (moderate-certainty evidence). More nonneoplastic polyps were removed in the CADe than the standard group (0.52 vs. 0.34 per colonoscopy; mean difference [MD], 0.18 polypectomy [CI, 0.11 to 0.26 polypectomy]; low-certainty evidence). Mean inspection time increased only marginally with CADe (MD, 0.47 minute [CI, 0.23 to 0.72 minute]; moderate-certainty evidence). LIMITATIONS: This review focused on surrogates of patient-important outcomes. Most patients, however, may consider cancer incidence and cancer-related mortality important outcomes. The effect of CADe on such patient-important outcomes remains unclear. CONCLUSION: The use of CADe for polyp detection during colonoscopy results in increased detection of adenomas but not advanced adenomas and in higher rates of unnecessary removal of nonneoplastic polyps. PRIMARY FUNDING SOURCE: European Commission Horizon 2020 Marie Sklodowska-Curie Individual Fellowship.

Impact of Artificial Intelligence on Colonoscopy Surveillance After Polyp Removal: A Pooled Analysis of Randomized Trials.

BACKGROUND AND AIMS: Artificial intelligence (AI) tools aimed at improving polyp detection have been shown to increase the adenoma detection rate during colonoscopy. However, it is unknown how increased polyp detection rates by AI affect the burden of patient surveillance after polyp removal. METHODS: We conducted a pooled analysis of 9 randomized controlled trials (5 in China, 2 in Italy, 1 in Japan, and 1 in the United States) comparing colonoscopy with or without AI detection aids. The primary outcome was the proportion of patients recommended to undergo intensive surveillance (ie, 3-year interval). We analyzed intervals for AI and non-AI colonoscopies for the U.S. and European recommendations separately. We estimated proportions by calculating relative risks using the Mantel-Haenszel method. RESULTS: A total of 5796 patients (51% male, mean 53 years of age) were included; 2894 underwent AI-assisted colonoscopy and 2902 non-AI colonoscopy. When following U.S. guidelines, the proportion of patients recommended intensive surveillance increased from 8.4% (95% CI, 7.4%-9.5%) in the non-AI group to 11.3% (95% CI, 10.2%-12.6%) in the AI group (absolute difference, 2.9% [95% CI, 1.4%-4.4%]; risk ratio, 1.35 [95% CI, 1.16-1.57]). When following European guidelines, it increased from 6.1% (95% CI, 5.3%-7.0%) to 7.4% (95% CI, 6.5%-8.4%) (absolute difference, 1.3% [95% CI, 0.01%-2.6%]; risk ratio, 1.22 [95% CI, 1.01-1.47]). CONCLUSIONS: The use of AI during colonoscopy increased the proportion of patients requiring intensive colonoscopy surveillance by approximately 35% in the United States and 20% in Europe (absolute increases of 2.9% and 1.3%, respectively). While this may contribute to improved cancer prevention, it significantly adds patient burden and healthcare costs.

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.

Texture and color enhancement imaging versus high definition white-light endoscopy for detection of colorectal neoplasia: a randomized trial.

BACKGROUND: Texture and color enhancement imaging (TXI) was recently proposed as a substitute for standard high definition white-light imaging (WLI) to increase lesion detection during colonoscopy. This international, multicenter randomized trial assessed the efficacy of TXI in detection of colorectal neoplasia. METHODS: Consecutive patients aged ≥ 40 years undergoing screening, surveillance, or diagnostic colonoscopies at five centers (Italy, Germany, Japan) between September 2021 and May 2022 were enrolled. Patients were randomly assigned (1:1) to TXI or WLI. Primary outcome was adenoma detection rate (ADR). Secondary outcomes were adenomas per colonoscopy (APC) and withdrawal time. Relative risks (RRs) adjusted for age, sex, and colonoscopy indication were calculated. RESULTS: We enrolled 747 patients (mean age 62.3 [SD 9.5] years, 50.2 % male). ADR was significantly higher with TXI (221/375, 58.9 %) vs. WLI (159/372, 42.7 %; adjusted RR 1.38 [95 %CI 1.20-1.59]). This was significant for ≤ 5 mm (RR 1.42 [1.16-1.73]) and 6-9 mm (RR 1.36 [1.01-1.83]) adenomas. A higher proportion of polypoid (151/375 [40.3 %] vs. 104/372 [28.0 %]; RR 1.43 [1.17-1.75]) and nonpolypoid (136/375 [36.3 %] vs. 102/372 [27.4 %]; RR 1.30 [1.05-1.61]) adenomas, and proximal (143/375 [38.1 %] vs. 111/372 [29.8 %]; RR 1.28 [1.05-1.57]) and distal (144/375 [38.4 %] vs. 98/372 [26.3 %]; RR 1.46 [1.18-1.80]) lesions were found with TXI. APC was higher with TXI (1.36 [SD 1.79] vs. 0.89 [SD 1.35]; incident rate ratio 1.53 [1.25-1.88]). CONCLUSIONS: TXI increased ADR and APC among patients undergoing colonoscopy for various indications. TXI increased detection of polyps < 10 mm, both in the proximal and distal colon, and may help to improve colonoscopy quality indicators.

Wide-area transepithelial sampling with computer-assisted analysis to detect high grade dysplasia and cancer in Barrett's esophagus: a multicenter randomized study.

BACKGROUND: Current surveillance for Barrett's esophagus (BE), consisting of four-quadrant random forceps biopsies (FBs), has an inherent risk of sampling error. Wide-area transepithelial sampling (WATS) may increase detection of high grade dysplasia (HGD) and esophageal adenocarcinoma (EAC). In this multicenter randomized trial, we aimed to evaluate WATS as a substitute for FB. METHODS: Patients with known BE and a recent history of dysplasia, without visible lesions, at 17 hospitals were randomized to receive either WATS followed by FB or vice versa. All WATS samples were examined, with computer assistance, by at least two experienced pathologists at the CDx Diagnostics laboratory. Similarly, all FBs were examined by two expert pathologists. The primary end point was concordance/discordance for detection of HGD/EAC between the two techniques. RESULTS: 172 patients were included, of whom 21 had HGD/EAC detected by both modalities, 18 had HGD/EAC detected by WATS but missed by FB, and 12 were detected by FB but missed by WATS. The detection rate of HGD/EAC did not differ between WATS and FB (P = 0.36). Using WATS as an adjunct to FB significantly increased the detection of HGD/EAC vs. FB alone (absolute increase 10 % [95 %CI 6 % to 16 %]). Mean procedural times in minutes for FB alone, WATS alone, and the combination were 6.6 (95 %CI 5.9 to 7.1), 4.9 (95 %CI 4.1 to 5.4), and 11.2 (95 %CI 10.5 to 14.0), respectively. CONCLUSIONS: Although the combination of WATS and FB increases dysplasia detection in a population of BE patients enriched for dysplasia, we did not find a statistically significant difference between WATS and FB for the detection of HGD/EAC as single modality.

Rapid on-site evaluation improves the sensitivity of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) for solid pancreatic lesions irrespective of technique: A single-centre experience.

OBJECTIVE: Endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) is the first-line technique for the sampling of pancreatic lesions. Many factors can influence the diagnostic performance of this procedure, including the use of rapid on-site evaluation (ROSE). The primary aim of this study was to compare the adequacy, diagnostic yield, accuracy, sensitivity and specificity of EUS-FNA for solid pancreatic lesions before and after the introduction of ROSE. METHODS: This retrospective single-centre study evaluated all consecutive patients who underwent EUS-FNA for suspicious, solid pancreatic masses from April 2012 to March 2015. We compared the findings of EUS-FNA procedures performed during the first and second years following the adoption of ROSE ("ROSE1" and "ROSE2", respectively) to those performed the year before ROSE introduction (the "pre-ROSE" group). RESULTS: Ninety-one consecutive patients with a total of 93 pancreatic lesions were enrolled. For the pre-ROSE, ROSE1 and ROSE2 groups, the adequacy rates were 96.2%, 96.6% and 100%, the diagnostic yield values were 76.9%, 89.7% and 92.1% and accuracy values were 69.2%, 86.2% and 89.5% (p = NS). Sensitivity for malignancy improved from 63.7% in the pre-ROSE group to 91.7% and 91.2% in the post-ROSE groups (p < 0.05). Specificity for malignancy was 100% in all groups. CONCLUSIONS: ROSE can improve the diagnostic performance of EUS-FNA for solid pancreatic lesions, although only sensitivity reached statistical significance.

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.

A randomised controlled trial of digital breast tomosynthesis vs digital mammography as primary screening tests: Screening results over subsequent episodes of the Proteus Donna study.

Proteus Donna is a randomised controlled trial aimed at prospectively evaluating screening with digital breast tomosynthesis (DBT), including interval cancer detection (ICD) and cancer detection (CD) in the analysis as a cumulative measure over subsequent screening episodes. Consenting women aged 46 to 68 attending the regional Breast Screening Service were randomly assigned to conventional digital mammography (DM, control arm) or DBT in addition to DM (DBT, study arm). At the subsequent round all participants underwent DM. Thirty-six months follow-up allowed for the identification of cancers detected in the subsequent screening and interscreening interval. Relative risk (RR) and 95% confidence interval (95% CI) were computed. Cumulative CD and Nelson-Aalen incidence were analysed over the follow-up period. Between 31 December 2014 and 31 December 2017, 43 022 women were randomised to DM and 30 844 to DBT. At baseline, CD was significantly higher (RR: 1.44, 95% CI: 1.21-1.71) in the study arm. ICD did not differ significantly between the two arms (RR: 0.92, 95% CI: 0.62-1.35). At subsequent screening with DM, the CD was lower (nearly significant) in the study arm (RR: 0.83, 95% CI: 0.65-1.06). Over the follow-up period, the cumulative CD (comprehensive of ICD) was slightly higher in the study arm (RR: 1.15, 95% CI: 1.01-1.31). The Nelson-Aalen cumulative incidence over time remained significantly higher in the study arm for approximately 24 months. Benign lesions detection was higher in the study arm at baseline and lower at subsequent tests. Outcomes are consistent with a lead time gain of DBT compared to DM, with an increase in false positives and moderate overdiagnosis.

Endoscopic Ultrasound-guided Fine-needle Biopsy With or Without Rapid On-site Evaluation for Diagnosis of Solid Pancreatic Lesions: A Randomized Controlled Non-Inferiority Trial.

BACKGROUND AND AIMS: The benefit of rapid on-site evaluation (ROSE) on the diagnostic accuracy of endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) has never been evaluated in a randomized study. This trial aimed to test the hypothesis that in solid pancreatic lesions (SPLs), diagnostic accuracy of EUS-FNB without ROSE was not inferior to that of EUS-FNB with ROSE. METHODS: A noninferiority study (noninferiority margin, 5%) was conducted at 14 centers in 8 countries. Patients with SPLs requiring tissue sampling were randomly assigned (1:1) to undergo EUS-FNB with or without ROSE using new-generation FNB needles. The touch-imprint cytology technique was used to perform ROSE. The primary endpoint was diagnostic accuracy, and secondary endpoints were safety, tissue core procurement, specimen quality, and sampling procedural time. RESULTS: Eight hundred patients were randomized over an 18-month period, and 771 were analyzed (385 with ROSE and 386 without). Comparable diagnostic accuracies were obtained in both arms (96.4% with ROSE and 97.4% without ROSE, P = .396). Noninferiority of EUS-FNB without ROSE was confirmed with an absolute risk difference of 1.0% (1-sided 90% confidence interval, -1.1% to 3.1%; noninferiority P < .001). Safety and sample quality of histologic specimens were similar in both groups. A significantly higher tissue core rate was obtained by EUS-FNB without ROSE (70.7% vs. 78.0%, P = .021), with a significantly shorter mean sampling procedural time (17.9 ± 8.8 vs 11.7 ± 6.0 minutes, P < .0001). CONCLUSIONS: EUS-FNB demonstrated high diagnostic accuracy in evaluating SPLs independently on execution of ROSE. When new-generation FNB needles are used, ROSE should not be routinely recommended. (ClinicalTrial.gov number NCT03322592.).

Dye-based chromoendoscopy for the detection of colorectal neoplasia: meta-analysis of randomized controlled trials.

BACKGROUND AND AIMS: Dye-based chromoendoscopy (DBC) could be effective in increasing the adenoma detection rate (ADR) in patients undergoing colonoscopy, but the technique is time-consuming and its uptake is limited. We aimed to assess the effect of DBC on ADR based on available randomized controlled trials (RCTs). METHODS: Four databases were searched up to April 2022 for RCTs comparing DBC with conventional colonoscopy (CC) in terms of ADR, advanced ADR, and sessile serrated adenoma detection rate as well as the mean adenomas per patient and non-neoplastic lesions. Relative risk (RR) for dichotomous outcomes and mean difference (MD) for continuous outcomes were calculated using random-effect models. The I2 test was used for quantifying heterogeneity. Risk of bias was evaluated with the Cochrane tool. RESULTS: Overall, 10 RCTs (5334 patients) were included. Indication for colonoscopy was screening or surveillance (3 studies) and mixed (7 studies). Pooled ADR was higher in the DBC group versus the CC group (95% CI, 48.1% [41.4%-54.8%] vs 39.3% [33.5%-46.4%]; RR, 1.20 [1.11-1.29]), with low heterogeneity (I2 = 29%). This effect was consistent for advanced ADR (RR, 1.21 [1.03-1.42]; I2 = .0%), sessile serrated adenomas (6.1% vs 3.5%; RR, 1.68 [1.15-2.47]; I2 = 9.8%), and mean adenomas per patient (MD, .24 [.17-.31]) overall and in the right-sided colon (MD, .28 [.14-.43]). A subgroup analysis considering only trials using high-definition white-light endoscopy reduced the heterogeneity while still showing a significant increase in adenoma detection with DBC: 51.6% (95% confidence interval [CI], 47.1%-56.1%) and 59.1% (95% CI, 54.7-63.3%), RR = 1.14 (95% CI, 1.06-1.23), P = .0004, I2 = .0%, P = .50. CONCLUSIONS: Meta-analysis of RCTs showed that DBC increases key quality parameters in colonoscopy, supporting its use in everyday clinical practice.

Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia.

BACKGROUND: Use of artificial intelligence may increase detection of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe) and reduce pathology costs by improving optical diagnosis (CADx). METHODS: A multicenter library of ≥ 200 000 images from 1572 polyps was used to train a combined CADe/CADx system. System testing was performed on two independent image sets (CADe: 446 with polyps, 234 without; CADx: 267) from 234 polyps, which were also evaluated by six endoscopists (three experts, three non-experts). RESULTS: CADe showed sensitivity, specificity, and accuracy of 92.9 %, 90.6 %, and 91.7 %, respectively. Experts showed significantly higher accuracy and specificity, and similar sensitivity, while non-experts + CADe showed comparable sensitivity but lower specificity and accuracy than CADe and experts. CADx showed sensitivity, specificity, and accuracy of 85.0 %, 79.4 %, and 83.6 %, respectively. Experts showed comparable performance, whereas non-experts + CADx showed comparable accuracy but lower specificity than CADx and experts. CONCLUSIONS: The high accuracy shown by CADe and CADx was similar to that of experts, supporting further evaluation in a clinical setting. When using CAD, non-experts achieved a similar performance to experts, with suboptimal specificity.

Efficacy of a computer-aided detection system in a fecal immunochemical test-based organized colorectal cancer screening program: a randomized controlled trial (AIFIT study).

BACKGROUND: Computer-aided detection (CADe) increases adenoma detection in primary screening colonoscopy. The potential benefit of CADe in a fecal immunochemical test (FIT)-based colorectal cancer (CRC) screening program is unknown. This study assessed whether use of CADe increases the adenoma detection rate (ADR) in a FIT-based CRC screening program. METHODS: In a multicenter, randomized trial, FIT-positive individuals aged 50-74 years undergoing colonoscopy, were randomized (1:1) to receive high definition white-light (HDWL) colonoscopy, with or without a real-time deep-learning CADe by endoscopists with baseline ADR > 25 %. The primary outcome was ADR. Secondary outcomes were mean number of adenomas per colonoscopy (APC) and advanced adenoma detection rate (advanced-ADR). Subgroup analysis according to baseline endoscopists' ADR (≤ 40 %, 41 %-45 %, ≥ 46 %) was also performed. RESULTS: 800 individuals (median age 61.0 years [interquartile range 55-67]; 409 men) were included: 405 underwent CADe-assisted colonoscopy and 395 underwent HDWL colonoscopy alone. ADR and APC were significantly higher in the CADe group than in the HDWL arm: ADR 53.6 % (95 %CI 48.6 %-58.5 %) vs. 45.3 % (95 %CI 40.3 %-50.45 %; RR 1.18; 95 %CI 1.03-1.36); APC 1.13 (SD 1.54) vs. 0.90 (SD 1.32; P  = 0.03). No significant difference in advanced-ADR was found (18.5 % [95 %CI 14.8 %-22.6 %] vs. 15.9 % [95 %CI 12.5 %-19.9 %], respectively). An increase in ADR was observed in all endoscopist groups regardless of baseline ADR. CONCLUSIONS: Incorporating CADe significantly increased ADR and APC in the framework of a FIT-based CRC screening program. The impact of CADe appeared to be consistent regardless of endoscopist baseline ADR.

The endoscopic ultrasound features of pancreatic fluid collections and their impact on therapeutic decisions: an interobserver agreement study.

BACKGROUND: A validated classification of endoscopic ultrasound (EUS) morphological characteristics and consequent therapeutic intervention(s) in pancreatic and peripancreatic fluid collections (PFCs) is lacking. We performed an interobserver agreement study among expert endosonographers assessing EUS-related PFC features and the therapeutic approaches used. METHODS: 50 EUS videos of PFCs were independently reviewed by 12 experts and evaluated for PFC type, percentage solid component, presence of infection, recognition of and communication with the main pancreatic duct (MPD), stent choice for drainage, and direct endoscopic necrosectomy (DEN) performance and timing. The Gwet's AC1 coefficient was used to assess interobserver agreement. RESULTS: A moderate agreement was found for lesion type (AC1, 0.59), presence of infection (AC1, 0.41), and need for DEN (AC1, 0.50), while fair or poor agreements were stated for percentage solid component (AC1, 0.15) and MPD recognition (AC1, 0.31). Substantial agreement was rated for ability to assess PFC-MPD communication (AC1, 0.69), decision between placing a plastic versus lumen-apposing metal stent (AC1, 0.62), and timing of DEN (AC1, 0.75). CONCLUSIONS: Interobserver agreement between expert endosonographers regarding morphological features of PFCs appeared suboptimal, while decisions on therapeutic approaches seemed more homogeneous. Studies to achieve standardization of the diagnostic endosonographic criteria and therapeutic approaches to PFCs are warranted.

Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial.

BACKGROUND & AIMS: 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. METHODS: 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. RESULTS: 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). CONCLUSIONS: 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.

Prophylactic Clipping After Colorectal Endoscopic Resection Prevents Bleeding of Large, Proximal Polyps: Meta-analysis of Randomized Trials.

BACKGROUND & AIMS: The benefits of prophylactic clipping to prevent bleeding after polypectomy are unclear. We conducted an updated meta-analysis of randomized trials to assess the efficacy of clipping in preventing bleeding after polypectomy, overall and according to polyp size and location. METHODS: We searched the MEDLINE/PubMed, Embase, and Scopus databases for randomized trials that compared the effects of clipping vs not clipping to prevent bleeding after polypectomy. We performed a random-effects meta-analysis to generate pooled relative risks (RRs) with 95% CIs. Multilevel random-effects metaregression analysis was used to combine data on bleeding after polypectomy and estimate associations between rates of bleeding and polyp characteristics. RESULTS: We analyzed data from 9 trials, comprising 71897 colorectal lesions (22.5% 20 mm or larger; 49.2% with proximal location). Clipping, compared with no clipping, did not significantly reduce the overall risk of postpolypectomy bleeding (2.2% with clipping vs 3.3% with no clipping; RR, 0.69; 95% confidence interval [CI], 0.45-1.08; P = .072). Clipping significantly reduced risk of bleeding after removal of polyps that were 20 mm or larger (4.3% had bleeding after clipping vs 7.6% had bleeding with no clipping; RR, 0.51; 95% CI, 0.33-0.78; P = .020) or that were in a proximal location (3.0% had bleeding after clipping vs 6.2% had bleeding with no clipping; RR, 0.53; 95% CI, 0.35-0.81; P < .001). In multilevel metaregression analysis that adjusted for polyp size and location, prophylactic clipping was significantly associated with reduced risk of bleeding after removal of large proximal polyps (RR, 0.37; 95% CI, 0.22-0.61; P = .021) but not small proximal lesions (RR, 0.88; 95% CI, 0.48-1.62; P = .581). CONCLUSIONS: In a meta-analysis of randomized trials, we found that routine use of prophylactic clipping does not reduce risk of postpolypectomy bleeding overall. However, clipping appeared to reduce bleeding after removal of large (more than 20 mm) proximal lesions.

Novel 1-L polyethylene glycol + ascorbate versus high-volume polyethylene glycol regimen for colonoscopy cleansing: a multicenter, randomized, phase IV study.

BACKGROUND AND AIMS: Adequate bowel cleansing is critical to ensure quality and safety of a colonoscopy. A novel 1-L polyethylene glycol plus ascorbate (1L-PEG+ASC) regimen was previously validated against low-volume regimens but was never compared with high-volume regimens. METHODS: In a phase IV study, patients undergoing colonoscopy were randomized 1:1 to receive split-dose 1L PEG+ASC or a split-dose 4-L PEG-based regimen (4L-PEG) in 5 Italian centers. Preparation was assessed with the Boston Bowel Preparation Scale (BBPS) by local endoscopists and centralized reading, both blinded to the randomization arm. The primary endpoint was noninferiority of 1L-PEG+ASC in colon cleansing. Secondary endpoints were superiority of 1L-PEG+ASC, patient compliance, segmental colon cleansing, adenoma detection rate, tolerability, and safety. RESULTS: Three hundred eighty-eight patients (median age, 59.8 years) were randomized between January 2019 and October 2019: 195 to 1L-PEG+ASC and 193 to 4L-PEG. Noninferiority of 1L-PEG+ASC was demonstrated for cleansing in both the entire colon (BBPS ≥ 6: 97.9% vs 93%; relative risk [RR], 1.03; 95% confidence interval [CI], 1.001-1.04; P superiority = .027) and in the right-sided colon segment (98.4% vs 96.0%; RR, 1.02; 95% CI, .99-1.02; P noninferiority = .013). Compliance was higher with 1L-PEG+ASC than with 4L-PEG (178/192 [92.7%] vs 154/190 patients [81.1%]; RR, 1.10; 95% CI, 1.05-1.12), whereas no difference was found regarding safety (moderate/severe side effects: 20.8% vs 25.8%; P = .253). No difference in adenoma detection rate (38.8% vs 43.0%) was found. CONCLUSIONS: One-liter PEG+ASC showed noninferiority compared with 4L-PEG in achieving adequate colon cleansing and provided a higher patient compliance. No differences in tolerability and safety were detected. (Clinical trial registration number: NCT03742232.).

PPV and Detection Rate of mt-sDNA Testing, FIT, and CT Colonography for Advanced Neoplasia: A Hierarchic Bayesian Meta-Analysis of the Noninvasive Colorectal Screening Tests.

BACKGROUND. Noninvasive tests for colorectal cancer (CRC) screening and prevention limit the need for invasive colonoscopy to follow up positive test results. However, the relative performance characteristics of available noninvasive tests have not yet been adequately compared. OBJECTIVE. We performed a systematic review and meta-analysis to compare the diagnostic performance of the available noninvasive CRC screening tests, including multitarget stool DNA (mt-sDNA) testing, fecal immunochemical testing (FIT), and CT colonography (CTC), with an emphasis on comparison of PPV and detection rate (DR) for advanced neoplasia (AN; encompassing cases of advanced adenomas and CRC). EVIDENCE ACQUISITION. After systematic searches of MEDLINE and Google Scholar databases, 10 mt-sDNA, 27 CTC, and 88 FIT published screening studies involving 25,132, 33,493, and 2,355,958 asymptomatic adults, respectively, were included. Meta-analysis with hierarchic Bayesian modeling was conducted in accordance with Cochrane Collaboration and PRISMA guidelines to determine test positivity rates (TPRs) leading to optical colonoscopy, as well as PPVs and DRs for both AN and CRC. Different positivity thresholds were considered for FIT and CTC. EVIDENCE SYNTHESIS. Point estimates (with 95% credible intervals) from pooled Bayesian meta-analysis combining all thresholds for FIT and stratifying CTC results by a polyp size threshold of 6 mm or larger (CTC6) and 10 mm or larger (CTC10) were calculated. TPR was 13.5% (10.9-16.6%) for mt-sDNA testing, 6.4% (5.8-7.2%) for FIT, 13.4% (11.4-15.6%) for CTC6, and 6.6% (5.2-7.7%) for CTC10. AN PPV was 26.9% (95% credible interval, 21.8-33.2%) for mt-sDNA testing, 31.8% (29.3-34.5%) for FIT, 34.4% (27.2-41.0%) for CTC6, and 61.0% (54.0-70.0%) for CTC10. CRC PPV was 2.4% (1.5-3.9%) for mt-sDNA testing, 4.9% (4.3-5.3%) for FIT, 3.5% (2.5-4.8%) for CTC6, and 6.0% (4.3-8.0%) for CTC10. The DR for AN was 3.4% (95% credible interval, 2.5-4.8%) for mt-SDNA, 2.0% (1.8-2.3%) for FIT, 4.8% (4.0-6.5%) for CTC6, and 4.0% (3.0-4.6%) for CTC10. When FIT is restricted to a lower threshold (< 10 µg Hb/g feces), its performance profile is similar to that of mt-sDNA testing, although available data are limited. AN PPV odds ratios (relative to CTC10 as the reference) were 0.24 (95% credible interval, 0.17-0.33) for mt-sDNA testing, 0.30 (0.24-0.45) for FIT, and 0.33 (0.25-0.47) for CTC6. CONCLUSION. Among noninvasive CRC screening tests, CTC with a polyp size threshold of 10 mm or larger most effectively targets AN, preserving detection while also decreasing unnecessary colonoscopies compared with mt-sDNA testing and FIT. CLINICAL IMPACT. CTC performed with a polyp size threshold for colonoscopy referral set at 10 mm or larger represents the most effective and efficient noninvasive screening test for CRC prevention and detection.

New and Recurrent Colorectal Cancers After Resection: a Systematic Review and Meta-analysis of Endoscopic Surveillance Studies.

BACKGROUND & AIMS: Outcomes of endoscopic surveillance after surgery for colorectal cancer (CRC) vary with the incidence and timing of CRC detection at anastomoses or non-anastomoses in the colorectum. We performed a systematic review and meta-analysis to evaluate the incidence of CRCs identified during surveillance colonoscopies of patients who have already undergone surgery for this cancer. METHODS: We searched PubMed, EMBASE, SCOPUS, and the Cochrane Central Register of Clinical Trials through January 1, 2018 to identify studies investigating rates of CRCs at anastomoses or other locations in the colorectum after curative surgery for primary CRC. We collected data from published randomized controlled, prospective, and retrospective cohort studies. Data were analyzed by multivariate meta-analytic models. RESULTS: From 2373 citations, we selected 27 studies with data on 15,803 index CRCs for analysis (89% of patients with stage I-III CRC). Overall, 296 CRCs at non-anastomotic locations were reported over time periods of more than 16 years (cumulative incidence, 2.2% of CRCs; 95% confidence interval [CI], 1.8%-2.9%). The risk of CRC at a non-anastomotic location was significantly reduced more than 36 months after resection compared with before this time point (odds ratio for non-anastomotic CRCs at 36-48 months vs 6-12 months after surgery, 0.61; 95% CI, 0.37-0.98; P = .031); 53.7% of all non-anastomotic CRCs were detected within 36 months of surgery. One hundred and fifty-eight CRCs were detected at anastomoses (cumulative incidence of 2.7%; 95% CI, 1.9%-3.9%). The risk of CRCs at anastomoses was significantly lower 24 months after resection than before (odds ratio for CRCs at anastomoses at 25-36 months after surgery vs 6-12 months, 0.56; 95% CI, 0.32-0.98; P = .036); 90.8% of all CRCs at anastomoses were detected within 36 months of surgery. CONCLUSIONS: After surgery for CRC, the highest risk of CRCs at anastomoses and at other locations in the colorectum is highest during 36 months after surgery-risk decreases thereafter. Patients who have undergone CRC resection should be evaluated by colonoscopy more closely during this time period. Longer intervals may be considered thereafter.

Computer-aided detection-assisted colonoscopy: classification and relevance of false positives.

BACKGROUND AND AIMS: 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. METHODS: 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. RESULTS: 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). CONCLUSIONS: 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.