Search

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.

Introduction Anastomotic leakage is the most important postoperative complication following colorectal anastomoses. Endoscopic techniques are newly implemented and are somewhat in between options that can be considered for the treatment of AL in selected cases. Aim Aim of this literature review is to present, analyze, and synthesize material from diverse sources to provide a comprehensive summary of the endoscopic procedures available for the treatment of fistula following LAR for rectal cancer. Materials and Methods A bibliographic search was carried out on Pubmed for articles published until 31th January 2021. Two hundred thirteen articles were screened and after a proper assessment thirty-four articles were left for the scopes of this narrative review. Results The most commonly applied endoscopic solutions are the transrectal vacuum-assisted closure (VAC), the Over-The-Scope clipping system (OTSC) and the OverStitch suturing system. They all seems to offer integrate solutions in the management of colorectal anastomotic leaks. Conclusion Early detection of anastomotic leak might increase the success rate of endoscopic techniques, reducing overall healing time and length of hospital stay. Endoscopic evaluation could be added as an adjunctive screening test to all those patients who are suspected of an early postoperative colorectal leak, in order to confirm the suspicion and to promptly start the endoscopic treatment.

Purpose. Bowel preparation for surveillance endoscopy following surgery can be impaired by suboptimal bowel function. Our study compares two groups of patients in order to evaluate the influence of colorectal resection on bowel preparation. Methods. From April 2010 to December 2011, 351 patients were enrolled in our retrospective study and divided into two homogeneous arms: resection group (RG) and control group. Surgical methods were classified as left hemicolectomy, right hemicolectomy, anterior rectal resection, and double colonic resection. Bowel cleansing was evaluated by nine skilled endoscopists using the Aronchick scale. Results. Among the 161 patients of the RG, surgery was as follows: 60 left hemicolectomies (37%), 62 right hemicolectomies (38%), and 33 anterior rectal resections (20%). Unsatisfactory bowel preparation was significantly higher in resected population (44% versus 12%; P value=0.000). No significant difference (38% versus 31%, P value=ns) was detected in the intermediate score, which represents a fair quality of bowel preparation. Conclusions. Our study highlights how patients with previous colonic resection are at high risk for a worse bowel preparation. Currently, the intestinal cleansing carried out by 4 L PEG based preparation does not seem to be sufficient to achieve the quality parameters required for the post-resection endoscopic monitoring.

The publisher regrets that in the published paper, the order of first name and last name for a number of authors in the author list was reversed. The correct order of names appears above. The publisher would like to apologise for any inconvenience caused.

begs some questions. Although the limitations of the lifting agent have been correctly identified by the authors, it would be useful to know the timing and details of the procedures used for preparation of blood, plasma, and serum. The quality of the agent used suggests that it behaves, in terms of viscosity and transparency, like a hematoma at the time of endoscopic resection. Thus, endoscopic visibility for detecting the mucosal layers may be affected by the lifting agent, especially when the amount of fluid used exceeds 1 4mL. Rightly, the authors emphasize that methylene or toluidine blue colorants can be used during submucosal resection without impairing visibility. However, they also have the advantage of highlighting the different wall layers according to different rates of absorption, and they are used in a strong concentration.As demonstrated by other studies