Search

Defining the next steps for artificial intelligence in colonoscopy: Referring to Ahmad OF et al. p. 893-901 AI in colonoscopy is at an early stage of this process, but there is already evidence that computer-aided polyp detection (CADe) improves adenoma detection rate (ADR) [4], a surrogate end point for colorectal cancer mortality [2]. Artificial intelligence (AI) in health care is rapidly advancing, driven by new developments in artificial or convolutional neural networks, which have allowed for an explosion in discriminative prediction complexity [1]. [Extracted from the article]

Background: Sessile serrated polyps (SSPs) are important precursors of colorectal carcinoma and interval cancer. Large SSPs (≥ 20 mm) outside the definition of serrated polyposis syndrome (SPS) have not been studied in comparison with SPS. We aimed to describe the characteristics of patients with large SSPs in this context.Methods: Patients with at least one SSP (≥ 20 mm) were eligible. Data from three consecutive colonoscopies were used to compare clinical and endoscopic characteristics in three patient groups: SPS, a solitary large SSP, and patients with at least two SSPs without fulfilling the criteria for SPS (oligo-SSP). Data on the diagnostic colonoscopy were collected retrospectively, whereas the remaining data was collected prospectively.Results: 67/146 patients (45.9 %) had SPS, 53/146 (36.3 %) had a solitary SSP, and 26/146 (17.8 %) were categorized as oligo-SSP. Personal (16.4 %, 9.4 %, and 11.5 %, respectively) and family (17.9 %, 17.0 %, and 23.1 %, respectively) history of colorectal carcinoma did not differ significantly between groups. Polyp burden was greater in SPS compared with solitary SSP but was not different from oligo-SSP (advanced adenomas: SPS 32.8 % vs. solitary SSP 9.4 % [P = 0.002] vs. oligo-SSP 34.6 % [P = 0.87]; ≥ 10 conventional adenomas: 11.9 % vs. 0 % [P = 0.01] vs. 3.8 % [P = 0.44], respectively). Dysplasia in large SSPs was frequent in all groups (41.1 % overall). SPS was recognized by referring endoscopists in only 9.0 % of cases.Conclusion: Patients with oligo-SSPs have similar synchronous polyp burden and clinical characteristics as patients with SPS and may require similar surveillance. Modification of the criteria for the diagnosis of SPS to include this group seems warranted. Patients with a solitary SSP have a lower risk of synchronous polyps, including advanced adenomas. Larger studies are warranted to determine whether these patients may return to standard surveillance following complete examination and clearance of the colon. [ABSTRACT FROM AUTHOR]

Large (≥20 mm) nonpedunculated colorectal polyps (LNPCPs) may have synchronous LNPCPs in up to 18% of cases. The nature of this relationship has not been investigated. We aimed to examine the relationship between individual LNPCP characteristics and synchronous colonic LNPCPs. Consecutive patients referred for resection of LNPCPs over 130 months until March 2022 were enrolled. Serrated lesions and mixed granularity LNPCPs were excluded from analysis. Patients with multiple LNPCPs resected were identified, and the largest was labelled as dominant. The primary outcome was the identification of individual lesion characteristics associated with the presence of synchronous LNPCPs. There were 3149 of 3381 patients (93.1%) who had a single LNPCP. In 232 (6.9%) a synchronous lesion was detected. Solitary lesions had a median size of 35 mm with a predominant Paris 0-IIa morphology (42.9%) and right colon location (59.5%). In patients with ≥2 LNPCPs, the dominant lesion had a median size of 40 mm, Paris 0-IIa (47.6%) morphology, and right colon location (65.9%). In this group, 35.8% of dominant LNPCPs were non-granular compared with 18.7% in the solitary LNPCP cohort. Non-granular (NG)-LNPCPs were more likely to demonstrate synchronous disease, with left colon NG-LNPCPs demonstrating greater risk (odds ratio, 4.78; 95% confidence interval, 2.95–7.73) than right colon NG-LNPCPs (odds ratio, 1.99; 95% confidence interval, 1.39–2.86). We found that 6.9% of LNPCPs have synchronous disease, with NG-LNPCPs demonstrating a greater than 4-fold increased risk. With post-colonoscopy interval cancers exceeding 5%, endoscopists must be cognizant of an individual's LNPCP phenotype when examining the colon at both index procedure and surveillance. ClinicalTrials.gov , NCT01368289; NCT02000141; NCT02198729. [ABSTRACT FROM AUTHOR]

Background and study aims: Endoscopic mucosal resection (EMR) of laterally spreading lesions (LSLs) involving the ileocecal valve (ICV) is technically demanding. Conventionally, these lesions are considered too challenging for endoscopic therapy and are primarily managed surgically. The aims of the study were to describe effectiveness, safety, and outcomes following EMR of LSLs at the ICV. Patients and methods: This was a single-center, prospective, observational, cohort study performed at an academic, tertiary referral center. Patients undergoing EMR for LSLs ≥20mm involving the ICV were recruited over a 5-year period. Standard or cap-assisted colonoscopy with injectand- resect EMR technique was performed with standardized post-EMR management. Procedural success, safety, and outcomes compared with non-ICV LSLs managed during the same period were analyzed. Results: A total of 53 patients with ICV LSLs were referred for EMR (median age 69 years; median lesion size 35.0 mm; 52.8% females). Six patients went directly to surgery because of an endoscopic diagnosis of malignancy (n=2) or technical failure of EMR (n=4). EMR achieved complete adenoma clearance in 44 out of 47 attempted (93.6 %). Surgery was ultimately avoided in 43/53 (81.1 %). Complications included bleeding in 6.4 %. There were no perforations or strictures. Early adenoma recurrence was detected in 7/40 patients (17.5 %), and 1/22 (4.5 %) had late recurrence. All were successfully managed endoscopically. Factors associated with failure of ICV EMR were ileal infiltration and involvement of both ICV lips. Conclusions: In the majority of cases, LSL involving the ICV can be effectively treated by EMR on an outpatient basis. In specialized centers, complications are infrequent, and>80% of patients ultimately avoid surgery. [ABSTRACT FROM AUTHOR]

The ability of optical evaluation to diagnose submucosal invasive cancer (SMIC) prior to endoscopic resection of large (≥20 mm) nonpedunculated colorectal polyps (LNPCPs) is critical to inform therapeutic decisions. Prior studies suggest that it is insufficiently accurate to detect SMIC. It is unknown whether lesion morphology influences optical evaluation performance. LNPCPs ≥20 mm referred for endoscopic resection within a prospective, multicenter, observational cohort were evaluated. Optical evaluation was performed prior to endoscopic resection with the optical prediction of SMIC based on established features (Kudo V pit pattern, depressed morphology, rigidity/fixation, ulceration). Optical evaluation performance outcomes were calculated. Outcomes were reported by dominant morphology: nodular (Paris 0–Is/0–IIa+Is) vs flat (Paris 0–IIa/0–IIb) morphology. From July 2013 to July 2019, 1583 LNPCPs (median size 35 [interquartile range, 25–50] mm; 855 flat, 728 nodular) were assessed. SMIC was identified in 146 (9.2%; 95% confidence interval [CI], 7.9%–10.8%). Overall sensitivity and specificity were 67.1% (95% CI, 59.2%–74.2%) and 95.1% (95% CI, 93.9%–96.1%), respectively. The overall SMIC miss rate was 3.0% (95% CI, 2.3%–4.0%). Significant differences in sensitivity (90.9% vs 52.7%), specificity (96.3% vs 93.7%), and SMIC miss rate (0.6% vs 5.9%) between flat and nodular LNPCPs were identified (all P <.027). Multiple logistic regression identified size ≥40 mm (odds ratio [OR], 2.0; 95% CI, 1.0–3.8), rectosigmoid location (OR, 2.0; 95% CI, 1.1–3.7), and nodular morphology (OR, 7.2; 95% CI, 2.8–18.9) as predictors of missed SMIC (all P <.039). Optical evaluation performance is dependent on lesion morphology. In the absence of features suggestive of SMIC, flat lesions can be presumed benign and be managed accordingly. [Display omitted] [ABSTRACT FROM AUTHOR]

Background & Aims: Wide-field endoscopic mucosal resection (WF-EMR) of large sessile colonic polyps is a safe and cost-effective outpatient treatment. Bleeding is the main complication. Few studies have examined risk factors for bleeding during the procedure (intraprocedural bleeding [IPB]) or after it (clinically significant post-endoscopic bleeding [CSPEB]). We investigated factors associated with IPB and CSPEB in a large prospective study. Methods: We analyzed data from WF-EMRs of sessile colorectal polyps ≥20 mm in size (mean size, 35.5 mm), which were performed on 1172 patients (mean age, 67.8 years) from June 2008–March 2013 at 7 tertiary hospitals as part of the Australian Colonic Endoscopic Resection Study. Data were collected on characteristics of patients and lesions, along with outcomes of procedures and clinical and histologic analyses. Independent predictors of IPB and CSPEB were identified by multiple logistic regression analysis. Results: Of the patients studied, 133 (11.3%) had IPB. Independent predictors included increasing lesion size (odds ratio, 1.24/10 mm; P < .001), Paris endoscopic classification of 0–IIa + Is (odds ratio, 2.12; P = .004), tubulovillous or villous histology (odds ratio, 1.84; P = .007), and study institutions that performed the procedure on fewer than 75 patients (odds ratio, 3.78; P < .001). All IPB was successfully controlled endoscopically. IPB prolonged procedures and was associated with early recurrence (relative risk, 1.68; P = .011). Seventy-three patients (6.2%) had CSPEB. On multivariable analysis, CSPEB was associated with proximal colon location (odds ratio, 3.72; P < .001), use of an electrosurgical current not controlled by a microprocessor (odds ratio, 2.03; P = .038), and IPB (odds ratio, 2.16; P = .016). Lesion size and comorbidities did not predict CSPEB. Conclusions: In a prospective study of patients undergoing WF-EMR of large sessile colonic polyps, IPB is associated with larger lesions, lesion histology, and Paris endoscopic classification of type 0–IIa + Is. IPB prolongs the duration of the procedure, is a marker for recurrence, and is associated with CSPEB. CSPEB occurs most frequently in the proximal colon and less when current is controlled by a microprocessor. [Copyright &y& Elsevier]