Development and Validation of an Automatic Image-Recognition Endoscopic Report Generation System: A Multicenter Study.

INTRODUCTION: Conventional gastrointestinal (GI) endoscopy reports written by physicians are time consuming and might have obvious heterogeneity or omissions, impairing the efficiency and multicenter consultation potential. We aimed to develop and validate an image recognition-based structured report generation system (ISRGS) through a multicenter database and to assess its diagnostic performance. METHODS: First, we developed and evaluated an ISRGS combining real-time video capture, site identification, lesion detection, subcharacteristics analysis, and structured report generation. White light and chromoendoscopy images from patients with GI lesions were eligible for study inclusion. A total of 46,987 images from 9 tertiary hospitals were used to train, validate, and multicenter test (6:2:2). Moreover, 5,699 images were prospectively enrolled from Qilu Hospital of Shandong University to further assess the system in a prospective test set. The primary outcome was the diagnosis performance of GI lesions in multicenter and prospective tests. RESULTS: The overall accuracy in identifying early esophageal cancer, early gastric cancer, early colorectal cancer, esophageal varices, reflux esophagitis, Barrett's esophagus, chronic atrophic gastritis, gastric ulcer, colorectal polyp, and ulcerative colitis was 0.8841 (95% confidence interval, 0.8775-0.8904) and 0.8965 (0.8883-0.9041) in multicenter and prospective tests, respectively. The accuracy of cecum and upper GI site identification were 0.9978 (0.9969-0.9984) and 0.8513 (0.8399-0.8620), respectively. The accuracy of staining discrimination was 0.9489 (0.9396-0.9568). The relative error of size measurement was 4.04% (range 0.75%-7.39%). DISCUSSION: ISRGS is a reliable computer-aided endoscopic report generation system that might assist endoscopists working at various hospital levels to generate standardized and accurate endoscopy reports (http://links.lww.com/CTG/A485).

Second-look endoscopy is not associated with better clinical outcomes after gastric endoscopic submucosal dissection: a prospective, randomized, clinical trial analyzed on an as-treated basis.

BACKGROUND: The efficacy of routine second-look endoscopy (SLE) to detect or prevent bleeding after gastric endoscopic submucosal dissection (ESD) has not yet been validated. OBJECTIVE: The aim of this study was to determine whether SLE affects clinical outcomes including bleeding and morbidity after gastric ESD. DESIGN: A prospective, randomized, controlled study with consecutive data analyzed on an as-treated basis. SETTING: A single, tertiary-care referral center. PATIENTS: A total of 182 patients. INTERVENTION: Gastric ESD and SLE. MAIN OUTCOME MEASUREMENTS: Incidence of and risk factors related to bleeding after ESD and outcomes by univariate or multivariate analysis. RESULTS: Among 182 patients enrolled, 74 and 81 patients were assigned to the SLE and no-SLE groups, respectively. Two groups were observed closely for 4 weeks. Bleeding occurred after ESD in 21 patients (13.5%). Hemoglobin loss (≥2.0 g/dL) was observed in 20 patients, and melena developed in 1 patient after ESD. However, only 1 patient needed a transfusion. Twelve patients (16.2%) in the SLE group and 9 in the no-SLE group (11.1%) experienced bleeding after ESD. The frequency of bleeding after ESD was not significantly different between the 2 groups (P = .66). There were no risk factors related to bleeding after ESD. LIMITATIONS: Single-center analysis. CONCLUSION: SLE is not routinely necessary because it does not affect clinical outcomes, including bleeding and morbidity after ESD. ( CLINICAL TRIAL REGISTRATION NUMBER: KCT0000146.).