Background Computer-aided detection (CAD) systems might assist endoscopists in the recognition of Barrett's neoplasia. Aim To develop a CAD system using endoscopic images of Barrett's neoplasia. Methods White light endoscopy (WLE) overview images of 40 neoplastic Barrett's lesions and 20 non-dysplastic Barret's oesophagus (NDBO) patients were prospectively collected. Experts delineated all neoplastic images. The overlap area of at least four delineations was labelled as the ‘sweet spot’. The area with at least one delineation was labelled as the ‘soft spot’. The CAD system was trained on colour and texture features. Positive features were taken from the sweet spot and negative features from NDBO images. Performance was evaluated using leave-one-out cross-validation. Outcome parameters were diagnostic accuracy of the CAD system per image, and localization of the expert soft spot by CAD delineation (localization score) and its indication of preferred biopsy location (red-flag indication score). Results Accuracy, sensitivity and specificity for detection were 92, 95 and 85%, respectively. The system localized and red-flagged the soft spot in 100 and 90%, respectively. Conclusion This uniquely trained and validated CAD system detected and localized early Barrett's neoplasia on WLE images with high accuracy. This is an important step towards real-time automated detection of Barrett's neoplasia.

There has been a vast increase in GI literature focused on the use of machine learning in endoscopy. The relative novelty of this field poses a challenge for reviewers and readers of GI journals. To appreciate scientific quality and novelty of machine learning studies, understanding of the technical basis and commonly used techniques is required. Clinicians often lack this technical background, while machine learning experts may be unfamiliar with clinical relevance and implications for daily practice. Therefore, there is an increasing need for a multidisciplinary, international evaluation on how to perform high-quality machine learning research in endoscopy. This review aims to provide guidance for readers and reviewers of peer-reviewed GI journals to allow critical appraisal of the most relevant quality requirements of machine learning studies. The paper provides an overview of common trends and their potential pitfalls and proposes comprehensive quality requirements in six overarching themes: terminology, data, algorithm description, experimental setup, interpretation of results and machine learning in clinical practice.

No abstract

No abstract

Introduction Transanal total mesorectal excision (TaTME) has rapidly emerged as a novel approach for rectal cancer surgery. Safety profiles are still emerging and more comparative data is urgently needed. This study aimed to compare indications and short‐term outcomes of TaTME, open, laparoscopic, and robotic TME internationally. Methods A pre‐planned analysis of the European Society of Coloproctology (ESCP) 2017 audit was performed. Patients undergoing elective total mesorectal excision (TME) for malignancy between 1 January 2017 and 15 March 2017 by any operative approach were included. The primary outcome measure was anastomotic leak. Results Of 2579 included patients, 76.2% (1966/2579) underwent TME with restorative anastomosis of which 19.9% (312/1966) had a minimally invasive approach (laparoscopic or robotic) which included a transanal component (TaTME). Overall, 9.0% (175/1951, 15 missing outcome data) of patients suffered an anastomotic leak. On univariate analysis both laparoscopic TaTME (OR 1.61, 1.02–2.48, P = 0.04) and robotic TaTME (OR 3.05, 1.10–7.34, P = 0.02) were associated with a higher risk of anastomotic leak than non‐transanal laparoscopic TME. However this association was lost in the mixed‐effects model controlling for patient and disease factors (OR 1.23, 0.77–1.97, P = 0.39 and OR 2.11, 0.79–5.62, P = 0.14 respectively), whilst low rectal anastomosis (OR 2.72, 1.55–4.77, P < 0.001) and male gender (OR 2.29, 1.52–3.44, P < 0.001) remained strongly associated. The overall positive circumferential margin resection rate was 4.0%, which varied between operative approaches: laparoscopic 3.2%, transanal 3.8%, open 4.7%, robotic 1%. Conclusion This contemporaneous international snapshot shows that uptake of the TaTME approach is widespread and is associated with surgically and pathologically acceptable results.