Search

Background: Endoscopic submucosal dissection (ESD) is a complex procedure, requiring enhanced technical skills. Translation into clinical practice of ESD training programs has not been documented. Our aim was to assess ESD training pathways of endoscopists participating in dedicated workshops and its clinical impact on ESD outcomes. Methods: Participants of live porcine models ESD workshops, from 2013 to 2019, were included. They were invited to complete a survey focusing on human ESD performance after training, prior skills/competencies, complete learning pathway, and clinical outcomes. Results: From 118 invited participants, 40 (34%) completed the questionnaire. Nineteen (47%) endoscopists performed human ESD after the workshop, predominantly male (89%). At the beginning of human ESD, endoscopists had a mean of 7.7 (standard deviation (SD) 4.1) years of endoscopic experience and were all performing endoscopic mucosal resection (and emergency endoscopy. Before ESD practice, 100% of the participants were trained with live animal models and 68% with ex vivo models. The majority started clinical ESD in the lower third of the stomach or rectum (90%), with lesions ≤30 mm (89%). Each endoscopist performed a median of 19 (interquartile range 8–32) cumulative ESDs, over a mean of 3.9 (SD 2.0) years. Total en bloc resection rate was 92%, R0 resection rate 88%, and curative resection rate 86%, whereas adverse events remained <10%. Endoscopists with >10 human ESD procedures achieve clinical competence thresholds. Conclusions: Participants of ESD workshops are adequately skilled prior to clinical ESD, complying with recommendations for training and properly implementing the technique. Transfer to clinical practice, of prior ESD skills obtained in hands-on training courses, was documented. Structured training programs achieve clinical outcomes exceeding established standards, namely in the very initial clinical phase. [ABSTRACT FROM AUTHOR]

Purpose: Wireless Capsule Endoscopy (WCE) is a minimally invasive diagnosis tool for lesion detection in the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the significant amount of acquired data leads to difficulties in the diagnosis by the physicians; which can be eased with computer assistance. This paper addresses a method for the automatic detection of tumors in WCE by using a two‐step based procedure: region of interest selection and classification. Methods: The first step aims to separate abnormal from normal tissue by using automatic segmentation based on a Gaussian Mixture Model (GMM). A modified version of the Anderson method for convergence acceleration of the expectation–maximization (EM) algorithm is proposed. The proposed features for both segmentation and classification are based on the CIELab color space, as a way of bypassing lightness variations, where the L component is discarded. Tissue variability among subjects, light inhomogeneities and even intensity differences among different devices can be overcome by using simultaneously features from both regions. In the second step, an ensemble system with partition of the training data with a new training scheme is proposed. At this stage, the gating network is trained after the experts have been trained decoupling the joint maximization of both modules. The partition module is also used at the test step, leading the incoming data to the most likely expert allowing incremental adaptation by preserving data diversity. Results: This algorithm outperforms others based on texture features selected from Wavelets and Curvelets transforms, classified by a regular support vector machine (SVM) in more than 5%. Conclusions: This work shows that simpler features can outperform more elaborate ones if appropriately designed. In the current case, luminance was discarded to cope with saturated tissue, facilitating the color perception. Ensemble systems remain an open research field. In the current case, changes in both topology and training strategy have led to significant performance improvements. A system with this level of performance can be used in current clinical practice. [ABSTRACT FROM AUTHOR]