Search

Volumetric laser endomicroscopy (VLE) is a balloon-based technique, which provides a circumferential near-microscopic scan of the esophageal wall layers, and has potential to improve Barrett's neoplasia detection. Interpretation of VLE imagery in Barrett's esophagus (BE) however is time-consuming and complex, due to a large amount of visual information and numerous subtle gray-shaded VLE images. Computer-aided detection (CAD), analyzing multiple neighboring VLE frames, might improve BE neoplasia detection compared to automated single-frame analyses. This study is to evaluate feasibility of automatic data extraction followed by CAD using a multiframe approach for detection of BE neoplasia. Prospectively collected ex-vivo VLE images from 29 BE-patients with and without early neoplasia were retrospectively analyzed. Sixty histopathology-correlated regions of interest (30 nondysplastic vs. 30 neoplastic) were assessed using different CAD systems. Multiple neighboring VLE frames, corresponding to 1.25 millimeter proximal and distal to each region of interest, were evaluated. In total, 3060 VLE frames were analyzed via the CAD multiframe analysis. Multiframe analysis resulted in a significantly higher median AUC (median level = 0.91) compared to single-frame (median level = 0.83) with a median difference of 0.08 (95% CI, 0.06–0.10), P  < 0.001. A maximum AUC of 0.94 was reached when including 22 frames on each side using a multiframe approach. In total, 3060 VLE frames were automatically extracted and analyzed by CAD in 3.9 seconds. Multiframe VLE image analysis shows improved BE neoplasia detection compared to single-frame analysis. CAD with multiframe analysis allows for fast and accurate VLE interpretation, thereby showing feasibility of automatic full scan assessment in a real-time setting during endoscopy. [ABSTRACT FROM AUTHOR]

Background: Volumetric laser endomicroscopy (VLE) allows for near-microscopic imaging of the superficial esophageal wall and may improve detection of early neoplasia in Barrett's esophagus (BE). Interpretation of a 6-cm long, circumferential VLE "full scan" may however be challenging for endoscopists. We aimed to evaluate the accuracy of VLE experts in correctly diagnosing VLE full scans of early neoplasia and non-dysplastic BE (NDBE)., Methods: 29 VLE full scan videos (15 neoplastic and 14 NDBE) were randomly evaluated by 12 VLE experts using a web-based module. Experts were blinded to the endoscopic BE images and histology. The 15 neoplastic cases contained a subtle endoscopically visible lesion, which on endoscopic resection showed high grade dysplasia or cancer. NDBE cases had no visible lesions and an absence of dysplasia in all biopsies. VLE videos were first scored as "neoplastic" or "NDBE." If neoplastic, assessors located the area most suspicious for neoplasia. Primary outcome was the performance of VLE experts in differentiating between non-dysplastic and neoplastic full scan videos, calculated by accuracy, sensitivity, and specificity. Secondary outcomes included correct location of neoplasia, interobserver agreement, and level of confidence., Results: VLE experts correctly labelled 73 % (95 % confidence interval [CI] 67 % - 79 %) of neoplastic VLE videos. In 54 % (range 27 % - 66 %) both neoplastic diagnosis and lesion location were correct. NDBE videos were consistent with endoscopic biopsies in 52 % (95 %CI 46 % - 57 %). Interobserver agreement was fair (kappa 0.28). High level of confidence was associated with a higher rate of correct neoplastic diagnosis (81 %) and lesion location (73 %)., Conclusions: Identification of subtle neoplastic lesions in VLE full scans by experts was disappointing. Future studies should focus on improving methodologies for reviewing full scans, development of refined VLE criteria for neoplasia, and computer-aided diagnosis of VLE scans., Competing Interests: B.E. Bouma: NinePoint Medical (inventor on patents and consultant), E.K. Ganguly: Boston Scientific (consultant), V.J.A. Konda: Pentax (research grant), D.K. Pleskow: NinePoint Medical (consultant), Boston Scientific/Olympus/Fujifilm/ Medtronic/CSA (consultant), A. Sethi: Boston Scientific/Olympus/Fujifilm (consultant), M.S. Smith: NinePoint Medical (consultant), A.J. Trindade: NinePoint Medical (research support), Olympus/Pentax (consultant), M.B. Wallace: NinePoint Medical (research support), Fujifilm/Boston Scientific/Olympus/ Medtronic (research grants), K.K. Wang: NinePoint Medical (research support), G.J. Tearney: NinePoint Medical (consultant and royalties), Boston Scientific (research support), iLumen (research support), C.L. Leggett: NinePoint Medical (indirect research support), J.J. Bergman: NinePoint Medical (research support), Fujifilm (speaking fees)., (Thieme. All rights reserved.)

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., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY. Published by BMJ.)

Patients suffering from Barrett's Esophagus (BE) are at an increased risk of developing esophageal adenocarcinoma and early detection is crucial for a good prognosis. To aid the endoscopists with the early detection for this preliminary stage of esophageal cancer, this work concentrates on the development and extensive evaluation of a state-of-the-art computer-aided classification and localization algorithm for dysplastic lesions in BE. To this end, we have employed a large-scale endoscopic data set, consisting of 494,355 images, in combination with a novel semi-supervised learning algorithm to pretrain several instances of the proposed neural network architecture. Next, several Barrett-specific data sets that are increasingly closer to the target domain with significantly more data compared to other related work, were used in a multi-stage transfer learning strategy. Additionally, the algorithm was evaluated on two prospectively gathered external test sets and compared against 53 medical professionals. Finally, the model was also evaluated in a live setting without interfering with the current biopsy protocol. Results from the performed experiments show that the proposed model improves on the state-of-the-art on all measured metrics. More specifically, compared to the best performing state-of-the-art model, the specificity is improved by more than 20% points while simultaneously preserving high sensitivity and reducing the false positive rate substantially. Our algorithm yields similar scores on the localization metrics, where the intersection of all experts is correctly indicated in approximately 92% of the cases. Furthermore, the live pilot study shows great performance in a clinical setting with a patient level accuracy, sensitivity, and specificity of 90%. Finally, the proposed algorithm outperforms each individual medical expert by at least 5% and the average assessor by more than 10% over all assessor groups with respect to accuracy., (Copyright © 2020 The Authors. Published by Elsevier B.V. All rights reserved.)

Barrett cancer is a treatable disease when detected at an early stage. However, current screening protocols are often not effective at finding the disease early. Volumetric Laser Endomicroscopy (VLE) is a promising new imaging tool for finding dysplasia in Barrett's esophagus (BE) at an early stage, by acquiring cross-sectional images of the microscopic structure of BE up to 3-mm deep. However, interpretation of VLE scans is difficult for medical doctors due to both the size and subtlety of the gray-scale data. Therefore, algorithms that can accurately find cancerous regions are very valuable for the interpretation of VLE data. In this study, we propose a fully-automatic multi-step Computer-Aided Detection (CAD) algorithm that optimally leverages the effectiveness of deep learning strategies by encoding the principal dimension in VLE data. Additionally, we show that combining the encoded dimensions with conventional machine learning techniques further improves results while maintaining interpretability. Furthermore, we train and validate our algorithm on a new histopathologically validated set of in-vivo VLE snapshots. Additionally, an independent test set is used to assess the performance of the model. Finally, we compare the performance of our algorithm against previous state-of-the-art systems. With the encoded principal dimension, we obtain an Area Under the Curve (AUC) and F 1 score of 0.93 and 87.4% on the test set respectively. We show this is a significant improvement compared to the state-of-the-art of 0.89 and 83.1%, respectively, thereby demonstrating the effectiveness of our approach., (Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved.)