1. Improved Barrett's neoplasia detection using computer-assisted multiframe analysis of volumetric laser endomicroscopy
- Author
-
M R Struyvenberg, F van der Sommen, A F Swager, A J de Groof, A Rikos, E J Schoon, J J Bergman, P H N de With, W L Curvers, Gastroenterology and Hepatology, Graduate School, AGEM - Re-generation and cancer of the digestive system, CCA - Imaging and biomarkers, Center for Care & Cure Technology Eindhoven, Video Coding & Architectures, Electrical Engineering, and EAISI Health
- Subjects
Adult ,Male ,Barrett's neoplasia ,Esophageal Neoplasms ,CAD ,volumetric laser endomicroscopy ,Adenocarcinoma ,Barrett Esophagus ,03 medical and health sciences ,0302 clinical medicine ,Region of interest ,Image Interpretation, Computer-Assisted ,Endomicroscopy ,Humans ,Medicine ,Early Detection of Cancer ,computer-aided detection ,Aged ,Retrospective Studies ,Microscopy ,Principal Component Analysis ,Esophageal wall ,business.industry ,Gastroenterology ,General Medicine ,Middle Aged ,Cad system ,Computer aided detection ,Data extraction ,Area Under Curve ,Case-Control Studies ,030220 oncology & carcinogenesis ,Feasibility Studies ,Female ,030211 gastroenterology & hepatology ,Esophagoscopy ,Nuclear medicine ,business ,Precancerous Conditions ,Algorithms - Abstract
SUMMARYVolumetric 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
- Published
- 2020
- Full Text
- View/download PDF