A CAD System for Real-Time Characterization of Neoplasia in Barrett's Esophagus NBI Videos

Barrett's Esophagus (BE) is a well-known precursor for Esophageal Adenocarcinoma (EAC). Endoscopic detection and diagnosis of early BE neoplasia is performed in two steps: primary detection of a suspected lesion in overview and a targeted and detailed inspection of the specific area using Narrow-Band Imaging (NBI). Despite the improved visualization of tissue by NBI and clinical classification systems, endoscopists have difficulties with correct characterization of the imagery. Computer-aided Diagnosis (CADx) may assist endoscopists in the classification of abnormalities in NBI imagery. We propose an endoscopy-driven pre-trained deep learning-based CADx, for the characterization of NBI imagery of BE. We evaluate the performance of the algorithm on images as well as on videos, for which we use several post-hoc and real-time video analysis methods. The proposed real-time methods outperform the post-hoc methods on average by 1.2% and 2.3% for accuracy and specificity, respectively. The obtained results show promising methods towards real-time endoscopic video analysis and identifies steps for further development.