Deep principal dimension encoding for the classification of early neoplasia in Barrett's Esophagus with volumetric laser endomicroscopy. (March 2020)

• Record Type: Journal Article
• Authors: van der Putten, Joost; Struyvenberg, Maarten; de Groof, Jeroen; Scheeve, Thom; Curvers, Wouter; Schoon, Erik; Bergman, Jacques J.G.H.M.; de With, Peter H.N.; van der Sommen, Fons
• Is Part Of: Computerized medical imaging and graphics. Volume 80(2020)
• Publication Date: 2020-03
• Subjects: Deep learning -- Segmentation -- Classification -- Volumetric laser endomicroscopy; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2020.101701
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: First fully automatic algorithm for the classification of dysplasia in snapshots. Improved performance by exploiting the inherent characteristics of the data. Principal dimension encoding is generalizable and preserves interpretability. Evaluated on an independent in-vivo test set. Abstract: 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.