3 March 2017 Evaluation of image features and classification methods for Barrett's cancer detection using VLE imaging
Author Affiliations +
Abstract
Volumetric Laser Endomicroscopy (VLE) is a promising technique for the detection of early neoplasia in Barrett’s Esophagus (BE). VLE generates hundreds of high resolution, grayscale, cross-sectional images of the esophagus. However, at present, classifying these images is a time consuming and cumbersome effort performed by an expert using a clinical prediction model. This paper explores the feasibility of using computer vision techniques to accurately predict the presence of dysplastic tissue in VLE BE images. Our contribution is threefold. First, a benchmarking is performed for widely applied machine learning techniques and feature extraction methods. Second, three new features based on the clinical detection model are proposed, having superior classification accuracy and speed, compared to earlier work. Third, we evaluate automated parameter tuning by applying simple grid search and feature selection methods. The results are evaluated on a clinically validated dataset of 30 dysplastic and 30 non-dysplastic VLE images. Optimal classification accuracy is obtained by applying a support vector machine and using our modified Haralick features and optimal image cropping, obtaining an area under the receiver operating characteristic of 0.95 compared to the clinical prediction model at 0.81. Optimal execution time is achieved using a proposed mean and median feature, which is extracted at least factor 2.5 faster than alternative features with comparable performance.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sander Klomp, Fons van der Sommen, Anne-Fré Swager, Svitlana Zinger, Erik J. Schoon, Wouter L. Curvers, Jacques J. Bergman, Peter H. N. de With, "Evaluation of image features and classification methods for Barrett's cancer detection using VLE imaging", Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101340D (3 March 2017); doi: 10.1117/12.2253860; https://doi.org/10.1117/12.2253860
PROCEEDINGS
10 PAGES + PRESENTATION

SHARE
Back to Top