3 March 2017 Computer assisted optical biopsy for colorectal polyps
Author Affiliations +
Abstract
We propose a method for computer-assisted optical biopsy for colorectal polyps, with the final goal of assisting the medical expert during the colonoscopy. In particular, we target the problem of automatic classification of polyp images in two classes: adenomatous vs non-adenoma. Our approach is based on recent advancements in convolutional neural networks (CNN) for image representation. In the paper, we describe and compare four different methodologies to address the binary classification task: a baseline with classical features and a Random Forest classifier, two methods based on features obtained from a pre-trained network, and finally, the end-to-end training of a CNN. With the pre-trained network, we show the feasibility of transferring a feature extraction mechanism trained on millions of natural images, to the task of classifying adenomatous polyps. We then demonstrate further performance improvements when training the CNN for our specific classification task. In our study, 776 polyp images were acquired and histologically analyzed after polyp resection. We report a performance increase of the CNN-based approaches with respect to both, the conventional engineered features and to a state-of-the-art method based on videos and 3D shape features.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fernando J. Navarro-Avila, Fernando J. Navarro-Avila, Yadira Saint-Hill-Febles, Yadira Saint-Hill-Febles, Janis Renner, Janis Renner, Peter Klare, Peter Klare, Stefan von Delius, Stefan von Delius, Nassir Navab, Nassir Navab, Diana Mateus, Diana Mateus, } "Computer assisted optical biopsy for colorectal polyps", Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101340J (3 March 2017); doi: 10.1117/12.2254595; https://doi.org/10.1117/12.2254595
PROCEEDINGS
7 PAGES + PRESENTATION

SHARE
Back to Top