A Two-Stage Lesion Recognition System for Diagnostic Support in Colon NBI Endoscopy

In this paper, we propose a two-stage Computer-Aided Diagnosis (CAD) system for lesion recognition using detecting and classifying method based on deep learning architecture. The proposed CAD system can presents quantitative inference results from images token by colorectal Narrow Band Imaging (NBI) endoscopy to clinical doctors, which aims to reduce the variation and burden of diagnoses due to the experience of diagnosing doctors. As a result, for our test dataset, the current accuracy has reached 67% for magnified images.