An Image Processing Tool for Efficient Feature Extraction in Computer-Aided Detection Systems

In this paper, we present an image processing tool that supports efficient image feature extraction and pre-processing developed in the context of a computer-aided detection (CAD) system for lung cancer nodule detection from CT images. We outline the main functionalities of the tool, which implements a number of novel methods for handling image pre-processing and feature extraction tasks. In particular, we describe an efficient way to compute the run-length feature, a photometric feature describing the texture of an image.