<title>Computer-assisted diagnostic (CAD) methods for x-ray imaging and teleradiology</title>

Abstract

The development and evaluation of a new class of algorithms for computer assisted diagnostic (CAD) methods for segmentation and detection of masses in digitized mammograms is reported. Both non-adaptive and adaptive methods are reported that employ two key novel CAD modules, specifically tailored for digital mammography, namely: (a) a multiorientation directional wavelet transform for removal of directional features and for the direct detection of speculations for spiculated lesions, and (b) a multiresolution wavelet transform for image enhancement to improve the segmentation of suspicious areas. The aim of the work is to provide a brief overview of both the non-adaptive and adaptive methods and comparison of their performance using computer ROC curves. An image data base containing regions of interest (ROI), enclosing all mass types and normal tissues, was used for the relative comparison of the performance, where electronic ground truth was established. The result confirm the importance of using adaptive CAD methods that should potentially allow a more generalized and robust application for larger image data bases, images generated from different sensors, or direct X-ray detection, as required for clinical trials and teleradiology applications.