Abstract:
The latest technological changes In diagnostic radiology are fast replacing the conventional cathode ray tube (CRT) displays with liquid crystal displays (LCDs). Even though LCDs offer considerable advantages over conventional CRTs, the pixelated pattern of LCDs can obscure the micro-calcifications. It is thus important to understand and evaluate them. Our evaluation strategy is based on computer-aided diagnostics using physics-based enhancement and deformable models. This evaluation system combines both lesion segmentation and quantification. Hence, it is an integrated approach. The Full Field Digital Mammography (FFDM) 50 μm, X-ray images were acquired using Fischer's Full Field Digital Mammography and Ultrasound System (FFDMUS). These images were then enhanced to improve the contrast resolution using physics based strategy. The enhanced lesion images were displayed on LCD and CRT displays. We then segmented the lesions using gradient vector flow (GVF)-based deformable model and quantify them using the Hausdorff distance measure (HDM) and polyline distance metric (PDM). Our results using the PDM method on FFDMUS X-ray images show that lesions quantified from LCD images show a 12.5% improvement over lesions quantified from CRT images. A similar behavior was observed using HDM method where the result was 8.7% better on LCDs compared to CRTs. Hence we conclude that use of LCD displays for mammography applications with image enhancement techniques will have a better diagnostic accuracy when compared to the CRT displays. © Copyright 2005 Society for Information Display.
Duke University * Arts & Sciences * Physics * Faculty * Staff * Grad * Researchers * Reload * Login
Copyright (c) 2001-2002 by Duke University Physics.