Computerized analysis of abnormal asymmetry in digital chest radiographs: Evaluation of potential utility

The purpose of this study was to develop and test a computerized method for the fully automated analysis of abnormal asymmetry in digital posteroanter ior (PA) chest radiographs. An automated lung segmentation method was used to identify the aerated lung regions in 600 chest radiographs. Minimal a pr iori lung morphology information was required for this gray-level threshold ing-based segmentation. Consequently, segmentation was applicable to grossl y abnormal cases. The relative areas of segmented right and left lung regio ns in each image were compared with the corresponding area distributions of normal images to determine the presence of abnormal asymmetry. Computerize d diagnoses were compared with image ratings assigned by a radiologist. The ability of the automated method to distinguish normal from asymmetrically abnormal cases was evaluated by using receiver operating characteristic (RO C) analysis, which yielded an area under the ROC curve of 0.84. This automa ted method demonstrated promising performance in its ability to detect abno rmal asymmetry in PA chest images. We believe this method could play a role in a picture archiving and communications (PACS) environment to immediatel y identify abnormal cases and to function as one component of a multifacete d computer-aided diagnostic scheme. Copyright (C) 1999 by W.B. Saunders Com pany.