コンピュータ支援診断とPACSへの応用

概要

論文の詳細を見る
We are developing a scheme of computer-aided diagnosis (CAD) which refers to a diagnosis made by a radiologist who takes into consideration the results of an automated computer analysis of radiographic images. The general approach is to alert the radiologist by indicating potential lesion sites and/or by providing objective measurements of normal and abnormal patterns. In this study, we demonstrated the current results fo our computerized automatic analysis for (1) the identification of lung nodules and pneumothoraces, and the assessment of cardiomegaly and interstitial disease in chest radiography; (2) the identification of clustered microcalcifications and masses in mammography, and (3)the assessment of stenotic regions in angiography. In addition, the basic scheme of lung texture analysis for assessment of interstitial diseases was presented, and the effects of digital parameters in digitization of chest images on the results of the lung texture analysis was discussed. Preliminary results obtained with CAD from various radiographic examinations are very encouraging. However, CAD is still at an early stage of its development. It will be necessary to increase further understanding of image features of normal and abnormal patterns, and to establish large databases. We believe that CAD will become a reality in the near future.
Japan Society of Medical Physicsの論文