A coronary calcification diagnosis system based on helical CT images

In this paper, we describe a computer assisted diagnostic algorithm for cor onary calcifications based on helical X-ray CT images which is used in mass screening process for lung cancer diagnosis. Our diagnostic algorithm cons ists of four processes: First, we choose the heart slices from the CT image s which were taken at the mass screening. We classify the heart slices into three sections which have different coronary geometries, using the informa tion of the heart shape, trachea, CT values in the heart region, and the bo ne. Second, we extract the heart region in each slice, using the informatio n of the lung shape and the body of vertebra. Third, we detect the candidat e regions of the coronary calcifications using an edge filter and threshold ing pixel values. Finally, to increase the effectiveness of the diagnosis, we exclude the artifact regions included in the candidate regions by using the diagnostic rule based on the neural network. We applied this algorithm to helical CT images of 462 patients screened for lung cancer. The results generated by this system were compared with a physician's diagnosis. This s ystem could detect 213 of 214 regions which were diagnosed as coronary calc ifications or probably coronary calcifications by a physician. There was on ly one false negative case. The false positive ratio was 0.30 per patient.