Abstract
It is desired to develop a computer‐aided detection system that automatically detects carotid artery calcifications（CACs）on dental panoramic radiographs（DPRs）. In our previous study, an automated method for the detection of CACs was proposed, in which the sensitivity of CAC detection was 90 % with 4.6 false positives（FPs）per image. We noticed that the regions of interest（ROIs）determined automatically as possible carotid artery regions by our previous scheme were relatively larger than those estimated by a dental radiologist. In this paper, we verified the necessity of an introduction of appropriate size and location of ROIs which are similar with those by the dental radiologist. We found that the sensitivity was maintained along with those appropriate ROIs, but the number of FPs per image was reduced to 0.9 using 100 DPRs. This result indicates that it is possible to reduce the number of FPs by accurately tailoring ROIs to individual cases.
