Detection of calcification region in dental panoramic radiographs considering local intensity distribution

This paper proposes an improvement of an automatic detection method for carotid artery calcification in dental panoramic radiographs based on local intensity distribution. To improve detection rates, K-Means method with constraints is used for enhancement of an estimated shape of the calcification. For the reduction of detection error rates, “surrounding region occupancy rate” which is a new statistics is defined. The proposed method can achieve higher detection rates and lower detection error rates. The experimental result shows that the improvement of the detection performance is obtained.