| Paper Abstract and Keywords |
| Presentation |
2024-10-03 15:10
A New Calcification Region Detector for Dental Panoramic Radiographs
Sota Nakano, Mitsuji Muneyasu, Soh Yoshida, Akira Asano (Kansai Univ.), Nanae Dewake, Nobuo Yoshinari (Matsumoto Dental Univ.), Keiichi Uchida (Matsumoto Dental Univ. Hospital) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
Calcification regions are sometimes observed in carotid arteries on dental panoramic radiographs and are expected to be detected as a sign of atherosclerosis. For this purpose, a detector that combines a segmentation model and a discriminator in series and its training method have been proposed. Although this method has achieved a significant improvement in accuracy compared to previous methods, it has not yet been sufficiently explored from the viewpoint of computational complexity. In this paper, we propose a new detector that outperforms the previous method in terms of both computational complexity and identification accuracy. The proposed detector uses TransFuse as the segmentation model and ResNet-10 as the discriminator. We show that the proposed method can significantly reduce the number of parameters while improving detection performance by applying it to actual data and evaluating it. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
dental panoramic radiograph / vascular disease / deep learning / semantic segmentation / discriminator / / / |
| Reference Info. |
ITE Tech. Rep. |
| Paper # |
|
| Date of Issue |
|
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|