Summary
International Workshop on Smart Info-Media Systems in Asia
2021
Session Number:RS3
Session:
Number:RS3-1
Detection of Calcification Regions from Dental Panoramic Radiographs Based on Semantic Segmentation Using Deep Learning
Taito Murano, Mitsuji Muneyasu, Soh Yoshida, Kosin Chamnongthai, Akira Asano, Keiichi Uchida, Nanae Dewake, Yasuaki Ishioka, Nobuo Yoshinari,
pp.122-127
Publication Date:2021/9/20
Online ISSN:2188-5079
PDF download
Summary:
Dental panoramic radiographs may show calcification regions that are a sign of vascular disease. Finding these regions in dentistry encourages medical checkups, and the sudden onset of vascular disease can be prevented. Therefore, some automatic detection methods for calcification regions have been proposed. Recently, a method using a deep learning-based object detector has been proposed. However, so far, no method that gives sufficiently reliable and practical results has been proposed. In this paper, we propose a method of estimating the location of calcification regions by semantic segmentation, which has been increasingly applied to medical image processing in recent years. The proposed method is also based on deep learning. The experimental results show that the proposed method improves detection accuracy.