Tooth recognition and classification using multi-task learning and post-processing in dental panoramic radiographs
Tooth recognition and classification using multi-task learning and post-processing in dental panoramic radiographs
复制标题
在牙科全景射线照片中使用多任务学习和后处理进行牙齿识别和分类
DOI：
10.1117/12.2582046
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Fujita Hiroshi
中科院分区：
文献类型：
--
作者：
Morishita Takumi;Muramatsu Chisako;Zhou Xiangrong;Takahashi Ryo;Hayashi Tatsuro;Nishiyama Wataru;Hara Takeshi;Ariji Yoshiko;Ariji Eiichiro;Katsumata Akitoshi;Fujita Hiroshi
本研究旨在分析牙科全景片，以完善牙科档案，协助牙科医师诊断。作为初始阶段，我们检测每个牙齿并对其进行分类。由于这项研究的最终目标包括多个任务，如确定牙齿状况和识别病变，我们提出了一个多任务训练的基础上单次拍摄多盒检测器（SSD）与分支，以预测牙齿的存在或不存在。结果表明，与原始SSD相比，该模型的检测率提高了1.0%，每幅图像的假阳性数减少了0.03，按牙齿类型的检测率（成功检测和分类的牙齿总数/牙齿总数）提高了1.6%，表明了多任务学习在牙科全景X光片中的有效性。此外，我们整合了不区分牙型的单类检测结果和16类（中切牙、侧切牙、犬齿、第一前磨牙、第二前磨牙、第一磨牙、第二磨牙、第三磨牙，按上下颌区分）检测结果，以提高检出率，并包括后处理，用于将牙齿分类为32种类型并校正牙齿编号。结果，32种牙齿类型的检测率为98.8%，每幅图像的假阳性率为0.33，分类率为92.4%。
The purpose of this study is to analyze dental panoramic radiographs for completing dental files to contribute to the diagnosis by dentists. As the initial stage, we detected each tooth and classified its tooth type. Since the final goal of this study includes multiple tasks, such as determination of dental conditions and recognition of lesions, we proposed a multitask training based on a Single Shot Multibox Detector (SSD) with a branch to predict the presence or absence of a tooth. The results showed that the proposed model improved the detection rate by 1.0%, the number of false positives per image by 0.03, and the detection rate by tooth type (total number of successfully detected and classified teeth/total number of teeth) by 1.6% compared with the original SSD, suggesting the effectiveness of the multi-task learning in dental panoramic radiographs. In addition, we integrated results of single-class detection without distinguishing the tooth type and 16-class (central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar, third molar, distinguished by upper and lower jaws) detection for improving the detection rate and included post-processing for classification of teeth into 32 types and correction of tooth numbering. As a result, the detection rate of 98.8%, 0.33 false positives per image, and classification rate of 92.4% for 32 tooth types were archived.
影响因子：
3.3
作者：
Tuzoff, Dmitry, V;Tuzova, Lyudmila N.;Bednenko, Georgiy B.
通讯作者：
Bednenko, Georgiy B.