Mu-Qing Liu1,2,3,4, Zi-Neng Xu5, Wei-Yu Mao1,2,3,4, Yuan Li1,2,3,4, Xiao-Han Zhang1,2,3,4, Hai-Long Bai5, Peng Ding5, Kai-Yuan Fu6,7,8,9. 1. Center for TMD and Orofacial Pain, Department of Oral and Maxillofacial Radiology, Peking University School and Hospital of Stomatology, No. 22 Zhong Guan Cun South Ave, Beijing, 100081, People's Republic of China. 2. National Clinical Research Center for Oral Diseases, Beijing, China. 3. National Engineering Laboratory for Digital and Material Technology of Stomatology, Beijing, China. 4. Beijing Key Laboratory of Digital Stomatology, Beijing, China. 5. Deepcare, Inc, Beijing, China. 6. Center for TMD and Orofacial Pain, Department of Oral and Maxillofacial Radiology, Peking University School and Hospital of Stomatology, No. 22 Zhong Guan Cun South Ave, Beijing, 100081, People's Republic of China. kqkyfu@bjmu.edu.cn. 7. National Clinical Research Center for Oral Diseases, Beijing, China. kqkyfu@bjmu.edu.cn. 8. National Engineering Laboratory for Digital and Material Technology of Stomatology, Beijing, China. kqkyfu@bjmu.edu.cn. 9. Beijing Key Laboratory of Digital Stomatology, Beijing, China. kqkyfu@bjmu.edu.cn.
Abstract
OBJECTIVES: The objective of our study was to develop and validate a deep learning approach based on convolutional neural networks (CNNs) for automatic detection of the mandibular third molar (M3) and the mandibular canal (MC) and evaluation of the relationship between them on CBCT. MATERIALS AND METHODS: A dataset of 254 CBCT scans with annotations by radiologists was used for the training, the validation, and the test. The proposed approach consisted of two modules: (1) detection and pixel-wise segmentation of M3 and MC based on U-Nets; (2) M3-MC relation classification based on ResNet-34. The performances were evaluated with the test set. The classification performance of our approach was compared with two residents in oral and maxillofacial radiology. RESULTS: For segmentation performance, the M3 had a mean Dice similarity coefficient (mDSC) of 0.9730 and a mean intersection over union (mIoU) of 0.9606; the MC had a mDSC of 0.9248 and a mIoU of 0.9003. The classification models achieved a mean sensitivity of 90.2%, a mean specificity of 95.0%, and a mean accuracy of 93.3%, which was on par with the residents. CONCLUSIONS: Our approach based on CNNs demonstrated an encouraging performance for the automatic detection and evaluation of the M3 and MC on CBCT. Clinical relevance An automated approach based on CNNs for detection and evaluation of M3 and MC on CBCT has been established, which can be utilized to improve diagnostic efficiency and facilitate the precision diagnosis and treatment of M3.
OBJECTIVES: The objective of our study was to develop and validate a deep learning approach based on convolutional neural networks (CNNs) for automatic detection of the mandibular third molar (M3) and the mandibular canal (MC) and evaluation of the relationship between them on CBCT. MATERIALS AND METHODS: A dataset of 254 CBCT scans with annotations by radiologists was used for the training, the validation, and the test. The proposed approach consisted of two modules: (1) detection and pixel-wise segmentation of M3 and MC based on U-Nets; (2) M3-MC relation classification based on ResNet-34. The performances were evaluated with the test set. The classification performance of our approach was compared with two residents in oral and maxillofacial radiology. RESULTS: For segmentation performance, the M3 had a mean Dice similarity coefficient (mDSC) of 0.9730 and a mean intersection over union (mIoU) of 0.9606; the MC had a mDSC of 0.9248 and a mIoU of 0.9003. The classification models achieved a mean sensitivity of 90.2%, a mean specificity of 95.0%, and a mean accuracy of 93.3%, which was on par with the residents. CONCLUSIONS: Our approach based on CNNs demonstrated an encouraging performance for the automatic detection and evaluation of the M3 and MC on CBCT. Clinical relevance An automated approach based on CNNs for detection and evaluation of M3 and MC on CBCT has been established, which can be utilized to improve diagnostic efficiency and facilitate the precision diagnosis and treatment of M3.
Authors: H Ghaeminia; G J Meijer; A Soehardi; W A Borstlap; J Mulder; O J C Vlijmen; S J Bergé; T J J Maal Journal: Int J Oral Maxillofac Surg Date: 2011-04-19 Impact factor: 2.789
Authors: Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun Journal: Nature Date: 2017-01-25 Impact factor: 49.962
Authors: H Ghaeminia; G J Meijer; A Soehardi; W A Borstlap; J Mulder; S J Bergé Journal: Int J Oral Maxillofac Surg Date: 2009-07-28 Impact factor: 2.789
Authors: Purv Shashank Patel; Jigna S Shah; Bhavin B Dudhia; Purva Bharat Butala; Yesha V Jani; Roseline S Macwan Journal: Indian J Dent Res Date: 2020 Jan-Feb