Classification of the implant-ridge relationship utilizing the MobileNet architecture

Hao-Chieh Chang; Li-Wen Yu; Bo-Yi Liu; Po-Chun Chang

doi:10.1016/j.jds.2023.08.002

Classification of the implant-ridge relationship utilizing the MobileNet architecture

J Dent Sci. 2024 Jan;19(1):411-418. doi: 10.1016/j.jds.2023.08.002. Epub 2023 Aug 17.

Authors

Hao-Chieh Chang¹, Li-Wen Yu^{1

2}, Bo-Yi Liu³, Po-Chun Chang^{1

2

4}

Affiliations

¹ Graduate Institute of Clinical Dentistry, School of Dentistry, College of Medicine, National Taiwan University, Taipei, Taiwan.
² Division of Periodontics, Department of Dentistry, National Taiwan University Hospital, Taipei, Taiwan.
³ Department of Biomechatronics Engineering, National Taiwan University, Taipei, Taiwan.
⁴ School of Dentistry, College of Dental Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan.

Abstract

Background/purpose: Proper implant-ridge classification is crucial for developing a dental implant treatment plan. This study aimed to verify the ability of MobileNet, an advanced deep learning model characterized by a lightweight architecture that allows for efficient model deployment on resource-constrained devices, to identify the implant-ridge relationship.

Materials and methods: A total of 630 cone-beam computerized tomography (CBCT) slices from 412 patients were collected and manually classified according to Terheyden's definition, preprocessed, and fed to MobileNet for training under the conditions of limited datasets (219 slices, condition A) and full datasets (630 cases) without and with automatic gap filling (conditions B and C).

Results: The overall model accuracy was 84.00% in condition A and 95.28% in conditions B and C. In condition C, the accuracy rates ranged from 94.00 to 99.21%, with F1 scores of 89.36-100.00%, and errors due to unidentifiable bone-implant contact and miscellaneous reasons were eliminated.

Conclusion: The MobileNet architecture was able to identify the implant-ridge classification on CBCT slices and can assist clinicians in establishing a reliable preoperative diagnosis and treatment plan for dental implants. These results also suggest that artificial intelligence-assisted implant-ridge classification can be performed in the setting of general dental practice.

Keywords: Alveolar process; Artificial intelligence; Dental implants; Implantology.