Construction of a new automatic grading system for jaw bone mineral density level based on deep learning using cone beam computed tomography

Abstract

To develop and verify an automatic classification method using artificial intelligence deep learning to determine the bone mineral density level of the implant site in oral implant surgery from radiographic data obtained from cone beam computed tomography (CBCT) images. Seventy patients with mandibular dentition defects were scanned using CBCT. These Digital Imaging and Communications in Medicine data were cut into 605 training sets, and then the data were processed with data standardization, and the Hounsfiled Unit (HU) value level was determined as follows: Type 1, 1000–2000; type 2, 700–1000; type 3, 400–700; type 4, 100–400; and type 5, − 200–100. Four trained dental implant physicians manually identified and classified the area of the jaw bone density level in the image using the software LabelMe. Then, with the assistance of the HU value generated by LabelMe, a physician with 20 years of clinical experience confirmed the labeling level. Finally, the HU mean values of various categories marked by dental implant physicians were compared to the mean values detected by the artificial intelligence model to assess the accuracy of artificial intelligence classification. After the model was trained on 605 training sets, the statistical results of the HU mean values of various categories in the dataset detected by the model were almost the same as the HU grading interval on the data annotation. This new classification provides a more detailed solution to guide surgeons to adjust the drilling rate and tool selection during preoperative decision-making and intraoperative hole preparation for oral implant surgery.

The Application of Deep Learning on CBCT in Dentistry

“…The accuracy could reach 84.63% and 95.20% in hexagonal prism and cylindrical voxel shapes, respectively [ 70 ]. Nested-U-Net was also used, and the Dice score could reach 75% [ 71 ]. QCBCT-NET, which combines a generative adversarial network (Cycle-GAN) and U-Net, can be used to measure the mineral density of bone.…”

Dental Caries Detection and Classification in CBCT Images Using Deep Learning

“…Deep learning has been widely used in CBCT images. 20 , 21 This technique is used in a variety of fields, including segmentation of the upper airway, 22 , 23 , 24 segmentation of the inferior alveolar nerve, 25 , 26 bone-related disease, 27 , 28 tooth segmentation and endodontics, 29 temporomandibular joint and sinus disease, 30 , 31 dental implant, 32 , 33 and landmark localisation. 34 , 35 Previous studies evaluated the caries detection performance of deep learning methods.…”

Correlation between peri-implant bone mineral density and primary implant stability based on artificial intelligence classification

“…In our previous studies, we preliminarily established a new artificial intelligence (AI) based BMD grading system 11 , which introduced a fresh approach to BMD classification. According to HU value, BMD was divided into five grades: 1 grade for HU value > 1000, 2 grade for HU value 700–1000, 3 grade for HU value 400–700, 4 grade for HU value 100–400, and 5 grade for HU value < 100.…”