Dataset Information

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction.

ABSTRACT: High-fidelity three-dimensional (3D) models of tooth-bone structures are valuable for virtual dental treatment planning; however, they require integrating data from cone-beam computed tomography (CBCT) and intraoral scans (IOS) using methods that are either error-prone or time-consuming. Hence, this study presents Deep Dental Multimodal Fusion (DDMF), an automatic multimodal framework that reconstructs 3D tooth-bone structures using CBCT and IOS. Specifically, the DDMF framework comprises CBCT and IOS segmentation modules as well as a multimodal reconstruction module with novel pixel representation learning architectures, prior knowledge-guided losses, and geometry-based 3D fusion techniques. Experiments on real-world large-scale datasets revealed that DDMF achieved superior segmentation performance on CBCT and IOS, achieving a 0.17 mm average symmetric surface distance (ASSD) for 3D fusion with a substantial processing time reduction. Additionally, clinical applicability studies have demonstrated DDMF's potential for accurately simulating tooth-bone structures throughout the orthodontic treatment process.

SUBMITTER: Liu J

PROVIDER: S-EPMC10499902 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction.

Liu Jiaxiang J Hao Jin J Lin Hangzheng H Pan Wei W Yang Jianfei J Feng Yang Y Wang Gaoang G Li Jin J Jin Zuolin Z Zhao Zhihe Z Liu Zuozhu Z

Patterns (New York, N.Y.) 20230815 9

High-fidelity three-dimensional (3D) models of tooth-bone structures are valuable for virtual dental treatment planning; however, they require integrating data from cone-beam computed tomography (CBCT) and intraoral scans (IOS) using methods that are either error-prone or time-consuming. Hence, this study presents Deep Dental Multimodal Fusion (DDMF), an automatic multimodal framework that reconstructs 3D tooth-bone structures using CBCT and IOS. Specifically, the DDMF framework comprises CBCT a ...[more]

PMID: 37720330

Similar Datasets

Project description:BackgroundNumerous strategies have been proposed to decrease orthodontic treatment time. Photobiomodulation (PBM) has previously been demonstrated to assist in this objective. The aim of this study was to test if intraoral PBM increases the rate of tooth alignment and reduces the time required to resolve anterior dental crowding.MethodsNineteen orthodontic subjects with Class I or Class II malocclusion and Little's Irregularity Index (LII) ≥ 3 mm were selected from a pool of applicants, providing 28 total arches. No cases required extraction. The test group (N = 11, 18 arches, 10 upper, 8 lower) received daily PBM treatment with an intraoral LED device (OrthoPulse™, Biolux Research Ltd.) during orthodontic treatment, while the control group (N = 8, 10 arches, 3 upper, 7 lower) received only orthodontic treatment. The PBM device exposed the buccal side of the gums to near-infrared light with a continuous 850-nm wavelength, generating an average daily energy density of 9.5 J/cm(2). LII was measured at the start (T0) of orthodontic treatment until alignment was reached (T1, where LII ≤ 1 mm). The control group was mostly bonded with 0.018-in slot self-ligating SPEED brackets (Hespeler Orthodontics, Cambridge, ON. Canada), while conventionally-ligating Ormco Mini-Diamond twins were used on the PBM group (Ormco, Glendora, Calif. USA). Both groups progressed through alignment with NiTi arch-wires from 0.014-in through to 0.018-in (Ormco), with identical arch-wire changes. The rate of anterior alignment, in LII mm/week, and total treatment time was collected for both groups. Cox proportional hazards models were used to compare groups and while considering age, sex, ethnicity, arch and degree of crowding.ResultsThe mean alignment rate for the PBM group was significantly higher than that of the control group, with an LII change rate of 1.27 mm/week (SD 0.53, 95 % CI ± 0.26) versus 0.44 mm/week (SD 0.20, 95 % CI ± 0.12), respectively (p = 0.0002). The treatment time to alignment was significantly smaller for the PBM group, which achieved alignment in 48 days (SD 39, 95 % CI ± 39), while the control group took 104 days (SD 55, 95 % CI ±19, p = 0.0053) on average. These results demonstrated that intraoral PBM increased the average rate of tooth movement by 2.9-fold, resulting in a 54 % average decrease in alignment duration versus control. The average PBM compliance to daily treatments was 93 % during alignment.ConclusionsUnder the limitations of this study, the findings suggest that intraoral PBM could be used to decrease anterior alignment treatment time, which could consequently decrease full orthodontic treatment time. However, due to its limitations, further research in the form of a large, randomized trial is needed.Trial registrationClinicalTrials.gov NCT02267837 . Registered 10 October 2014.

Dataset Information

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction.

Publications

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets