AI Article Synopsis
- The study aimed to evaluate how dental fillings affect an AI tool used for segmenting teeth in cone-beam computed tomography (CBCT) scans.
- A total of 175 scans were analyzed, with the AI tool showing good performance in both filled and unfilled teeth, although the presence of fillings slightly impacted segmentation accuracy.
- The AI tool was found to be significantly faster than manual methods, making it a promising solution for efficient tooth segmentation even when dental fillings are present.
Article Abstract
Objectives: To assess the influence of dental fillings on the performance of an artificial intelligence (AI)-driven tool for tooth segmentation on cone-beam computed tomography (CBCT) according to the type of tooth.
Methods: A total of 175 CBCT scans (500 teeth) were recruited for performing training (140 CBCT scans - 400 teeth) and validation (35 CBCT scans - 100 teeth) of the AI convolutional neural networks. The test dataset involved 74 CBCT scans (226 teeth), which was further divided into control and experimental groups depending on the presence of dental filling: without filling (control group: 24 CBCT scans - 113 teeth) and with coronal and/or root filling (experimental group: 50 CBCT scans - 113 teeth). The segmentation performance for both groups was assessed. Additionally, 10% of each tooth type (anterior, premolar, and molar) was randomly selected for time analysis according to manual, AI-based and refined-AI segmentation methods.
Results: The presence of fillings significantly influenced the segmentation performance (p<0.05). However, the accuracy metrics showed an excellent range of values for both control (95% Hausdorff Distance (95% HD): 0.01-0.08 mm; Intersection over union (IoU): 0.97-0.99; Dice similarity coefficient (DSC): 0.98-0.99; Precision: 1.00; Recall: 0.97-0.99; Accuracy: 1.00) and experimental groups (95% HD: 0.17-0.25 mm; IoU: 0.91-0.95; DSC: 0.95-0.97; Precision:1.00; Recall: 0.91-0.95; Accuracy: 0.99-1.00). The time analysis showed that the AI-based segmentation was significantly faster with a mean time of 29.8 s (p<0.001).
Conclusions: The proposed AI-driven tool allowed an accurate and time-efficient approach for the segmentation of teeth on CBCT images irrespective of the presence of high-density dental filling material and the type of tooth.
Clinical Significance: Tooth segmentation is a challenging and time-consuming task, mainly in the presence of artifacts generated by dental filling material. The proposed AI-driven tool could offer a clinically acceptable approach for tooth segmentation, to be applied in the digital dental workflows considering its time efficiency and high accuracy regardless of the presence of dental fillings.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jdent.2022.104069 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Toward Closing the Loop in Image-to-Image Conversion in Radiotherapy: A Quality Control Tool to Predict Synthetic Computed Tomography Hounsfield Unit Accuracy.
J Imaging
December 2024
Institute of Biomedical Engineering, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany.
In recent years, synthetic Computed Tomography (CT) images generated from Magnetic Resonance (MR) or Cone Beam Computed Tomography (CBCT) acquisitions have been shown to be comparable to real CT images in terms of dose computation for radiotherapy simulation. However, until now, there has been no independent strategy to assess the quality of each synthetic image in the absence of ground truth. In this work, we propose a Deep Learning (DL)-based framework to predict the accuracy of synthetic CT in terms of Mean Absolute Error (MAE) without the need for a ground truth (GT).
View Article and Find Full Text PDFInter-Fraction Motion and Dosimetric Analysis of Volumetric Modulated Arc Therapy for Craniospinal Irradiation in Adult Medulloblastoma Patients.
J Pers Med
November 2024
Department of Radiation Oncology, Miulli General Regional Hospital, Acquaviva delle Fonti, 70021 Bari, Italy.
. Adult medulloblastoma (AMB) patients should receive postoperative craniospinal irradiation (CSI) as a standard treatment. Volumetric intensity-modulated arc therapy (VMAT) is a promising method for CSI.
View Article and Find Full Text PDFMandibular bone defect healing using polylactic acid-nano-hydroxyapatite-gelatin scaffold loaded with hesperidin and dental pulp stem cells in rat.
Tissue Cell
December 2024
Stem Cells Technology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran; Department of Natural Sciences, West Kazakhstan Marat Ospanov Medical University, Aktobe, Kazakhstan. Electronic address:
Addressing mandibular defects poses a significant challenge in maxillofacial surgery. Recent advancements have led to the development of various biomimetic composite scaffolds aimed at facilitating mandibular defect reconstruction. This study aimed to assess the regenerative potential of a novel composite scaffold consisting of polylactic acid (PLA), hydroxyapatite nanoparticles (n-HA), gelatin, hesperidin, and human dental pulp stem cells (DPSCs) in a rat model of mandibular bone defect.
View Article and Find Full Text PDFIs the orthodontics-first method more stable than the surgery-first approach for orthognathic correction of maxillary deficiency?
J Craniomaxillofac Surg
December 2024
Glasgow University Dental Hospital & School, Glasgow, UK. Electronic address:
This study was carried out to compare the stability of Le Fort I maxillary advancement between the surgery-first approach (SFA) and the orthodontics-first approach (OFA), and to evaluate the impact of the quality of postoperative occlusion on maxillary stability. In total, 26 patients (13 SFA and 13 OFA) were included in this study. Cone beam computed tomography (CBCT) scans taken at T0 (1 week before surgery), T1 (1 week after surgery), and T2 (6 months after surgery) were used for the assessment of maxillary stability.
View Article and Find Full Text PDFA novel system for classification for midpalatal suture ossification based on pseudocolored and multilayer reconstructed coronal slices: Indication for selection of maxillary expansion methods.
Am J Orthod Dentofacial Orthop
December 2024
Center of Craniofacial Orthodontics, Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine; College of Stomatology, Shanghai Jiao Tong University; National Center for Stomatology; National Clinical Research Center for Oral Diseases; Shanghai Key Laboratory of Stomatology; Shanghai Research Institute of Stomatology; Research Unit of Oral and Maxillofacial Regenerative Medicine, Chinese Academy of Medical Sciences, Shanghai, China. Electronic address:
Introduction: A novel method was established for the staging of midpalatal suture (MPS) ossification based on a pseudocoloring stack of anterior and posterior MPS coronal slices obtained by cone-beam computed tomography (CBCT).
Methods: CBCT scans of 240 subjects aged 5-35 years were pseudocolor processed. The slice thickness of stacked anterior and posterior coronal observation planes was set at 5.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!