Understanding Occlusion and Temporomandibular Joint Function Using Deep Learning and Predictive Modeling

Clinical and Experimental Dental Research, Journal Year: 2024, Volume and Issue: 10(6)

Published: Nov. 19, 2024

ABSTRACT Objectives Advancements in artificial intelligence (AI)‐driven predictive modeling dentistry are outpacing the clinical translation of research findings. Predictive uses statistical methods to anticipate norms related TMJ dynamics, complementing imaging modalities like cone beam computed tomography (CBCT) and magnetic resonance (MRI). Deep learning, a subset AI, helps quantify analyze complex hierarchical relationships occlusion function. This narrative review explores application deep learning identify trends associations Results Debates persist regarding best practices for managing occlusal factors temporomandibular joint (TMJ) function analysis while interpreting quantifying findings mitigating biases remain challenging. Data generated from noninvasive chairside tools such as jaw trackers, video tracking, 3D scanners with virtual articulators offer unique insights by predicting variations dynamic movement, TMJ, occlusion. The predictions help us understand highly individualized surrounding that often required address disorders (TMDs) general practice. Conclusions Normal function, occlusion, appropriate management TMDs continue attract ongoing debate. examines how aid understanding provides into dental conditions may improve diagnosis treatment outcomes techniques.

Language: Английский

---

Accuracy of the digital implant impression with splinted and non-splinted intraoral scan bodies: A systematic review

The Journal of Indian Prosthodontic Society, Journal Year: 2025, Volume and Issue: 25(1), P. 3 - 12

Published: Jan. 1, 2025

Introduction: Accurate implant impressions are crucial for successful prosthetic rehabilitation. Digital using intraoral scanners (IOS) have emerged as an alternative to conventional techniques. Various factors influence the accuracy of digital impressions, including scan body design, scanning protocol, and splinting Aim Objective: To evaluate difference between splinted nonsplinted bodies in single or multiple implants by measuring distance angular deviations superimposed impressions. Materials Methods: PRISMA guidelines were followed this systematic review. Electronic databases searched relevant studies published up January 2024. Inclusion criteria encompassed clinical trials, vivo vitro on partially fully edentulous arches. Two reviewers independently assessed abstracts, titles full texts. Data extraction included deviation, trueness, precision measurements. Discussion: Most found that improved particularly complete-arch cases. Splinting techniques varied, light-cured resin, pattern dental floss, custom-made splints. Factors such inter-implant distance, number choice IOS also influenced accuracy. However, some reported no significant improvement even negative effects Conclusion: generally improves especially It enhances stitching process workflows provides more stable reference points. effectiveness may vary depending specific situation, used. Further research is needed establish standardized protocols long-term outcomes digitally fabricated restorations based

Language: Английский

---

Multi-objective optimization for enhanced digitalization in direct 3D printing: an application in dentistry

Clinical Oral Investigations, Journal Year: 2025, Volume and Issue: 29(5)

Published: April 11, 2025

Language: Английский

---

Classifying Dental Care Providers Through Machine Learning with Features Ranking

Data & Metadata, Journal Year: 2025, Volume and Issue: 4, P. 755 - 755

Published: April 7, 2025

This study investigates the application of machine learning (ML) models for classifying dental providers into two categories—standard rendering and safety net clinic (SNC) providers—using a 2018 dataset 24,300 instances with 20 features. The dataset, characterized by high missing values (38.1%), includes service counts (preventive, treatment, exams), delivery systems (FFS, managed care), beneficiary demographics. Feature ranking methods such as information gain, Gini index, ANOVA were employed to identify critical predictors, revealing treatment-related metrics (TXMT_USER_CNT, TXMT_SVC_CNT) top-ranked Twelve ML models, including k-Nearest Neighbors (kNN), Decision Trees, Support Vector Machines (SVM), Stochastic Gradient Descent (SGD), Random Forest, Neural Networks, Boosting, evaluated using 10-fold cross-validation. Classification accuracy was tested across incremental feature subsets derived from rankings. Network achieved highest (94.1%) all features, followed Boosting (93.2%) Forest (93.0%). Models showed improved performance more features incorporated, SGD ensemble demonstrating robustness data. highlighted dominance treatment annotation codes in distinguishing provider types, while demographic variables (AGE_GROUP, CALENDAR_YEAR) had minimal impact. underscores importance selection enhancing model efficiency accuracy, particularly imbalanced healthcare datasets. These findings advocate integrating feature-ranking techniques advanced algorithms optimize classification, enabling targeted resource allocation underserved populations.

Language: Английский

---

Predictive modelling of freeway space utilising clinical history, normalised muscle activity, dental occlusion, and mandibular movement analysis

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 16, 2024

Abstract This study aimed to predict dental freeway space by examining the clinical history, habits, occlusal parameters, mandibular hard tissue movement, soft motion, muscle activity, and temporomandibular joint function of 66 participants. Data collection involved video-based facial landmark tracking, electrognathography, surface electromyography range space, chewing tasks, phonetic expressions, vibration analysis, 3D jaw scans occlusion. resulted in a dataset 121 predictor features, with as target variable. Six models were trained on synthetic data ranging from 500 25,000 observations, 65 original observations reserved for testing: Linear Regression, Random Forest, CatBoost Regressor, XGBoost Multilayer Perceptron Neural Network (MPNN), TabNet. Explainable AI indicated that key predictors included phonetics, resting temporalis activity during clenching, body weight, lateral displacements, arch parameters. excelled test error 0.65 mm using 5000 points, while refined MPNN achieved best performance points unique predictors, yielding an absolute 0.43 observations.

Language: Английский

---

A comparison of a handheld minicomputer and an external graphics processing unit in performing 3D intraoral scans

Journal of Prosthetic Dentistry, Journal Year: 2024, Volume and Issue: 133(2), P. 568 - 574

Published: April 12, 2024

Statement of problemWhether the use an external graphics processing unit (eGPU) and a handheld computer prolongs operation time for 3-dimensional (3D) intraoral scanning or produces clinically unacceptable scans is unclear.PurposeThe purpose this in vitro study was to compare 3D scan accuracy small portable device eGPU with desktop-grade workstations.Material methodsA computer, laptop, desktop workstation, card were used printed set maxillary mandibular casts 10 consecutive times using scanner. The provided by manufacturers scanner, process conducted single operator following best-practice methods. required models analyzed via 1-way ANOVA. Dimensional similarity assessed Hausdorff distance (HD) across resultant 80 independent bimaxillary scans. A dental scanner which served as control reference. HD values multifactorial ANOVA (α=.05).ResultsIn real-time rendering scans, laptop without took significantly longer (146.41 ±10.66 seconds) (F=30.58, P<.001) compared when connected (117.66 ±6.95 (114.84 ±7.20 seconds). Postprocessing more favorable on workstation (16.61 ±4.18 (27.85 ±8.89 (32.37 ±7.16 connected, combination (14.66 ±7.37 producing best results (F=14.60, P<.001). assessments showed high consistency (F=0.92, P=.44), no discrepancies noted prepared tooth surfaces. minicomputer produced all 4 groups.ConclusionsThe offered comparable output from traditional while preserving details preparations but at faster rates.

Language: Английский

---

Relationship between anterior occlusion, arch dimension, and mandibular movement during speech articulation: A three-dimensional analysis

Journal of Prosthetic Dentistry, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 1, 2024

Language: Английский

---

Application of 3D neural networks and explainable AI to classify ICDAS detection system on mandibular molars

Journal of Prosthetic Dentistry, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

---

TSegLab: Multi-stage 3D dental scan segmentation and labeling

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 185, P. 109535 - 109535

Published: Dec. 20, 2024

Language: Английский

---