Development and Validation of a Magnetic Resonance Imaging-Based Machine Learning Model for TMJ Pathologies.
The purpose of this study was to propose a machine learning model and assess its ability to classify TMJ pathologies on magnetic resonance (MR) images. This retrospective cohort study included 214 TMJs from 107 patients with TMJ signs and symptoms. A radiomics platform was used to extract (Huiying M...
| Published in: | BioMed Research International pp. 1 - 12 |
|---|---|
| Main Authors: | , , , , |
| Format: | diagnostic images research tables/charts Journal Article |
| Published: |
Wiley-Blackwell
7/6/2021
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=151269899&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 151269899 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 23146133 FT2T jtl: BioMed Research International issn: 23146133 maglogo: N pubinfo: dt: 7/6/2021 pid: 480 pub: Wiley-Blackwell place: Malden, Massachusetts artinfo: ui: 151269899 151269899 151269899 10.1155/2021/6656773 151269899 ppf: 1 ppct: 11 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Development and Validation of a Magnetic Resonance Imaging-Based Machine Learning Model for TMJ Pathologies. aug: au: Orhan, Kaan Driesen, Lukas Shujaat, Sohaib Jacobs, Reinhilde Chai, Xiangfei affil: OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, University of Leuven and Oral & Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium sug: subj: Machine Learning Magnetic Resonance Imaging Temporomandibular Joint Diseases Diagnosis Prediction Models Instrument Validation Instrument Construction Temporomandibular Joint Diseases Classification Human Retrospective Design Prospective Studies China Mandibular Condyle Pathology Intervertebral Disk Displacement Algorithms Logistic Regression Random Forest Support Vector Machine Sensitivity and Specificity ROC Curve Validation Studies ab: The purpose of this study was to propose a machine learning model and assess its ability to classify TMJ pathologies on magnetic resonance (MR) images. This retrospective cohort study included 214 TMJs from 107 patients with TMJ signs and symptoms. A radiomics platform was used to extract (Huiying Medical Technology Co., Ltd., China) imaging features of TMJ pathologies, condylar bone changes, and disc displacements. Thereafter, different machine learning (ML) algorithms and logistic regression were implemented on radiomic features for feature selection, classification, and prediction. The following radiomic features included first-order statistics, shape, texture, gray-level cooccurrence matrix (GLCM), gray-level run length matrix (GLRLM), and gray-level size zone matrix (GLSZM). Six classifiers, including logistic regression (LR), random forest (RF), decision tree (DT), k -nearest neighbors (KNN), XGBoost, and support vector machine (SVM) were used for model building which could predict the TMJ pathologies. The performance of models was evaluated by sensitivity, specificity, and ROC curve. KNN and RF classifiers were found to be the most optimal machine learning model for the prediction of TMJ pathologies. The AUC, sensitivity, and specificity for the training set were 0.89 and 1, while those for the testing set were 0.77 and 0.74, respectively, for condylar changes and disc displacement, respectively. For TMJ condylar bone changes Large-Area High-Gray-Level Emphasis, Gray-Level Nonuniformity, Long-Run Emphasis Long-Run High-Gray-Level Emphasis, Flatness, and Volume features, while for TMJ disc displacements Average Intensity, Sum Average, Spherical Disproportion, and Entropy features, were selected. This study has proposed a machine learning model by KNN and RF analysis on TMJ MR images, which can be used to classify condylar changes and TMJ disc displacements. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|