Accuracy of biomarkers obtained from cone beam computed tomography in assessing the internal trabecular structure of the mandibular condyle

Deep learning for osteoarthritis classification in temporomandibular joint

OBJECTIVES

This study aimed to develop a diagnostic support tool using pretrained models for classifying panoramic images of the temporomandibular joint (TMJ) into normal and osteoarthritis (OA) cases.

SUBJECTS AND METHODS

A total of 858 panoramic images of the TMJ (395 normal and 463 TMJ-OA) were obtained from 518 individuals from January 2015 to December 2018. The data were randomly divided into training, validation, and testing sets (6:2:2). We used pretrained Resnet152 and EfficientNet-B7 as transfer learning models. The accuracy, specificity, sensitivity, area under the curve, and gradient-weighted class activation mapping (grad-CAM) of both trained models were evaluated. The performances of the trained models were compared to that of dentists (both TMD specialists and general dentists).

RESULTS

The classification accuracies of ResNet-152 and EfficientNet-B7 were 0.87 and 0.88, respectively. The trained models exhibited the highest accuracy in OA classification. In the grad-CAM analysis, the trained models focused on specific areas in osteoarthritis images where erosion or osteophyte were observed.

CONCLUSIONS

The artificial intelligence model improved the diagnostic power of TMJ-OA when trained with two-dimensional panoramic condyle images and can be effectively applied by dentists as a screening diagnostic tool for TMJ-OA.

Radiomics approach to the condylar head for legal age classification using cone-beam computed tomography: A pilot study

Legal age estimation of living individuals is a critically important issue, and radiomics is an emerging research field that extracts quantitative data from medical images. However, no reports have proposed age-related radiomics features of the condylar head or an age classification model using those features. This study aimed to introduce a radiomics approach for various classifications of legal age (18, 19, 20, and 21 years old) based on cone-beam computed tomography (CBCT) images of the mandibular condylar head, and to evaluate the usefulness of the radiomics features selected by machine learning models as imaging biomarkers. CBCT images from 85 subjects were divided into eight age groups for four legal age classifications: ≤17 and ≥18 years old groups (18-year age classification), ≤18 and ≥19 years old groups (19-year age classification), ≤19 and ≥20 years old groups (20-year age classification) and ≤20 and ≥21 years old groups (21-year age classification). The condylar heads were manually segmented by an expert. In total, 127 radiomics features were extracted from the segmented area of each condylar head. The random forest (RF) method was utilized to select features and develop the age classification model for four legal ages. After sorting features in descending order of importance, the top 10 extracted features were used. The 21-year age classification model showed the best performance, with an accuracy of 91.18%, sensitivity of 80%, and specificity of 95.83%. Radiomics features of the condylar head using CBCT showed the possibility of age estimation, and the selected features were useful as imaging biomarkers.

Quantitative bone imaging biomarkers and joint space analysis of the articular Fossa in temporomandibular joint osteoarthritis using artificial intelligence models

Temporomandibular joint osteoarthritis (TMJ OA) is a disease with a multifactorial etiology, involving many pathophysiological processes, and requiring comprehensive assessments to characterize progressive cartilage degradation, subchondral bone remodeling, and chronic pain. This study aimed to integrate quantitative biomarkers of bone texture and morphometry of the articular fossa and joint space to advance the role of imaging phenotypes for diagnosis of Temporomandibular Joint Osteoarthritis (TMJ OA) in early to moderate stages by improving the performance of machine-learning algorithms to detect TMJ OA status. Ninety-two patients were prospectively enrolled (184 h-CBCT scans of the right and left mandibular condyles), divided into two groups: 46 control and 46 TMJ OA subjects. No significant difference in the articular fossa radiomic biomarkers was found between TMJ OA and control patients. The superior condyle-to-fossa distance (p < 0.05) was significantly smaller in diseased patients. The interaction effects of the articular fossa radiomic biomarkers enhanced the performance of machine-learning algorithms to detect TMJ OA status. The LightGBM model achieved an AUC 0.842 to diagnose the TMJ OA status with Headaches and Range of Mouth Opening Without Pain ranked as top features, and top interactions of VE-cadherin in Serum and Angiogenin in Saliva, TGF-β1 in Saliva and Headaches, Gender and Muscle Soreness, PA1 in Saliva and Range of Mouth Opening Without Pain, Lateral Condyle Grey Level Non-Uniformity and Lateral Fossa Short Run Emphasis, TGF-β1 in Serum and Lateral Fossa Trabeculae number, MMP3 in Serum and VEGF in Serum, Headaches and Lateral Fossa Trabecular spacing, Headaches and PA1 in Saliva, and Headaches and BDNF in Saliva. Our preliminary results indicate that condyle imaging features may be more important in regards to main effects, but the fossa imaging features may have a larger contribution in terms of interaction effects. More studies are needed to optimize and further enhance machine-learning algorithms to detect early markers of disease, improve prediction of disease progression and severity to ultimately better serve clinical decision support systems in the treatment of patients with TMJ OA.

Three-dimensional radiological anatomy of condyle trabecular bone based on a Volume-of-Interest analysis

OBJECTIVES

Three-dimensional radiological anatomic characteristics of condyle trabeculae was obtained quantitatively based on a volume-of-interest (VOI) analysis.

METHODS

Nine human mandibular condyle specimens were scanned by micro-computed tomography (micro-CT). A total of 34 VOIs were selected from each condyle specimen, which were divided into six layers and four parts to analyze the morphological characteristics of trabeculae based on cylindrical VOIs with a diameter and height of 2 mm. One-way analysis of variance was used to compare the regional differences of morphological parameters among each layer and part.

RESULTS

Values for bone mineral density, bone volume/total volume, trabecular thickness, and trabecular bone number were greater in the anterior part compared with the posterior part; and the lateral part was larger than the medial part in the first, second, and third layers, while the medial part was larger in the fourth and fifth layers; these values in the first and sixth layers were much larger, while those in the third and fourth layers were smaller. Bone surface area/bone volume, trabecular spacing, and trabecular bone pattern factor were larger in the posterior part than in the anterior part; and the lateral part was larger than the medial part in the fourth and fifth layers, while the medial part was larger in the first and second layers.

CONCLUSIONS

The morphological distribution of VOIs was anisotropic within trabecular bone of human mandibular condyles. The upper and lower ends of trabecular bone were much more compact, with higher bone density, trabecular thickness, and trabecular number than in the middle layers.

Differentiation of osteosarcoma from osteomyelitis using microarchitectural analysis on panoramic radiographs

Diagnosing osteosarcoma (OS) is very challenging and OS is often misdiagnosed as osteomyelitis (OM) due to the nonspecificity of its symptoms upon initial presentation. This study investigated the possibility of detecting OS-induced trabecular bone changes on panoramic radiographs and differentiating OS from OM by analyzing fractal dimensions (FDs) and degrees of anisotropy (DAs). Panoramic radiographs of patients with histopathologically proven OS and OM of the jaw were obtained. A total of 23 patients with OS and 40 patients with OM were enrolled. To investigate whether there was a microarchitectural difference between OS lesions and normal trabecular areas in each patient, two regions of interest (ROIs) were located on the CT images. Three microarchitectural parameters (box-counting FD, fast Fourier transform-based FD, and DA) were calculated. For both OS and OM, significant differences were found for all three microarchitectural parameters. Compared to normal trabecular bone, trabecular bone affected by OS and OM became isotropic and more complex. When comparing OS and OM, a statistically significant difference was found only in DA. Trabecular bones affected by OS became more isotropic than those affected by OM. Microarchitectural analysis, especially DA, could be useful for detecting OS-induced trabecular alterations and differentiating OS from OM.

Evaluation and correlation of condylar cortication by cone-beam computed tomography: A retrospective study

Background:

Temporomandibular joint (TMJ) is a ginglymo-diarthroidial joint with fibroelastic cartilage. The chondrogenesis initiates from the 12^th week of intrauterine life and the development of condyle is associated with growth. The condylar cortication shows distinct morphological variation for each individual in each stage of their life. The cortical bone around the condyle could be used as a factor for chronological age assessment and it can act as a tool in forensic medicine.

Aim and Objective:

The study was carried out to evaluate the cortical grading in mandibular condyle using two different applications and to correlate their grades with chronological age.

Setting and Design:

Hospital-based retrospective observational cross-sectional study.

Materials and Methods:

The study was carried out in 40 patients and 80 TMJs were assessed for cortication grades in Carestream 3D imaging and Image J applications. These grading from both the applications were correlated with the chronological age.

Statistical Analysis:

SPSS (Statistical Analysis for the Social Science) – Cohen's Kappa inter-examiner reliability and Spearman's correlation coefficient were used.

Results:

The radiological assessment of condylar cortication in individual application showed significant results and the relationship of cortication with chronological age showed a significant correlation.

Conclusion:

The condylar cortication grading is a simple technique and can be used as a factor for chronological age assessment. This is an initial study which used two different applications to view the cortication of the mandibular condyle and to correlate the cortication with chronological age. Hence, a large sample size-based study is required for further research.

Temporomandibular Joint Osteoarthritis Diagnosis Using Privileged Learning of Protein Markers

Diagnosis of temporomandibular joint (TMJ) Osteoarthritis (OA) before serious degradation of cartilage and subchondral bone occurs can help prevent chronic pain and disability. Clinical, radiomic, and protein markers collected from TMJ OA patients have been shown to be predictive of OA onset. Since protein data can often be unavailable for clinical diagnosis, we harnessed the learning using privileged information (LUPI) paradigm to make use of protein markers only during classifier training. Three different LUPI algorithms are compared with traditional machine learning models on a dataset extracted from 92 unique OA patients and controls. The best classifier performance of 0.80 AUC and 75.6 accuracy was obtained from the KRVFL+ model using privileged protein features. Results show that LUPI-based algorithms using privileged protein data can improve final diagnostic performance of TMJ OA classifiers without needing protein microarray data during classifier diagnosis.

TMJOAI: An Artificial Web-Based Intelligence Tool for Early Diagnosis of the Temporomandibular Joint Osteoarthritis

Osteoarthritis is a chronic disease that affects the temporomandibular joint (TMJ), causing chronic pain and disability. To diagnose patients suffering from this disease before advanced degradation of the bone, we developed a diagnostic tool called TMJOAI. This machine learning based algorithm is capable of classifying the health status TMJ in of patients using 52 clinical, biological and jaw condyle radiomic markers. The TMJOAI includes three parts. the feature preparation, selection and model evaluation. Feature generation includes the choice of radiomic features (condylar trabecular bone or mandibular fossa), the histogram matching of the images prior to the extraction of the radiomic markers, the generation of feature pairwise interaction, etc.; the feature selection are based on the p-values or AUCs of single features using the training data; the model evaluation compares multiple machine learning algorithms (e.g. regression-based, tree-based and boosting algorithms) from 10 times 5-fold cross validation. The best performance was achieved with averaging the predictions of XGBoost and LightGBM models; and the inclusion of 32 additional markers from the mandibular fossa of the joint improved the AUC prediction performance from 0.83 to 0.88. After cross-validation and testing, the tools presented here have been deployed on an open-source, web-based system, making it accessible to clinicians. TMJOAI allows users to add data and automatically train and update the machine learning models, and therefore improve their performance.

Quantitative bone imaging biomarkers to diagnose temporomandibular joint osteoarthritis

Bone degradation of the condylar surface is seen in temporomandibular joint osteoarthritis (TMJ OA); however, the initial changes occur in the subchondral bone. This cross-sectional study was performed to evaluate 23 subchondral bone imaging biomarkers for TMJ OA. The sample consisted of high-resolution cone beam computed tomography scans of 84 subjects, divided into two groups: TMJ OA (45 patients with TMJ OA) and control (39 asymptomatic subjects). Six regions of each mandibular condyle scan were extracted for computation of five bone morphometric and 18 grey-level texture-based variables. The groups were compared using the Mann-Whitney U-test, and the receiver operating characteristics (ROC) curve was determined for each variable that showed a statically significance difference. The results showed statistically significant differences in the subchondral bone microstructure in the lateral and central condylar regions between the control and TMJ OA groups (P< 0.05). The area under the ROC curve (AUC) for these variables was between 0.620 and 0.710. In conclusion, 13 imaging bone biomarkers presented an acceptable diagnostic performance for the diagnosis of TMJ OA, indicating that the texture and geometry of the subchondral bone microarchitecture may be useful for quantitative grading of the disease.

Osteoarthritis of the Temporomandibular Joint can be diagnosed earlier using biomarkers and machine learning

After chronic low back pain, Temporomandibular Joint (TMJ) disorders are the second most common musculoskeletal condition affecting 5 to 12% of the population, with an annual health cost estimated at $4 billion. Chronic disability in TMJ osteoarthritis (OA) increases with aging, and the main goal is to diagnosis before morphological degeneration occurs. Here, we address this challenge using advanced data science to capture, process and analyze 52 clinical, biological and high-resolution CBCT (radiomics) markers from TMJ OA patients and controls. We tested the diagnostic performance of four machine learning models: Logistic Regression, Random Forest, LightGBM, XGBoost. Headaches, Range of mouth opening without pain, Energy, Haralick Correlation, Entropy and interactions of TGF-β1 in Saliva and Headaches, VE-cadherin in Serum and Angiogenin in Saliva, VE-cadherin in Saliva and Headaches, PA1 in Saliva and Headaches, PA1 in Saliva and Range of mouth opening without pain; Gender and Muscle Soreness; Short Run Low Grey Level Emphasis and Headaches, Inverse Difference Moment and Trabecular Separation accurately diagnose early stages of this clinical condition. Our results show the XGBoost + LightGBM model with these features and interactions achieves the accuracy of 0.823, AUC 0.870, and F1-score 0.823 to diagnose the TMJ OA status. Thus, we expect to boost future studies into osteoarthritis patient-specific therapeutic interventions, and thereby improve the health of articular joints.

Software comparison to analyze bone radiomics from high resolution CBCT scans of mandibular condyles

OBJECTIVES

Radiomics refers to the extraction and analysis of advanced quantitative imaging from medical images to diagnose and/or predict diseases. In the dentistry field, the bone data from mandibular condyles could be computationally analyzed using the voxel information provided by high-resolution CBCT scans to increase the diagnostic power of temporomandibular joint (TMJ) conditions. However, such quantitative information demands innovative computational software, algorithm implementation, and validation. Our study's aim was to compare a newly developed BoneTexture application to two-consolidated software with previous applications in the medical field, Ibex and BoneJ, to extract bone morphometric and textural features from mandibular condyles.

METHODS

We used an imaging database of HR-CBCT TMJs scans with an isotropic voxel size of 0.08 mm3 . A single group with 66 distinct mandibular condyles composed the final sample. We calculated 18 variables for bone textural features and 5 for bone morphometric measurements using the Ibex, BoneJ and BoneTexture applications. Spearman correlation and Bland-Altman plot analyses were done to compare the agreement among software.

RESULTS

The results showed a high Spearman correlation among the software applications ( r = 0.7-1), with statistical significance for all variables, except Grey Level Non-Uniformity and Short Run Emphasis. The Bland-Altman vertical axis showed, in general, good agreement between the software applications and the horizontal axis showed a narrow average distribution for Correlation, Long Run Emphasis and Long Run High Grey Level Emphasis.

CONCLUSIONS

Our data showed consistency among the three applications to analyze bone radiomics in high-resolution CBCT. Further studies are necessary to evaluate the applicability of those variables as new bone imaging biomarkers to diagnose bone diseases affecting TMJs.

Minimally Invasive Approach for Diagnosing TMJ Osteoarthritis

This study's objectives were to test correlations among groups of biomarkers that are associated with condylar morphology and to apply artificial intelligence to test shape analysis features in a neural network (NN) to stage condylar morphology in temporomandibular joint osteoarthritis (TMJOA). Seventeen TMJOA patients (39.9 ± 11.7 y) experiencing signs and symptoms of the disease for less than 10 y and 17 age- and sex-matched control subjects (39.4 ± 15.2 y) completed a questionnaire, had a temporomandibular joint clinical exam, had blood and saliva samples drawn, and had high-resolution cone beam computed tomography scans taken. Serum and salivary levels of 17 inflammatory biomarkers were quantified using protein microarrays. A NN was trained with 259 other condyles to detect and classify the stage of TMJOA and then compared to repeated clinical experts' classifications. Levels of the salivary biomarkers MMP-3, VE-cadherin, 6Ckine, and PAI-1 were correlated to each other in TMJOA patients and were significantly correlated with condylar morphological variability on the posterior surface of the condyle. In serum, VE-cadherin and VEGF were correlated with one another and with significant morphological variability on the anterior surface of the condyle, while MMP-3 and CXCL16 presented statistically significant associations with variability on the anterior surface, lateral pole, and superior-posterior surface of the condyle. The range of mouth opening variables were the clinical markers with the most significant associations with morphological variability at the medial and lateral condylar poles. The repeated clinician consensus classification had 97.8% agreement on degree of degeneration within 1 group difference. Predictive analytics of the NN's staging of TMJOA compared to the repeated clinicians' consensus revealed 73.5% and 91.2% accuracy. This study demonstrated significant correlations among variations in protein expression levels, clinical symptoms, and condylar surface morphology. The results suggest that 3-dimensional variability in TMJOA condylar morphology can be comprehensively phenotyped by the NN.

Alternative cone-beam CT method for the analysis of mandibular condylar bone in patients with degenerative joint disease

OBJECTIVE

The aim of this study was to investigate the use of 3D microstructural bone analysis in patients with degenerative joint disorder (DJD) to enhance the diagnostic capacity of cone beam computed tomography (CBCT) in the evaluation of bone tissue.

METHODS

147 TMJ CBCT images of 88 participants were assessed with regard to DJD in the mandibular condyle. We divided each condyle into 3 groups (0, 1, 2) according to diagnosis of DJD: 0 indicates normal condyles (control individuals), 1 indicates mild erosive osteoarthritic change (EOC) and 2 indicates severe EOC. 3D fractal dimension (FD) was calculated on CBCT images of mandibular condyle and were compared with the radiographic diagnosis of patients.

RESULTS

ANOVA test showed that there was statistically significant difference in FD values among each groups. The average FD value of group 0 was 1.971, group 1 was 1.918 and group 2 was 1.863. Lower FD values and more severe degenerative changes were seen in patient group 2. To evaluate the reliability of fractal analysis (FA) method, receiver operating characteristic (ROC) curve analysis was performed. Area under the curve (AUC) was 0.717 (p < 0.001).

CONCLUSION

This study provides a preliminary conclusion that fractal analysis may be a helpful tool to enhance the diagnostic capacity of CBCT in the evaluation of DJD.

Shape variation analyzer: a classifier for temporomandibular joint damaged by osteoarthritis

We developed a deep learning neural network, the Shape Variation Analyzer (SVA), that allows disease staging of bony changes in temporomandibular joint (TMJ) osteoarthritis (OA). The sample was composed of 259 TMJ CBCT scans for the training set and 34 for the testing dataset. The 3D meshes had been previously classified in 6 groups by 2 expert clinicians. We improved the robustness of the training data using data augmentation, SMOTE, to alleviate over-fitting and to balance classes. We combined geometrical features and a shape descriptor, heat kernel signature, to describe every shape. The results were compared to nine different supervised machine learning algorithms. The deep learning neural network was the most accurate for classification of TMJ OA. In conclusion, SVA is a 3D Sheer extension that classifies pathology of the temporomandibular joint osteoarthritis cases based on 3D morphology.