3D Morphology Analysis of TMJ Articular Eminence in Magnetic Resonance Imaging

Magnetic resonance imaging evaluation of the disc morphology of temporomandibular joint in patients with severe hemophilia

OBJECTIVES

This study aimed to assess the morphological differences in the articular disc (AD) between hemophilic patients and healthy individuals of the control group for further association with signs and symptoms.

METHODS

Fourteen severe hemophilic patients had their AD evaluated by magnetic resonance imaging (MRI). The morphological findings were compared to those of a control group consisting of 14 healthy individuals. MRI was used to evaluate all the components of the temporomandibular (TMJ), including the AD, resulting in sequential T1-weighted parasagittal images. All the images were acquired with teeth in maximum intercuspation position.

RESULTS

Morphological alterations showed significant statistical differences (P-value = 0.0068), whereas no statistical differences were found in the other variables, including TMJ pain, headache, bruxism and mouth opening limitation. In the group of non-hemophilic individuals, only two (14.29%) presented AD with non-biconcave features, whereas in the group of hemophilic patients, nine (64.29%) presented AD with a morphology other than biconcave.

CONCLUSIONS

In patients with severe hemophilia, there seems to be a pattern of morphological alterations in the articular disc over time. The standard biconcave morphology of AD tends to change into other ones, particularly biplanar, hemiconvex and folded.

Classifying Temporomandibular Disorder with Artificial Intelligent Architecture Using Magnetic Resonance Imaging

This study proposes a new diagnostic tool for automatically extracting discriminative features and detecting temporomandibular joint disc displacement (TMJDD) accurately with artificial intelligence. We analyzed the structural magnetic resonance imaging (MRI) images of 52 patients with TMJDD and 32 healthy controls. The data were split into training and test sets, and only the training sets were used for model construction. U-net was trained with 100 sagittal MRI images of the TMJ to detect the joint cavity between the temporal bone and the mandibular condyle, which was used as the region of interest, and classify the images into binary categories using four convolutional neural networks: InceptionResNetV2, InceptionV3, DenseNet169, and VGG16. The best models were InceptionV3 and DenseNet169; the results of InceptionV3 for recall, precision, accuracy, and F1 score were 1, 0.81, 0.85, and 0.9, respectively, and the corresponding results of DenseNet169 were 0.92, 0.86, 0.85, and 0.89, respectively. Automated detection of TMJDD from sagittal MRI images is a promising technique that involves using deep learning neural networks. It can be used to support clinicians in diagnosing patients as having TMJDD.

Temporomandibular joint segmentation in MRI images using deep learning

OBJECTIVES

Temporomandibular joint (TMJ) internal derangements (ID) represent the most prevalent temporomandibular joint disorder (TMD) in the population and its diagnosis typically relies on magnetic resonance imaging (MRI). TMJ articular discs in MRIs usually suffer from low resolution and contrast, and it is difficult to identify them. In this study, we applied two convolutional neural networks (CNN) to delineate mandibular condyle, articular eminence, and TMJ disc in MRI images.

METHODS

The models were trained on MRI images from 100 patients and validated on images from 40 patients using 2D slices and 3D volume as input, respectively. Data augmentation and five-fold cross-validation scheme were applied to further regularize the models. The accuracy of the models was then compared with four raters having different expertise in reading TMJ-MRI images to evaluate the performance of the models.

RESULTS

Both models performed well in segmenting the three anatomical structures. A Dice coefficient of about 0.7 for the articular disc, more than 0.9 for the mandibular condyle, and Hausdorff distance of about 2mm for the articular eminence were achieved in both models. The models reached near-expert performance for the segmentation of TMJ articular disc and performed close to the expert in the segmentation of mandibular condyle and articular eminence. They also surpassed non-experts in segmenting the three anatomical structures.

CONCLUSION

This study demonstrated that CNN-based segmentation models can be a reliable tool to assist clinicians identifying key anatomy on TMJ-MRIs. The approach also paves the way for automatic diagnosis of TMD.

CLINICAL SIGNIFICANCE

Accurately locating the articular disc is the hardest and most crucial step in the interpretation of TMJ-MRIs and consequently in the diagnosis of TMJ-ID. Automated software that assists in locating the articular disc and its surrounding structures would improve the reliability of TMJ-MRI interpretation, save time and assist in reader training. It will also serve as a foundation for additional automated analysis of pathology in TMJ structures to aid in TMD diagnosis.

Deep negative volume segmentation

Clinical examination of three-dimensional image data of compound anatomical objects, such as complex joints, remains a tedious process, demanding the time and the expertise of physicians. For instance, automation of the segmentation task of the TMJ (temporomandibular joint) has been hindered by its compound three-dimensional shape, multiple overlaid textures, an abundance of surrounding irregularities in the skull, and a virtually omnidirectional range of the jaw's motion-all of which extend the manual annotation process to more than an hour per patient. To address the challenge, we invent a new workflow for the 3D segmentation task: namely, we propose to segment empty spaces between all the tissues surrounding the object-the so-called negative volume segmentation. Our approach is an end-to-end pipeline that comprises a V-Net for bone segmentation, a 3D volume construction by inflation of the reconstructed bone head in all directions along the normal vector to its mesh faces. Eventually confined within the skull bones, the inflated surface occupies the entire "negative" space in the joint, effectively providing a geometrical/topological metric of the joint's health. We validate the idea on the CT scans in a 50-patient dataset, annotated by experts in maxillofacial medicine, quantitatively compare the asymmetry given the left and the right negative volumes, and automate the entire framework for clinical adoption.

Influence of post type on periapical status: a prospective study in a Brazilian population

OBJECTIVES

This prospective study assessed the effect of post type used to restore endodontically treated teeth in the onset, progression, and remission of periapical lesions.

MATERIALS AND METHODS

One hundred and forty teeth (92 patients) were endodontically treated and received a glass fiber post or a cast metal post and a final restoration at a University Clinic by undergraduate students. All patients were followed up for a mean period of 5.1 ± 2.2 years. Periapical Index (PAI) was used for endodontic assessment. Two calibrated and blind examiners assessed the radiographs. The longevity of the endodontic treatment was analyzed using Kaplan-Meier statistics.

RESULTS

Of the included teeth, 67.1% received glass fiber posts while 32.9% received cast metal posts. There were 4 endodontic failures, two glass fiber posts with a PAI = 3 in the baseline and PAI = 4 in the last follow-up, and one PAI = 4 in baseline and last follow-up. One cast metal post-failure was PAI = 4 in the baseline and the last follow-up. After 9.4 years, the overall success rate of the endodontic treatment was 97.1% (p = 0.7).

CONCLUSIONS

The tested posts presented similar endodontic healing. Precautions taken during endodontic therapy, post cementation, and final restoration are more likely to be responsible for the success of endodontic treatment rather than a specific type of post. Clinical relevance The type of post is not related to the success of the endodontic treatment.

Semi-automated three-dimensional volumetric evaluation of mandibular condyles

OBJECTIVES

The aim of this study is to research the mandibular condyle volumes of the Turkish subpopulation by sex, age, laterality, and posterior occlusal support, to provide volumetric data for young and old patient groups.

METHODS

The CBCT images of 690 condyles from 345 patients (165 females and 180 males) were assessed. Patients aged 18-25 years were chosen for the younger group, and 45-70 years for the older group. The dental statuses of the older patient group were divided into three categories, based on the Eichner index. All the CBCT images were transferred to the three-dimensional volumetric analysis software, ITK-Snap (Penn Image Computing and Science Laboratory (PICSL) at the University of Pennsylvania and Scientific Computing and Imaging Institute (SCI) at the University of Utah) and analyzed with sagittal, coronal, and axial sections. Mandibular condyles were defined using semi-automatic segmentation, then manual segmentation was performed to ensure accuracy. Analyses were performed using MedCalc statistical software. The p value < 0.05 was considered statistically significant.

RESULTS

The mean right condyle volume for the whole sample (n = 345) was 1678.8 mm³ and the left condyle volume was 1661.3 mm³. Males had a larger condyle volume than females in both the younger and older patient groups (p = 0.035, p < 0.01, respectively). The Eichner index did not correlate significantly with condylar volume in the older patient group (p = 0.134, p = 0.122).

CONCLUSION

There were significant differences between the volumes of mandibular condyles for different sex, while there were no significant differences in relation to age, laterality, and posterior occlusal support.

Temporomandibular joint morphology does not influence the presence of arthralgia in patients with disk displacement with reduction: a magnetic resonance imaging-based study

OBJECTIVE

The aim of this study was to compare, by using magnetic resonance imaging (MRI), temporomandibular joint (TMJ) morphology between patients with disk displacement with reduction (DDWR) with or without arthralgia and a control group and to identify which factors are associated with the concomitant presence of arthralgia in DDWR patients.

STUDY DESIGN

In this investigation, 36 TMJ MRIs were divided into 3 groups. Group 1 (n = 12) comprised patients with DDWR and arthralgia; group 2 (n = 12) comprised patients with DDWR without arthralgia; and group 3 (n = 12) was the control group. Disk and mandibular condyle morphologies; articular eminence morphology and inclination; size of the mandibular fossa; joint space size; joint effusion; bone marrow of the mandibular condyle; and the relative signal intensity of retrodiscal tissue were evaluated.

RESULTS

Fisher's exact test and 1-way analysis of variance (ANOVA) revealed no significant differences (P > .05) between groups for any variable. Logistic regression analysis showed that no anatomic variables were related to the concomitant presence of arthralgia in patients with DDWR (P > .05).

CONCLUSIONS

As evaluated on MRI scans, no significant differences in the anatomic characteristics of the TMJ were detected between DDWR patients with or without concomitant arthralgia and the control group. There were no factors associated with the concomitant presence of arthralgia in patients with DDWR.

Subjective analysis of the application of enhancement filters on magnetic resonance imaging of the temporomandibular joint

OBJECTIVE

The aim of this study was to investigate the effect of enhancement filters on magnetic resonance imaging (MRI) of the temporomandibular joint (TMJ).

STUDY DESIGN

In total, 66 MRI scans of the TMJ were analyzed without filtration and with the application of 2 filters: Sharpen 1 and Sharpen 2 (OnDemand software). Two dentomaxillofacial radiologists examined the original and filtered images individually. Intra- and interobserver concordance was measured by using generalized estimating equations. The observers evaluated the subjective image quality and the visibility of 3 components of the TMJ: disk, condyle, and articular eminence. The images were ranked on a 4-point scale, from poor to excellent. The image quality of all filtered images was compared by using the χ² test and Bonferroni correction for multiple comparisons.

RESULTS

Intra- and interobserver concordance was good. The images filtered with Sharpen 1 and Sharpen 2 provided better definition of the structures compared with nonfiltered images, providing the highest scores for subjective image quality for all structures (P < .0001).

CONCLUSIONS

The use of enhancement filters led to improved subjective quality and may improve the diagnostic efficacy of MRI in TMJ evaluation.

Three-Dimensional Volume Imaging to Increase the Accuracy of Surgical Management in a Case of Recurrent Chordoma of the Clivus

Patient: Male, 53

Final Diagnosis: Clivus chordoma

Symptoms: Pain the eye

Medication: —

Clinical Procedure: —

Specialty: Radiology