Automatic Segmentation of Mandibular Ramus and Condyles

Automated localization of mandibular landmarks in the construction of mandibular median sagittal plane

OBJECTIVE

To use deep learning to segment the mandible and identify three-dimensional (3D) anatomical landmarks from cone-beam computed tomography (CBCT) images, the planes constructed from the mandibular midline landmarks were compared and analyzed to find the best mandibular midsagittal plane (MMSP).

METHODS

A total of 400 participants were randomly divided into a training group (n = 360) and a validation group (n = 40). Normal individuals were used as the test group (n = 50). The PointRend deep learning mechanism segmented the mandible from CBCT images and accurately identified 27 anatomic landmarks via PoseNet. 3D coordinates of 5 central landmarks and 2 pairs of side landmarks were obtained for the test group. Every 35 combinations of 3 midline landmarks were screened using the template mapping technique. The asymmetry index (AI) was calculated for each of the 35 mirror planes. The template mapping technique plane was used as the reference plane; the top four planes with the smallest AIs were compared through distance, volume difference, and similarity index to find the plane with the fewest errors.

RESULTS

The mandible was segmented automatically in 10 ± 1.5 s with a 0.98 Dice similarity coefficient. The mean landmark localization error for the 27 landmarks was 1.04 ± 0.28 mm. MMSP should use the plane made by B (supramentale), Gn (gnathion), and F (mandibular foramen). The average AI grade was 1.6 (min-max: 0.59-3.61). There was no significant difference in distance or volume (P > 0.05); however, the similarity index was significantly different (P < 0.01).

CONCLUSION

Deep learning can automatically segment the mandible, identify anatomic landmarks, and address medicinal demands in people without mandibular deformities. The most accurate MMSP was the B-Gn-F plane.

[Comparative evaluation of the accuracy of 3D TMJ analysis performed by different methods of processing computed tomograms]

OBJECTIVE

The aim of this study. Comparison of the accuracy of segmentation of TMJ elements in different ways and assessment of the suitability of the data obtained for the diagnosis of TMJ dysfunction.

MATERIALS AND METHODS

To study the segmentation of the bone elements of the TMJ (articular fossa, head of the LF), 60 computed tomograms of the maxillofacial region of patients were randomly selected in various ways (archival material). In group 1, the results of CT processing by AI diagnostics algorithms (Russia) were collected; in group 2, the results of CT processing based on the semi-automatic segmentation method in the Avantis3D program. The results of CT processing by Avantis3D AI algorithms (Russia) with different probability modes - 0.4 and 0.9, respectively, were selected for the third and fourth groups. Visually, the coincidence of the contours of the LF heads and articular pits isolated using different methods with their contours on all possible sections of the original CT itself was evaluated. The time spent on TMJ segmentation according to CT data was determined and compared using the methods described above.

RESULTS

Of the 240 objects, only 7.5% of the cases showed a slight discrepancy between the contours of the original CT in group b1, which was the lowest of all. A slight discrepancy in the TMJ contours to be corrected is characteristic of the semi-automatic method of segmentation by optical density was detected in 50.4% (group 2). The largest percentage of significant errors not subject to correction was noted in the first group, which made it impossible to perform a full 3D analysis of the TMJ, and the smallest in the second and fourth. The magnitude of the error in determining the width of the articular gap in different groups is comparable to the size of one voxel per CT. When segmentation is carried out using AI, the difference between segmented objects is close to zero values. The average time spent on TMJ segmentation in group 1 was 10.2±1.23 seconds, in group 2 - 12.6±1.87 seconds, in groups 3 and 4 - 0.46±0.12 seconds and 0.46±0.13 seconds, respectively.

CONCLUSION

The developed automated method for segmenting TMJ elements using AI is obviously more suitable for practical work, since it requires minimal time, and is almost as accurate as other methods under consideration.

Current Applications of Deep Learning and Radiomics on CT and CBCT for Maxillofacial Diseases

The increasing use of computed tomography (CT) and cone beam computed tomography (CBCT) in oral and maxillofacial imaging has driven the development of deep learning and radiomics applications to assist clinicians in early diagnosis, accurate prognosis prediction, and efficient treatment planning of maxillofacial diseases. This narrative review aimed to provide an up-to-date overview of the current applications of deep learning and radiomics on CT and CBCT for the diagnosis and management of maxillofacial diseases. Based on current evidence, a wide range of deep learning models on CT/CBCT images have been developed for automatic diagnosis, segmentation, and classification of jaw cysts and tumors, cervical lymph node metastasis, salivary gland diseases, temporomandibular (TMJ) disorders, maxillary sinus pathologies, mandibular fractures, and dentomaxillofacial deformities, while CT-/CBCT-derived radiomics applications mainly focused on occult lymph node metastasis in patients with oral cancer, malignant salivary gland tumors, and TMJ osteoarthritis. Most of these models showed high performance, and some of them even outperformed human experts. The models with performance on par with human experts have the potential to serve as clinically practicable tools to achieve the earliest possible diagnosis and treatment, leading to a more precise and personalized approach for the management of maxillofacial diseases. Challenges and issues, including the lack of the generalizability and explainability of deep learning models and the uncertainty in the reproducibility and stability of radiomic features, should be overcome to gain the trust of patients, providers, and healthcare organizers for daily clinical use of these models.