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

Ryakhovsky A.N.

Central Research Institute of Dentistry and Maxillofacial Surgery

ORCID: 0000-0002-0308-126X

Ryakhovsky S.A.

«Avantis» dental clinic

ORCID: 0000-0002-6031-5632

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

Authors:

Ryakhovsky A.N., Ryakhovsky S.A.

More about the authors

Journal: Stomatology. 2024;103(2): 56‑60

DOI: 10.17116/stomat202410302156

Downloaded: 2

Contact the author

Table of contents

To cite this article:

Ryakhovsky AN, Ryakhovsky SA. Comparative evaluation of the accuracy of 3D TMJ analysis performed by different methods of processing computed tomograms. Stomatology. 2024;103(2):56‑60. (In Russ.)
https://doi.org/10.17116/stomat202410302156

Close metadata

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.

Keywords:

3D TMJ analysis

CT segmentation using artificial intelligence

Authors:

Ryakhovsky A.N.

Central Research Institute of Dentistry and Maxillofacial Surgery

ORCID: 0000-0002-0308-126X

Ryakhovsky S.A.

«Avantis» dental clinic

ORCID: 0000-0002-6031-5632

Received:

12.06.2023

Accepted:

31.08.2023

List of references:

Caruso S, Storti E, Nota A, Ehsani S, Gatto R. Temporomandibular Joint Anatomy Assessed by CBCT Images. BioMed Res Int. 2017;1(10):2916953. https://doi.org/10.1155/2017/2916953
De Kanter RJAM, Battistuzzi PGFCM, Truin G. Temporomandibular Disorders: «Occlusion» Matters! J Pain Res Manag. 2018;1:13. https://doi.org/10.1155/2018/8746858.
Kalladka M, Young A, Thomas D, Heir G, Quek S, Khan J. The relation of temporomandibular disorders and dental occlusion: a narrative review. Quintessence Int. 2022;53(5):450-459. https://doi.org/10.3290/j.qi.b2793201.
Alkhader M, Kuribayashi A, Ohbayashi N, Nakamura S, Kurabayashi T. Usefulness of cone beam computed tomography in temporomandibular joints with soft tissue pathology. Dentomaxillofac Radiol. 2010;39(6):343-348. https://doi.org/10.1259/dmfr/76385066.
Al-Saleh MAQ, Alsufyani NA, Saltaji H, Jaremko JL. Major MRI and CBCT image registration of temporomandibular joint: a systematic review. J Otolaryngol. Head Neck Surg. 2016;45(1):30. https://doi.org/10.1186/s40463-016-0144-4
Honda KT, Larheim A, Johannessen S, Arai Y, Shinoda K, Westesson PL, Honda K. Oral Surgery, Ortho cubic super-high resolution computed tomography: A new radiographic technique with application to the temporomandibular joint. Oral Med, Oral Pathol, Oral Radiol Endodontol. 2001; 91(2):239-243. https://doi.org/10.1067/moe.2001.111942.
Ryakhovsky AN, Vykhodtseva MA. Obosnovanie metodiki 3D-analiza visochno-nizhnechelyustnogo sustava po dannym komp’yuternoi tomografii [Validation of the technique of TMJ 3D analysis based on computer tomography. Stomatologiya. 2022;101(1):23-32. https://doi.org/10.17116/stomat202210101123
Le C, Deleat-Besson R, Prieto J, Brosset S, Dumont M, Zhang W, Cevidanes L, Bianchi J, Ruellas A, Gomes L, Gurgel M, Massaro C. Automatic Segmentation of Mandibular Ramus and Condyles. Annu Int Conf IEEE Eng Med Biol Soc. 2021;2021:2952-2955. https://doi.org/10.1109/EMBC46164.2021.9630727.
Li M, Punithakumar K, Major PW, HLeabc L, Pacheco-Pereira C, Punithakumarb K, RKaipatura N, Nebbea B, LJaremkob J, Almeidaa FT. Temporomandibular joint segmentation in MRI images using deep learning. J Dent. 2022;127:104345 https://doi.org/10.1016/j.jdent.2022.104345.
Verhelst PJ, Smolders A, Beznik T, Verhelst PJ, Meewis J, Van Gerven A, Williams H, Politis C, Jacobs R. Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography. J Dent. 2021; 114:103786. https://doi.org/10.1016/j.jdent.2021.103786.
Duman ŞB, Syed AZ, Celik Ozen D, Bayrakdar İŞ, Salehi HS, Abdelkarim A, Celik Ö, Eser G, Altun O, Orhan K. Convolutional Neural Network Performance for Sella Turcica Segmentation and Classification Using CBCT Images. Diagnostics (Basel). 2022;12(9):2244. https://doi.org/13390/diagnostics12092244.
Liang B, Wei Rl, Zhang J, Li Y, Yang T, Xu S, Zhang K, Xia W, Guo B, Liu B, Zhou F, Wu Q, Dai J Liang B. Applying pytorch toolkit to plan optimization for circular cone based robotic radiotherapy. Radiat Oncol. 2022; 17(1):82. https://doi.org/10.1186/s13014-022-02045-y
Novac OC, Chirodea MC, Novac CM, BizonN, Oproescu M, Stan OP, Gordan KT. Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network. Sensors (Basel). 2022;22(22):872. https://doi.org/10.3390/s22228872.
Zimmer L, Lindauer M, Hutter F. Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL. IEEE Trans Pattern Anal Mach Intell. 2021;43(9):3079-3090. https://doi.org/10.1109/TPAMI.2021.3067763

Close metadata