Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 26.
doi: 10.1007/s00266-025-05066-6. Online ahead of print.

A Fully Automated 3D CT U-Net Framework for Segmentation and Measurement of the Masseter Muscle, Innovatively Incorporating a Self-Supervised Algorithm to Effectively Reduce Sample Size: A Validation Study in East Asian Populations

Xiaohui Qiu  1 , Wenqing Han  2 , Lisheng Wang  3 , Gang Chai  4
Affiliations

A Fully Automated 3D CT U-Net Framework for Segmentation and Measurement of the Masseter Muscle, Innovatively Incorporating a Self-Supervised Algorithm to Effectively Reduce Sample Size: A Validation Study in East Asian Populations

Xiaohui Qiu et al. Aesthetic Plast Surg. .

Abstract

Objective: The segmentation and volume measurement of the masseter muscle play an important role in radiological evaluation. Manual segmentation is considered the gold standard, but it has limited efficiency. This study aims to develop and evaluate a U-Net-based coarse-to-fine learning framework for automated segmentation and volume measurement of the masseter muscle, providing baseline data on muscle characteristics in 840 healthy East Asian volunteers, while introducing a self-supervised algorithm to reduce the sample size required for deep learning.

Method: A database of 840 individuals (253 males, 587 females) with negative head CT scans was utilized. Following G. Power's sample size calculation, 15 cases were randomly chosen for clinical validation. Masseter segmentation was conducted manually in manual group and automatically in Auto-Seg group. The primary endpoint was the masseter muscle volume, while the secondary endpoints included morphological score and runtime, benchmarked against manual segmentation. Reliability tests and paired t tests analyzed intra- and inter-group differences. Additionally, automatic volumetric measurements and asymmetry, calculated as (L - R)/(L±R) × 100%, were evaluated, with the clinical parameter correlation analyzed via Pearson's correlation test.

Results: The volume accuracy of automatic segmentation matched that of manual delineation (P > 0.05), demonstrating equivalence. Manual segmentation's runtime (937.3 ± 95.9 s) significantly surpassed the algorithm's (<1 s, p < 0.001). Among 840 patients, masseter asymmetry was 4.6% ± 4.6%, with volumes of (35.5 ± 9.6) cm3 for adult males and (26.6 ± 7.5) cm3 for adult females.

Conclusion: The U-Net-based algorithm demonstrates high concordance with manual segmentation in delineating the masseter muscle, establishing it as a reliable and efficient tool for CT-based assessments in healthy East Asian populations.

Level of evidence ii: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Keywords: Automatic segmentation; Convolutional neural networks (ConvNets); Masseter muscle; U-Net.

PubMed Disclaimer

Conflict of interest statement

Declarations. Conflict of interest: We declare that we have no financial or personal relationships with other individuals or organizations that could improperly influence our work. Furthermore, we have no professional or other personal interests in any product, service, and/or company that could be construed as influencing the position presented in or the review of the manuscript titled"A fully automated 3D CT U-Net framework for segmentation and measurement of the masseter muscle, innovatively incorporating a self-supervised algorithm to effectively reduce sample size: A validation study in East Asian populations." Ethical Approval: This study was approved by the Ethics Committee of The Ninth People’s Hospital Affiliated to Shanghai Jiao Tong University, with the ethical approval number: K23687. This study is a retrospective study, and informed consent is not required for this type of research.

Similar articles

See all similar articles

References

    1. Seltzer SE, Wang AM. Modern imaging of the masseter muscle: Normal anatomy and pathosis on CT and MRI. Oral Surgery, Oral Medicine, Oral Pathology. 1987;63(5):622–9. - PubMed
    1. Lin CS, Liu LK, Lee WJ, Peng LN, Lin CP, Lee SY, Chen LK. Low masseter muscle mass is associated with frailty in community-dwelling older adults: I-Lan Longitudinal Aging Study. Exp Gerontol. 2022;163:111777. - PubMed
    1. Pan Y, Wang Y, Li G, Chen S, Xu T. Validity and reliability of masseter muscles segmentation from the transverse sections of Cone-Beam CT scans compared with MRI scans. Int J Comput Assist Radiol Surg. 2022;17(4):751–9. - PubMed
    1. Hartstone-Rose A, Perry J, Morrow CJ. Bite force estimation and the fiber architecture of felid masticatory muscles. Anatom Record Adv Integrative Anatomy Evolutionary Biol. 2012;295(8):1336–51.
    1. Chollet F. Xception: Deep Learning with depthwise separable convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.

LinkOut - more resources