Feasibility and Reliability of an Automated Muscle Segmentation Pipeline Linking Thoracic Supine Kyphosis and Trunk Muscle–Fat% on CT
Tomography · 23.04.2026 · 12 (5) · 59
DOI: 10.3390/tomography12050059 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tomography, online erschienen am 23.04.2026. Verfasst von Tianxi Liang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Kyphosis, Muscle, Skeletal, Adipose Tissue. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
As muscles atrophy, myocytes are replaced by fat and muscle strength diminishes, increasing thoracic supine kyphosis. Here, we investigate the relationship between muscle fat percentage (muscle–fat%) and thoracic supine kyphosis on CT.
Methods
Thoracic Cobb angle was measured on supine CT scans from the AtlasDataset by four observers (n=533). Nine muscles were manually labeled on 100 scans (manual cohort). An nnU-Net model was trained on 80 cases with internal validation on 20 cases, then applied to segment the remaining 433 AtlasDataset scans (automated cohort). External segmentation benchmarking was performed on 30 cases from a separate open-source dataset. Associations between supine thoracic curvature and muscle–fat% were evaluated only in AtlasDataset.
Results
Manual supine thoracic Cobb angle measurements demonstrated good inter-observer reproducibility (ICC(2,k) = 0.98) with a mean across-rater per-case SD of 3.4°. The nnU-Net achieved Dice scores >0.93 across all nine muscle groups on internal and external segmentation benchmarking. For both manual and automated cohorts, thoracic supine kyphosis correlated with muscle–fat% in the paraspinal (r = 0.35, 0.42), quadratus lumborum (r = 0.29, 0.33), vastus (r = 0.38, 0.32), psoas (r = 0.21, 0.23) and latissimus dorsi (r = 0.21, 0.17) muscles.
Conclusions
Automated measurement of trunk muscle–fat% provides a reproducible imaging biomarker correlated with thoracic supine kyphosis on CT. Identifying fatty atrophy of core muscles may help identify potential targets for interventions in hyperkyphotic patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA.
- Independent Researcher, Zhitong Zou, Brighton, BN2 1AD, UK.
- Independent Researcher, Aida Y. Prince, Brighton BN2 1AD, UK.
- Graduate School of Arts and Sciences, Georgetown University, Washington, DC 20057, USA.
- Department of Radiology, Columbia University Vagelos College of Physicians and Surgeons, New York, NY 10032, USA.
ORCID-Profile: Tianxi Liang, Rian Atri, Sarah Joseph, Yiyuan Shao, Zhitong Zou, Adrian J Villanueva, Aida Y Prince, Renke Deng, Kurt Teichman, Xinzi He, Martin R Prince
Zitieren
APA
Liang, T., Atri, R., Joseph, S., Shao, Y., Zou, Z., Villanueva, A. J., Prince, A. Y., Deng, R., Teichman, K., He, X., & Prince, M. R. (2026). Feasibility and Reliability of an Automated Muscle Segmentation Pipeline Linking Thoracic Supine Kyphosis and Trunk Muscle–Fat% on CT. Tomography, 12(5), 59. https://doi.org/10.3390/tomography12050059
Vancouver
Liang T, Atri R, Joseph S, Shao Y, Zou Z, Villanueva AJ, et al. Feasibility and Reliability of an Automated Muscle Segmentation Pipeline Linking Thoracic Supine Kyphosis and Trunk Muscle–Fat% on CT. Tomography. 2026;12(5):59. doi:10.3390/tomography12050059
BibTeX
@article{Liang2026,
author = {Liang, Tianxi and Atri, Rian and Joseph, Sarah and Shao, Yiyuan and Zou, Zhitong and Villanueva, Adrian J and Prince, Aida Y and Deng, Renke and Teichman, Kurt and He, Xinzi and Prince, Martin R},
title = {Feasibility and Reliability of an Automated Muscle Segmentation Pipeline Linking Thoracic Supine Kyphosis and Trunk Muscle–Fat% on CT},
journal = {Tomography},
year = {2026},
volume = {12},
number = {5},
pages = {59},
doi = {10.3390/tomography12050059}
}
EUVIMED