EUVIMEDEUVIMED entdecken
Open Access

A novel skeletal muscle quantitative method and deep learning‐based sarcopenia diagnosis for cervical cancer patients treated with radiotherapy

Zhe Wu, Lihua Deng, Wanyang Wu, Bin Zeng, Cheng Xu, Li Liu, Mujun Liu, Yi Wu

Medical Physics · 2025

DOI: 10.1002/mp.17791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Zhe Wu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), Ch…. Hauptthemen laut MEDLINE: Uterine Cervical Neoplasms, Sarcopenia, Deep Learning, Muscle, Skeletal. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Chongqing Science and Technology Talent Project, Chongqing key research and development program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Sarcopenia is associated with decreased survival in cervical cancer patients treated with radiotherapy. Cone‐beam computed tomography (CBCT) was widely used in image‐guided radiotherapy. Sarcopenia is assessed by the skeletal muscle index (SMI) of third lumbar vertebra (L3). Whereas, L3 is usually not included on the cervical cancer radiotherapy CBCT images.

Purpose

We aimed to explore the usefulness of CBCT for evaluating SMI and deep learning (DL)‐based automatic segmentation and sarcopenia diagnosis for cervical cancer radiotherapy patients. We evaluated the SMI through fifth lumbar vertebra (L5).

Methods

First, L3, L5 skeletal muscle area (SMA) were measured on CT and CBCT. The agreement of L5 skeletal muscle segmentation on CBCT was evaluated using the intraclass correlation coefficient (ICC). The relationships between L5‐SMI CT and L3‐SMI CT , L5‐SMI CBCT were established and assessed by Pearson analysis, Bland‐Altman plots. Second, the consequent CBCT images of 248 cervical cancer radiotherapy patients with whole L5 were collected as DL‐based automatic segmentation. An independent external validation dataset was used. We proposed an end‐to‐end anatomical distance‐guided dual branch feature fusion network to segment L5 skeletal muscle on CBCT images. The automatic segmentation results were used for sarcopenia diagnosis evaluation.

Results

The ICC values were greater than 0.95. The Pearson correlation coefficients (PCC) between L5‐SMI CT and L3‐SMI CT is 0.894. The PCC between L5‐SMI CT and L5‐SMI CBCT is 0.917. The L3‐SMI CT could be estimated through L5‐SMI CBCT by a linear regression equation. The adjusted R 2 values were greater than 0.7. The dice similarity coefficient of automatic segmentation is 87.09%. Our proposed DL network predicted sarcopenia with 84.38% accuracy and 85.71% F1‐score. In external validation dataset, the sarcopenia diagnosis accuracy and F1‐score are 80% and 82.61%, respectively.

Conclusion

The SMI quantitative measurement using CBCT for cervical cancer patients is feasible. And the DL network has the potential to assist in the sarcopenia diagnosis using CBCT images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Uterine Cervical NeoplasmsSarcopeniaDeep LearningMuscle, SkeletalImage Processing, Computer-AssistedHumansFemaleCone-Beam Computed TomographyMiddle AgedRadiotherapy, Image-GuidedAgedAdult

Stichwörter der Autor:innen

automatic segmentationcervical cancer radiotherapycone‐beam computed tomographydeep learningsarcopeniaskeletal muscle index

Autor:innen und Institutionen

  • Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), Chongqing, China.
  • Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, China.
  • Department of Radiation Oncology, Zigong First People's Hospital, Sichuan, China.
  • School of Computer and Communication Engineering, Northeastern University at Qinhuangdao, Qinhuangdao, China.
  • Department of Radiotherapy, Luhe Hospital, Beijing, China.

Förderung

  • National Natural Science Foundation of China
  • Chongqing Science and Technology Talent Project
  • Chongqing key research and development program
  • Chongqing Natural Science Foundation
  • Zigong Key Science and Technology Plan (Collaborative Innovation Project of Zigong Academy of Medical Sciences)

Zitieren

APA

Wu, Z., Deng, L., Wu, W., Zeng, B., Xu, C., Liu, L., Liu, M., & Wu, Y. (2025). A novel skeletal muscle quantitative method and deep learning‐based sarcopenia diagnosis for cervical cancer patients treated with radiotherapy. Medical Physics. https://doi.org/10.1002/mp.17791

Vancouver

Wu Z, Deng L, Wu W, Zeng B, Xu C, Liu L, et al. A novel skeletal muscle quantitative method and deep learning‐based sarcopenia diagnosis for cervical cancer patients treated with radiotherapy. Medical Physics. 2025. doi:10.1002/mp.17791

BibTeX
@article{Wu2025,
  author = {Wu, Zhe and Deng, Lihua and Wu, Wanyang and Zeng, Bin and Xu, Cheng and Liu, Li and Liu, Mujun and Wu, Yi},
  title = {A novel skeletal muscle quantitative method and deep learning‐based sarcopenia diagnosis for cervical cancer patients treated with radiotherapy},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.17791}
}
Kostenlos starten →