EUVIMEDOpdag EUVIMED
Randomisierte kontrollierte StudieOpen access · CC BY 4.0

Quantification of training‐induced alterations in body composition via automated machine learning analysis of MRI images in the thigh region: A pilot study in young females

Saied Ramedani iD, Ebru Kelesoglu, Norman Stutzig, Hendrik Von Tengg-Kobligk, Keivan Daneshvar Ghorbani, Tobias Siebert

Physiological Reports · 2025

DOI: 10.14814/phy2.70187 ↗

At a glance

Randomisierte kontrollierte Studie in Physiological Reports, 2025. Written by Saied Ramedani and 5 co-authors. Institution: Graduate School of Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland. Major MEDLINE topics: Magnetic Resonance Imaging, Body Composition, Machine Learning, Thigh. Cited 4 times so far (Crossref); 39 references. The full text is freely available (open access, CC BY 4.0). Funded by: Deutsche Forschungsgemeinschaft (DFG), Prokando.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The maintenance of an appropriate ratio of body fat to muscle mass is essential for the preservation of health and performance, as excessive body fat is associated with an increased risk of various diseases. Accurate body composition assessment requires precise segmentation of structures. In this study we developed a novel automatic machine learning approach for volumetric segmentation and quantitative assessment of MRI volumes and investigated the efficacy of using a machine learning algorithm to assess muscle, subcutaneous adipose tissue (SAT), and bone volume of the thigh before and after a strength training. Eighteen healthy, young, female volunteers were randomly allocated to two groups: intervention group (IG) and control group (CG). The IG group followed an 8‐week strength endurance training plan that was conducted two times per week. Before and after the training, the subjects of both groups underwent MRI scanning. The evaluation of the image data was performed by a machine learning system which is based on a 3D U‐Net‐based Convolutional Neural Network. The volumes of muscle, bone, and SAT were each examined using a 2 (GROUP [IG vs. CG]) × 2 (TIME [pre‐intervention vs. post‐intervention]) analysis of variance (ANOVA) with repeated measures for the factor TIME. The results of the ANOVA demonstrate significant TIME × GROUP interaction effects for the muscle volume ( F 1,16 = 12.80, p = 0.003, η P 2 = 0.44) with an increase of 2.93% in the IG group and no change in the CG (−0.62%, p = 0.893). There were no significant changes in bone or SAT volume between the groups. This study supports the use of artificial intelligence systems to analyze MRI images as a reliable tool for monitoring training responses on body composition.

Subjects

MeSH terms (MEDLINE)

Magnetic Resonance ImagingBody CompositionMachine LearningThighResistance TrainingHumansFemalePilot ProjectsYoung AdultAdultMuscle, SkeletalSubcutaneous Fat

Author keywords

body compositiondeep learningmachine learningmagnetic resonance imagingmusculoskeletal systemsports medicine

Authors and institutions

  • Graduate School of Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland.
  • Department of Diagnostic, Interventional and Pediatric Radiology, Bern University Hospital, University of Bern, Bern, Switzerland.
  • Prokando GmbH, Maybachstraße 27, Remseck am Neckar, 71686, Germany.
  • Motion and Exercise Science, University of Stuttgart, Stuttgart, Germany.
  • Stuttgart Center of Simulation Science, University of Stuttgart, Stuttgart, Germany.

ORCID profiles: Saied Ramedani

Funding

  • Deutsche Forschungsgemeinschaft (DFG)
  • Prokando

Cite

APA

Ramedani, S., Kelesoglu, E., Stutzig, N., Von Tengg-Kobligk, H., Daneshvar Ghorbani, K., & Siebert, T. (2025). Quantification of training‐induced alterations in body composition via automated machine learning analysis of MRI images in the thigh region: A pilot study in young females. Physiological Reports. https://doi.org/10.14814/phy2.70187

Vancouver

Ramedani S, Kelesoglu E, Stutzig N, Von Tengg-Kobligk H, Daneshvar Ghorbani K, Siebert T. Quantification of training‐induced alterations in body composition via automated machine learning analysis of MRI images in the thigh region: A pilot study in young females. Physiological Reports. 2025. doi:10.14814/phy2.70187

BibTeX
@article{Ramedani2025,
  author = {Ramedani, Saied and Kelesoglu, Ebru and Stutzig, Norman and Von Tengg-Kobligk, Hendrik and Daneshvar Ghorbani, Keivan and Siebert, Tobias},
  title = {Quantification of training‐induced alterations in body composition via automated machine learning analysis of MRI images in the thigh region: A pilot study in young females},
  journal = {Physiological Reports},
  year = {2025},
  doi = {10.14814/phy2.70187}
}
Start for free →