โก Quick Summary
This pilot study explored the use of automated machine learning to analyze MRI images for assessing body composition changes in young females following an 8-week strength training program. The results indicated a significant increase in muscle volume in the intervention group, highlighting the potential of AI in monitoring training responses.
๐ Key Details
- ๐ฉโ๐ฌ Participants: 18 healthy young females
- ๐๏ธโโ๏ธ Intervention: 8-week strength endurance training, twice a week
- ๐ฅ๏ธ Technology: 3D U-Net-based Convolutional Neural Network for MRI analysis
- ๐ Analysis Method: 2 (GROUP [IG vs. CG]) ร 2 (TIME [pre vs. post]) ANOVA
๐ Key Takeaways
- ๐ Muscle Volume Increase: 2.93% in the intervention group (IG) vs. no change in the control group (CG).
- ๐ฆด No Significant Changes: Bone and subcutaneous adipose tissue (SAT) volumes showed no significant differences.
- ๐ค AI Efficacy: The study supports the use of AI for reliable body composition monitoring.
- ๐ฌ Research Implications: Highlights the potential for machine learning in sports science and health monitoring.
- ๐ Study Duration: 8 weeks of training with MRI assessments before and after.
๐ Background
Maintaining a healthy ratio of body fat to muscle mass is crucial for overall health and performance. Excessive body fat is linked to various health risks, making accurate body composition assessment essential. Traditional methods often rely on manual segmentation of structures, which can be time-consuming and prone to error. The advent of machine learning offers a promising alternative for precise and efficient analysis.
๐๏ธ Study
Conducted with 18 healthy young females, this study aimed to evaluate the effectiveness of a novel machine learning approach for analyzing MRI images of the thigh region. Participants were divided into an intervention group (IG) that underwent an 8-week strength training program and a control group (CG) that did not participate in any training. MRI scans were performed before and after the intervention to assess changes in muscle, bone, and SAT volumes.
๐ Results
The analysis revealed a significant interaction effect for muscle volume, with the IG showing a 2.93% increase post-training, while the CG experienced a slight decrease of -0.62%. The statistical analysis (F1,16โ=โ12.80, pโ=โ0.003, ฮทP 2โ=โ0.44) confirmed the robustness of these findings, indicating that the training program effectively enhanced muscle volume in the intervention group.
๐ Impact and Implications
This study underscores the potential of artificial intelligence in the field of sports science and health monitoring. By utilizing machine learning for MRI analysis, researchers can gain valuable insights into training responses and body composition changes. Such advancements could lead to more personalized training programs and improved health outcomes for individuals engaged in strength training and rehabilitation.
๐ฎ Conclusion
The findings from this pilot study highlight the promising role of machine learning in accurately assessing body composition changes due to training interventions. As technology continues to evolve, integrating AI into health and fitness assessments could revolutionize how we monitor and enhance physical performance. Further research is encouraged to explore the broader applications of these technologies in various populations.
๐ฌ Your comments
What are your thoughts on the integration of machine learning in body composition analysis? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
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.
Abstract
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])โรโ2 (TIME [pre-intervention vs. post-intervention]) analysis of variance (ANOVA) with repeated measures for the factor TIME. The results of the ANOVA demonstrate significant TIMEโรโGROUP interaction effects for the muscle volume (F1,16โ=โ12.80, pโ=โ0.003, ฮทP 2โ=โ0.44) with an increase of 2.93% in the IG group and no change in the CG (-0.62%, pโ=โ0.893). 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.
Author: [‘Ramedani S’, ‘Kelesoglu E’, ‘Stutzig N’, ‘Von Tengg-Kobligk H’, ‘Daneshvar Ghorbani K’, ‘Siebert T’]
Journal: Physiol Rep
Citation: Ramedani S, et al. 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. 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. 2025; 13:e70187. doi: 10.14814/phy2.70187