Radiomics from multi-vendor MRI for muscle strength prediction
In an abstract of 141 adults scanned with Dixon MRI across three cohorts, radiomics features added predictive value for muscle strength beyond cross-sectional area, especially when older adults were included. [1]
Automatic summary · not editorially reviewed
The key findings
Dixon MRI from 141 adults in three cohorts (82 healthy on Philips, 24 healthy on GE, 35 older on Siemens) was used to predict muscle strength. [1]
Fat-fraction radiomics performed best in the full combined cohort (R²=0.64 versus 0.42 for CSA alone). [1]
The authors suggest radiomics may capture muscle quality beyond size, potentially helping future sarcopenia screening, but this is not a demonstrated clinical benefit. [1]
The source at a glance
- Study type / format
- Abstract of a multi-center, multi-scanner MRI prediction study
- Population / context
- 141 adults across three cohorts: 82 healthy (Philips, 22–94 years), 24 healthy (GE, 30–79 years) and 35 older adults (Siemens, 70–91 years), including healthy, pre-frail and sarcopenic participants.
- Summary based on
- Study abstract
- Publication status
- Preprint · peer-review status not confirmed
- Original publication
- October 7, 2026
Strength prediction across three MRI cohorts
The abstract describes a study predicting muscle strength from multi-center, multi-scanner Dixon MRI in 141 adults. Three cohorts were scanned: 82 healthy adults on Philips scanners (22–94 years), 24 healthy adults on GE scanners (30–79 years) and 35 older adults on Siemens scanners (70–91 years), including healthy, pre-frail and sarcopenic participants. Muscle cross-sectional area (CSA) was a strong predictor of strength in the healthy cohorts.
Supporting source [1]
Fat-fraction radiomics best in combined cohort
Radiomics features provided additional value when older adults were included. Fat-fraction radiomics showed the strongest and most consistent performance across cohort combinations, with the best result in the full combined cohort (R²=0.64 versus 0.42 for CSA alone). Water-only radiomics also retained predictive value, though generally less strongly. The most informative features reflected muscle size, signal magnitude and internal heterogeneity; SHAP analysis linked higher intramuscular heterogeneity to reduced strength.
Supporting source [1]
Suggested use and abstract-only limits
The authors suggest that radiomics can capture muscle quality features affecting force-generating capacity beyond size alone, particularly in older adults, and support automated MRI-based assessment of muscle composition and function, potentially helping future sarcopenia screening and functional risk stratification. These are suggestions, not demonstrated clinical benefits. This explainer is based only on the abstract; the full text was not reviewed, so study design details, follow-up and limitations beyond those stated are unknown.
Supporting source [1]
How to interpret this
Abstract only; the full text was not reviewed. Study design, follow-up and further limitations beyond those stated are unknown. The suggested screening and risk-stratification uses are proposals, not demonstrated benefits.
Based on the study abstract; the full paper, tables and supplementary data were not reviewed.
Source & supporting passages
Cigdem O, Montin E, Ghouth SB, Chaudhari A, Cameron D, Bergeron CM, Bergeron J, Ferrucci L, Gold GE, Lattanzi R, Deniz CM, Mazzoli V. · europepmc.org · October 7, 2026