Key result
CNN-automated measures of mid-thigh cross-sectional area from MRI were highly accurate compared to manual segmentation and strongly predicted appendicular lean mass and knee extensor strength in obese adults.
Why the study?
To train and test a machine learning model to automatically measure mid-thigh muscle cross-sectional area to provide rapid estimation of appendicular lean mass and predict knee extensor torque in obese adults.
Cohort (n=47)
No
A convolutional neural network can accurately automate the measurement of mid-thigh cross-sectional area from MRI scans to estimate appendicular lean mass and knee extensor strength in obese adults.
Answers are grounded in this paper and cite their sources.
CNN automation of mid-thigh CSA may aid lean mass and strength evaluation in obesity; leaves open clinical adoption pending prospective validation.
Purpose To train and test a machine learning model to automatically measure mid-thigh muscle cross-sectional area (CSA) to provide rapid estimation of appendicular lean mass (ALM) and predict knee extensor torque of obese adults. Methods Obese adults [body mass index (BMI) = 30–40 kg/m 2 , age = 30–50 years] were enrolled for this study. Participants received full-body dual-energy X-ray absorptiometry (DXA), mid-thigh MRI, and completed knee extensor and flexor torque assessments via isokinetic dynamometer. Manual segmentation of mid-thigh CSA was completed for all MRI scans. A convolutional neural network (CNN) was created based on the manual segmentation to develop automated quantification of mid-thigh CSA. Relationships were established between the automated CNN values to the manual CSA segmentation, ALM via DXA, knee extensor, and flexor torque. Results A total of 47 obese patients were enrolled in this study. Agreement between the CNN-automated measures and manual segmentation of mid-thigh CSA was high (>0.90). Automated measures of mid-thigh CSA were strongly related to the leg lean mass ( r = 0.86, p < 0.001) and ALM ( r = 0.87, p < 0.001). Additionally, mid-thigh CSA was strongly related to knee extensor strength ( r = 0.76, p < 0.001) and moderately related to knee flexor strength ( r = 0.48, p = 0.002). Conclusion CNN-measured mid-thigh CSA was accurate compared to the manual segmented values from the mid-thigh. These values were strongly predictive of clinical measures of ALM and knee extensor torque. Mid-thigh MRI may be utilized to accurately estimate clinical measures of lean mass and function in obese adults.
No takes yet. Share an insight, caveat, or question.
Bodkin et al. (2022) conducted a cohort in Obesity (n=47). CNN-automated measurement of mid-thigh cross-sectional area from MRI vs. Manual segmentation and DXA imaging was evaluated on Correlation between CNN-measured mid-thigh cross-sectional area and appendicular lean mass (ALM) (r = 0.87, p=<0.001). CNN-automated measures of mid-thigh cross-sectional area from MRI were highly accurate compared to manual segmentation and strongly predicted appendicular lean mass and knee extensor strength in obese adults.
Synapse has enriched 10 related papers. Consider them for comparative context: