Deep-Learning AI can Assess Sarcopenia in Chest and Abdominal CT Scans

Led by Dr. Perry Pickhardt, a team of researchers using a previously validated, fully automated AI model has found that muscle-mass measurements at the L1 and L3 vertebra levels performed similarly in assessing sarcopenia and predicting hip fracture and death. These findings open up the ability to assess sarcopenia using a chest CT scan in addition to abdominal scans.

The retrospective study of low-dose abdominal CT scans of 9,223 asymptomatic patients found “[a]utomated CT-based measurements of muscle attenuation for myosteatosis at the L1 level compare favorably with previously-established L3 level measurements and clinical risk scores for predicting hip fractures and death. Assessment for myopenia was less predictive of outcomes at both levels.” Previously-established L3 level measurements are considered the gold standard for evaluating sarcopenia.

The clinical impact, say the authors, is potentially significant. “Alternative use of the L1 rather than L3 level for CT-based muscle measurements allows sarcopenia assessment using both chest and abdominal CT scans, greatly increasing the potential yield of opportunistic CT screening.”

Sources:

Perry J. Pickhardt, Alberto A. Perez, John W. Garrett, Peter M. Graffy, Ryan Zea, and Ronald M. Summers. Automated Deep Learning Tool for Sarcopenia Assessment on CT: L1 Versus L3 Vertebral Level Muscle Measurements for Opportunistic Prediction of Adverse Clinical Outcomes Published online August 18, 2021, American Journal of Roentgenology Accessed August 30, 2021, at https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=133275

Ridley, Erik L. “AI can assess sarcopenia on chest and abdominal CT exams.” Published August 19, 2021, AuntMinnie.com Accessed August 20, 2021, at https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=133275