Health AI Central
Peer-Reviewed Publication
Comput Biol Med2026;216111944.September 22, 2026Journal Article

SegmentAnyMuscle: A universal muscle segmentation model across different locations in MRI.

Roy Colglazier1, Jisoo Lee2, Haoyu Dong3, Hanxue Gu4, Yaqian Chen4, Joseph Cao1, Zafer Yildiz2, Zhonghao Liu4, Nicholas Konz4, Jichen Yang4, Jikai Zhang4, Yuwen Chen4, Lin Li2, Adrian Camarena5, Maciej A Mazurowski6
1Department of Radiology, Duke University, NC, 27703, USA.
2Department of Biostatistics and Bioinformatics, Duke University, NC, 27703, USA.
3Department of Electrical and Computer Engineering, Duke University, NC, 27703, USA. Electronic address: haoyu.dong151@duke.edu.
4Department of Electrical and Computer Engineering, Duke University, NC, 27703, USA.
5Department of Surgery, Duke University, NC, 27703, USA.
6Department of Radiology, Duke University, NC, 27703, USA; Department of Biostatistics and Bioinformatics, Duke University, NC, 27703, USA; Department of Electrical and Computer Engineering, Duke University, NC, 27703, USA; Department of Computer Science, Duke University, NC, 27703, USA.
PubMed DOI

Abstract

Muscle mass and muscle quality, characterized by intramuscular adiposity and fiber composition, are clinically established biomarkers significantly associated with obesity, sarcopenia, frailty and cardiometabolic disorders. Current muscle quantification efforts are predominantly based on CT, often focusing on single anatomical region such as the L3 vertebral level, due it its relatively standardiz…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.