AI-enabled Body Composition Biomarkers at Post-Mortem CT for Enriching Autopsy: Analysis of a Large Decedent Cohort

Authors

• Max V. Golden, Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, Wisconsin, 53792, USA. mgolden3@wisc.edu.
• Matthew H. Lee, Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, Wisconsin, 53792, USA.
• John W. Garrett, Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, Wisconsin, 53792, USA.
• Shamsi Daneshvari Berry, Department of Biomedical Informatics, Western Michigan University, 1000 Oakland Dr., Kalamazoo, Michigan, 49008, USA.
• Nicollette Appel, Department of Anthropology, University of New Mexico, 1 University of New Mexico, Albuquerque, New Mexico, 87131, USA.
• Ronald M. Summers, Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Maryland, Bethesda, USA.
• Heather JH Edgar, Department of Anthropology, University of New Mexico, 1 University of New Mexico, Albuquerque, New Mexico, 87131, USA.
• Perry J. Pickhardt, Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, Wisconsin, 53792, USA. ppickhardt2@uwhealth.org.

Document Type

Article

Publication Date

10-1-2025

Abstract

OBJECTIVE: To correlate fully-automated PMCT-based body composition measures with causes of death and comorbidities.

MATERIALS AND METHODS: Retrospective study of New Mexico Decedent Image Database (NMDID) with non-contrast PMCT scans between 2010 and 2017. Automated pipeline of AI-driven algorithms for quantifying skeletal muscle, subcutaneous/visceral fat, and aortic calcification from the abdominal component of PMCT scans was used. Scans with more than minimal decomposition were excluded. Cause of death was categorized as "acute" or "chronic." A predetermined model derived CT-based "biological age."

RESULTS: 6638 decedents (mean age, 50±18 [SD]; 74% male) comprised the final cohort. 80% of deaths were classified as "acute," 10% as "chronic," and 10% "uncertain." Muscle density (HU) and area at the L3 lumbar level were higher in the "acute" versus "chronic" group (26 HU vs. 18 HU, p <  0.001; 192 cm

CONCLUSION: Fully-automated quantitative PMCT-based tissue biomarkers correlate with the temporal nature of death and chronic co-morbidities, supporting their use for enhancing autopsies.

Recommended Citation

Golden MV, Lee MH, Garrett JW, Berry SD, Appel N, Summers RM, Edgar HJH, Pickhardt PJ. AI-enabled body composition biomarkers at post-mortem CT for enriching autopsy: analysis of a large decedent cohort. Abdom Radiol (NY). 2025 Oct;50(10):5047-5058. doi: 10.1007/s00261-025-04878-z. Epub 2025 Mar 18. PMID: 40100280.