Morphomic Signatures Derived from Computed Tomography Predict Hepatocellular Carcinoma Occurrence in Cirrhotic Patients
- 25 Downloads
Background and Aims
Computed tomography (CT) provides scans of the human body from which digitized features can be extracted. The aim of this study was to examine the role of these digital biomarkers for predicting subsequent occurrence of hepatocellular carcinoma (HCC) in cirrhotic patients.
A cohort of 269 patients with cirrhosis were recruited and prospectively followed for the occurrence of HCC in Taiwan. CT scans were retrospectively retrieved and computationally processed using analytic morphomics. A predictive score was constructed using Cox regression and the generalized iterative modeling method, maximizing the log likelihood of the time to HCC development. An independent cohort of 274 patients from University of Michigan was utilized to examine the predictive validity of this score in a Western population.
Of the 27 digitized features at the 12th thoracic vertebral level, six features were significantly associated with HCC occurrence. Two digitized features (fascia eccentricity and the bone mineral density) were able to stratify patients into high- and low-risk groups with distinct cumulative incidence of HCC in both the training and validation cohorts (P = 0.015 and 0.044, respectively). When the two digitized features were tested in the Michigan cohort, only bone mineral density remained an effective predictor.
Digitized features derived from the CT were effective in predicting subsequent occurrence of HCC in cirrhosis patients. The bone mineral density measured on CT was an effective predictor for patients in both Taiwan and USA.
KeywordsBone mineral density Fascia eccentricity Prognosis Retrospective–prospective design
The authors would like to thank Brian Derstine, Brian Ross, Dr. Gigin Lin, Dr. Ching-Yi Hsieh, Wan-Ru Liang, Yi-Ting Liao, Yi-Wen Li, Chung-Yin Wu, Fang-Yi He, Hui-Chin Chen, Ya-Ming Cheng, Yu-Jean Chen, and Chien-Chih Wang of the liver research center for the excellent technical and administrative assistance.
PZ was partially supported by funding from the US National Institutes of Health (K01 DK106296). GLS was partially funded by U01 CA230669.
Compliance with Ethical Standards
Conflict of interest
SCW and the University of Michigan have a patent on the Morphomics Technique. SCW has equity interest in Applied Morphomics. No commercial funding was utilized for this project.
- 27.Stidham RW, Waljee AK, Day NM, et al. Body fat composition assessment using analytic morphomics predicts infectious complications after bowel resection in Crohnʼs disease. Inflamm Bowel Dis. 2015;1:1306–1313.Google Scholar