A study evaluated the software program Automatic Body composition Analyzer using Computed tomography image Segmentation (ABACS) to assess its efficacy at measuring body composition on computed tomography (CT) against manual segmentation in bladder cancer. The results were published in the European Journal of Radiology.

In this retrospective analysis, researchers analyzed 285 patients treated for bladder cancer at Duke University from 1996 to 2017. Abdominal CT images were measured manually at L3-level using Slice-O-Matic, while automated segmentation also was measured at L3 using ABACS. The measures of interest were skeletal muscle area, subcutaneous adipose tissue area, and visceral adipose tissue area. Performance between manual and automated segmentation was analyzed using the Pearson product-moment correlation coefficient, the interclass correlation coefficient, and the kappa statistic.

Analysis demonstrated that automated segmentation using ABACS was comparable with manual segmentation. The researchers noted that ABACS may expedite data collection.

Reference: Rigiroli F, Zhang D, Molinger J, et al. Automated versus manual analysis of body composition measures on computed tomography in patients with bladder cancer. Eur J Radiol. 2022;154:110413. doi:10.1016/j.ejrad.2022.110413

Link: https://pubmed.ncbi.nlm.nih.gov/35732083/