Clinical trial
Validation of a Body-Composition Segmentation Software on a Diverse Public CT Scan Cohort
Opening soon · Not applicable · 1 countries · Registry ID NCT07600866
What this study is about
This study evaluates the standalone performance of Soma, a deep-learning software developed by Nucleo Research, Inc. for the automated segmentation of body-composition tissues (skeletal muscle, subcutaneous adipose tissue, visceral adipose tissue, and intramuscular adipose tissue) on whole-body computed tomography (CT) images. The aim is to confirm that Soma produces segmentations and tissue-area measurements that agree with a multi-rater expert reference standard, on a diverse cohort representative of demographic and clinical variation. A total of 200 CT scans are sampled by stratified design from a curated pool of 2,066 scans aggregated from six publicly available, de-identified imaging datasets (autoPET, AMOS, MSD Pancreas, CT-ORG, ENHANCE.PET, RATIC). Three board-certified radiologists independently annotate the reference standard at the L3 slice. Primary performance is assessed using the Dice similarity coefficient against the multi-rater reference, with predefined thresholds and BCa bootstrap confidence intervals, both in aggregate and within every demographic and clinical subgroup. Secondary endpoints include Bland-Altman analysis of tissue-area agreement, 95th-percentile Hausdorff distance, Pearson correlation of derived indices, and Cohen's kappa for sarcopenia classification using Skeletal Muscle Index (SMI). The study is fully retrospective on de-identified images, involves no patient contact, and has been determined exempt by Salus IRB (Salus Number 26328) under 45 CFR 46.104(d)(4).
Basic eligibility
Full registry criteria
Treatments and study arms
Soma Body-Composition Segmentation Software
Soma is a deep-learning software pipeline developed by Nucleo Research, Inc. for the automated quantitative analysis of body composition from abdominal CT. It comprises (i) a U-Net segmentation model that delineates skeletal muscle, subcutaneous adipose tissue, visceral adipose tissue, and intramuscular adipose tissue on each axial CT slice; and (ii) an EfficientNet-Lite0 + BiLSTM model for automated L3 vertebra detection from axial CT volumes. In this validation study, segmentation performance is assessed on every fifth axial slice across the full scan depth. Outputs include per-tissue segmentation masks, tissue cross-sectional areas (cm\^2), and derived indices including the Skeletal Muscle Index (SMI = muscle area / height\^2). In this study, Soma is applied as the index test in standalone mode, fully blinded to the multi-rater radiologist reference standard.
Primary outcomes
Mean Dice Similarity Coefficient (DSC) between Soma-generated segmentation masks and the consensus reference from three board-certified radiologists, computed per tissue class (skeletal muscle, subcutaneous adipose tissue, visceral adipose tissue, intramuscular adipose tissue) on all annotated axial slices (every fifth slice across the full scan depth). Predefined performance thresholds: mean DSC greater than or equal to 0.90 for skeletal muscle, subcutaneous adipose, and visceral adipose tissues; mean DSC greater than or equal to 0.85 for intramuscular adipose tissue. Thresholds must be met both in aggregate and within every demographic and clinical subgroup with at least 20 scans (BMI category, age band, sex, body region, clinical context). Reported with 95% bias-corrected and accelerated (BCa) bootstrap confidence intervals.
Study locations
1 locations were listed when this page was built. The first 40 are shown.