Automated 3D body composition analysis on chest CT scans for survival prediction in high-grade extremity soft tissue sarcomas.

INTRODUCTION: High-grade soft tissue sarcomas (STShg) of the extremities are rare cancers with a poor prognosis. Accurate staging at initial evaluation is crucial for determining optimal treatment. Current guidelines recommend systematic chest computed tomography (CT) scans during initial assessment. Recent advances in artificial intelligence (AI)-based imaging software now enable automatic, rapid volumetric assessment of body composition from CT scans. Our study aims to evaluate the predictive role of body composition features, obtained using a dedicated AI program, on overall survival (OS) and disease-free survival (DFS), using staging chest CT scans from patients diagnosed with extremity STShg. MATERIALS AND METHODS: We conducted a single-center retrospective study at the Jules Bordet Institute, including patients diagnosed with extremity STShg between January 2010 and January 2023 who underwent CT scans covering the thoracic region. Using dedicated software, we performed automated 3D quantitative analysis of various anatomical compartments, including intramuscular adipose tissue (IMAT), pericardial adipose tissue (PAT), epicardial adipose tissue (EAT), and visceral adipose tissue (VAT). We assessed the association between body composition metrics and OS, DFS, local recurrence-free survival, and metastatic recurrence-free survival. RESULTS: Higher volumes of IMAT and PAT were associated with shorter OS, DFS, and local recurrence-free survival. Increased EAT volume correlated with reduced OS, while higher VAT volume was linked to worse OS and DFS. CONCLUSION: Our study suggests a potential predictive role of specific body composition features, particularly IMAT, PAT, EAT, and VAT volumes, in the prognosis of extremity STShg.