EPV127/#500 Impact of computed tomography-determined sarcopenia and artificial intelligence-driven waist skeletal muscle volume on survival outcome in endometrial cancer

Abstract

<h3>Objectives</h3> To investigate the impact of computed tomography (CT)-determined sarcopenia and body composition on survival outcomes in patients with endometrial cancer. <h3>Methods</h3> We retrospectively identified patients diagnosed with endometrial cancer between 2014 and 2018. Using an artificial intelligence-based tool, the skeletal muscle area (cm²) at the third lumbar vertebra (L3) and the skeletal muscle volume (cm³) at the waist level from pre-treatment CT scans were measured. These values were converted to the L3 skeletal muscle index (SMI) index and volumetric SMI by normalisation. The relationships between L3, volumetric SMIs, and survival outcomes were evaluated. <h3>Results</h3> Altogether, data of 385 patients were analysed. The mean patient age was 55.5 years. Applying the well-known cut-off value for sarcopenia to the L3 SMI, sarcopenia (&lt;39.0 cm²/m², n=177) and non-sarcopenia (≥39.0 cm²/m², n=208) groups showed similar progression-free survival (PFS; P=0.335) and overall survival (OS; P=0.241). Using the median value, the low-volumetric SMI group (&lt;206.0 cm³/m³, n=192) showed significantly worse PFS (3-year survival rate, 77.3% vs. 88.8%; P=0.004) and OS (3-year survival rate, 92.8% vs. 99.4%; P=0.003) than the high-volumetric SMI group (≥206.0 cm³/m³, n=193). In multivariate analyses adjusted for baseline body mass index and other factors, low-volumetric SMI was identified as an independent poor prognostic factor for PFS (adjusted HR, 1.762; 95% CI, 1.051–2.953; P=0.032) and OS (adjusted HR, 5.964; 95% CI, 1.296–27.448; P=0.022). <h3>Conclusions</h3> Waist skeletal muscle volume is a novel prognostic biomarker in patients with endometrial cancer. Assessing body composition before treatment may provide important prognostic information for such patients.