Hofmann Felix O, Heiliger Christian, Tschaidse Tengis, Jarmusch Stefanie, Auhage Liv A, Aghamaliyev Ughur, Gesenhues Alena B, Schiergens Tobias S, Niess Hanno, Ilmer Matthias, Werner Jens, Renz Bernhard W
Department of General, Visceral and Transplant Surgery, Ludwig-Maximilians-University Hospital Munich, Marchioninistrasse 15, 81377, Munich, Germany.
German Cancer Consortium (DKTK), Partner Site Munich, and German Cancer Research Center (DKFZ), Heidelberg, Germany.
Sci Rep. 2025 Apr 7;15(1):11909. doi: 10.1038/s41598-025-96238-6.
Sarcopenia and body composition metrics are strongly associated with patient outcomes. In this study, we developed and validated a flexible, open-access pipeline integrating available deep learning-based segmentation models with pre- and postprocessing steps to extract body composition measures from routine computed tomography (CT) scans. In 337 surgical oncology patients, total skeletal muscle tissue (SM), psoas muscle tissue (SM), visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT) were quantified both manually and using the pipeline. Automated and manual measurements showed strong correlations (SM: r = 0.776, VAT: r = 0.993, SAT: r = 0.984; all P < 0.001). Measurement discrepancies primarily resulted from segmentation errors, anatomical anomalies or image irregularities. SM measurements showed substantial variability depending on slice selection, whereas SM, averaged across all L3 levels, provided greater measurement stability. Overall, SM performed comparably to SM in predicting overall survival (OS). In summary, body composition measures derived from the pipeline strongly correlated with manual measurements and were prognostic for OS. The increased stability of SM across vertebral levels suggests it may serve as a more reliable alternative to psoas-based assessments. Future studies should address the identified areas of improvement to enhance the accuracy of automated segmentation models.
肌肉减少症和身体成分指标与患者预后密切相关。在本研究中，我们开发并验证了一种灵活的、开放获取的流程，该流程将现有的基于深度学习的分割模型与预处理和后处理步骤相结合，以从常规计算机断层扫描（CT）扫描中提取身体成分测量值。在337例外科肿瘤患者中，对总骨骼肌组织（SM）、腰大肌组织（SM）、内脏脂肪组织（VAT）和皮下脂肪组织（SAT）进行了手动和使用该流程的测量。自动测量和手动测量显示出很强的相关性（SM：r = 0.776，VAT：r = 0.993，SAT：r = 0.984；所有P < 0.001）。测量差异主要源于分割错误、解剖异常或图像不规则。SM测量值因切片选择而异，变化很大，而在所有L3水平上平均的SM提供了更高的测量稳定性。总体而言，在预测总生存期（OS）方面，SM的表现与SM相当。总之，从该流程得出的身体成分测量值与手动测量值密切相关，并且对OS具有预后价值。SM在不同椎体水平上稳定性的提高表明，它可能是基于腰大肌评估的更可靠替代方法。未来的研究应解决已确定的改进领域，以提高自动分割模型的准确性。
