Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Munich, Germany; Institute of Innovative Radiotherapy (iRT), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, Neuherberg, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany.
Department for Bioinformatics and Computational Biology, Informatik 12, Technical University of Munich (TUM), Garching, Germany.
Radiother Oncol. 2019 Jun;135:187-196. doi: 10.1016/j.radonc.2019.01.004. Epub 2019 Apr 5.
In soft tissue sarcoma (STS) patients systemic progression and survival remain comparably low despite low local recurrence rates. In this work, we investigated whether quantitative imaging features ("radiomics") of radiotherapy planning CT-scans carry a prognostic value for pre-therapeutic risk assessment.
CT-scans, tumor grade, and clinical information were collected from three independent retrospective cohorts of 83 (TUM), 87 (UW) and 51 (McGill) STS patients, respectively. After manual segmentation and preprocessing, 1358 radiomic features were extracted. Feature reduction and machine learning modeling for the prediction of grading, overall survival (OS), distant (DPFS) and local (LPFS) progression free survival were performed followed by external validation.
Radiomic models were able to differentiate grade 3 from non-grade 3 STS (area under the receiver operator characteristic curve (AUC): 0.64). The Radiomic models were able to predict OS (C-index: 0.73), DPFS (C-index: 0.68) and LPFS (C-index: 0.77) in the validation cohort. A combined clinical-radiomics model showed the best prediction for OS (C-index: 0.76). The radiomic scores were significantly associated in univariate and multivariate cox regression and allowed for significant risk stratification for all three endpoints.
This is the first report demonstrating a prognostic potential and tumor grading differentiation by CT-based radiomics.
尽管局部复发率较低，但软组织肉瘤（STS）患者的全身进展和生存率仍然相对较低。在这项工作中，我们研究了放射治疗计划 CT 扫描的定量成像特征（“放射组学”）是否对治疗前风险评估具有预后价值。
从三个独立的回顾性队列中分别收集了 83 名（TUM）、87 名（UW）和 51 名（麦吉尔）STS 患者的 CT 扫描、肿瘤分级和临床信息。手动分割和预处理后，提取了 1358 个放射组学特征。进行特征减少和机器学习建模，以预测分级、总生存期（OS）、远处（DPFS）和局部（LPFS）无进展生存期，然后进行外部验证。
放射组学模型能够区分 3 级和非 3 级 STS（受试者工作特征曲线下的面积（AUC）：0.64）。放射组学模型能够预测 OS（C 指数：0.73）、DPFS（C 指数：0.68）和 LPFS（C 指数：0.77）在验证队列中。临床放射组学综合模型显示对 OS 的最佳预测（C 指数：0.76）。放射组学评分在单变量和多变量 Cox 回归中具有显著相关性，并且允许对所有三个终点进行显著的风险分层。
这是第一项证明基于 CT 的放射组学具有预后潜力和肿瘤分级区分的报告。
