LAUSR

Simple Summary Soft-tissue sarcomas constitute a rare cancer type, with approximately 40% of patients experiencing disease recurrence. There is a need for a better identification of patients with especially aggressive tumors. Previous research demonstrated that the qualitative assessment of imaging data by radiologists (“semantic features”) and the algorithm-based analysis of imaging data (termed “radiomics”) may help to achieve a more thorough identification of patients at high risk for cancer-specific mortality. In this work, we compared the performance of predictions of patients’ survival based on semantic features extracted by radiologists with a “radiomic” approach. While some semantic features were helpful to identify high-risk patients, the radiomic approach achieved an overall improved ability to identify patients at high risk. For the radiomic prediction, only one MRI sequence was sufficient and an MRI sequence without the need for contrast agent achieved good predictive performance. Abstract Background: In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients’ risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS). Methods: Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS. Results: ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification. Conclusions: T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.