Table 1_Intratumoral habitat and peritumor radiomics for progression risk stratification of patients with soft tissue sarcoma: a multicenter study.docx

ObjectiveTo establish and validate a radiomics nomogram that incorporated tumor habitat and peritumor features to predict tumor progression in patients with soft tissue sarcoma (STS).
MethodsMRI data (fat-suppressed T2-weighted and contrast-enhanced fat-suppressed T1-weighted images) from 148 STS patients treated in four institutions were retrospectively enrolled. Patients were divided into a training cohort (n = 108) and validation cohort (n = 40). K-means clustering was applied to split intratumoral voxels into three habitats according to signal intensity values. A large number of radiomics features were extracted from numerous tumor-associated regions (tumor lesion, peritumor, tumor expansion, and intratumoral habitats) to construct a series of radiomics signatures. A nomogram integrating clinical predictors and radiomics signature was established and its value for predicting progression was validated.
ResultsThe nomogram yielded superior prediction performance and less predictive error in the validation cohort (C-index, 0.777; median area under the receiver operating characteristic curve, 0.808; integrated Brier score, 0.135). When patients were stratified according to risk of progression (low and high) based on the nomogram in both the training and validation cohorts, Kaplan–Meier survival analysis demonstrated significant differences in progression-free survival between the groups. In addition, it could attach incremental value to histopathological grade system in progression risk evaluation.
ConclusionA nomogram based on intratumoral habitat and peritumor radiomics predicts tumor progression in STS patients and stratifies them according to risk of progression.