Abstract
Radiomics entails a data-driven approach to imaging with a wide array of potential uses in characterizing soft tissue sarcomas, enabling extraction of quantitative features from routine clinical CT and MRI examinations. These features—encompassing descriptors of size, shape, and internal heterogeneity—can improve diagnostic accuracy, tumor grading, and treatment response assessment. Radiomics has shown promise in distinguishing benign from malignant lesions, subtyping sarcomas, and predicting metastatic potential. In particular, models integrating radiomic data with clinical variables have demonstrated performance comparable to expert radiologists in challenging diagnostic scenarios. Machine learning enhances radiomics by automating feature selection and improving predictive modeling. Despite its potential, challenges remain in standardizing imaging protocols, ensuring reproducibility, and integrating radiomics into clinical workflows. Multi-institutional collaboration is essential for broader model validation and clinical integration. By leveraging specific radiomics features as novel quantitative imaging biomarkers, radiomics can drive precision oncology in sarcoma, supporting tailored therapies and improving prognostic accuracy.