Objectives: This review systematically summarizes the evidence on the economic impact of magnetic resonance image-guided RT (MRIgRT). Methods: We systematically searched INAHTA, MEDLINE, and Scopus up to March 2022 to retrieve health economic studies. Relevant data were extracted on study type, model inputs, modeling methods and economic results. Results: Five studies were included. Two studies performed a full economic assessment to compare the cost-effectiveness of MRIgRT with other forms of image-guided radiation therapy. One study performed a cost minimization analysis and two studies performed an activity-based costing, all comparing MRIgRT with X-ray computed tomography image-guided radiation therapy (CTIgRT). Prostate cancer was the target condition in four studies and hepatocellular carcinoma in one. Considering the studies with a full economic assessment, MR-guided stereotactic body radiation therapy was found to be cost effective with respect to CTIgRT or conventional or moderate hypofractionated RT, even with a low reduction in toxicity. Conversely, a greater reduction in toxicity is required to compete with extreme hypofractionated RT without MR guidance. Conclusions: This review highlights the great potential of MRIgRT but also the need for further evidence, especially for late toxicity, whose reduction is expected to be the real added value of this technology.

Accurate preoperative distinction between in situ and invasive Breast Cancer (BC) is critical for clinical decision-making and treatment planning. Radiomics and Machine Learning (ML) have shown promise in enhancing diagnostic performance from breast MRI, yet their application to this specific task remains underexplored. The aim of this study was to evaluate the performance of several ML classifiers, trained on radiomic features extracted from DCE–MRI and supported by basic clinical information, for the classification of in situ versus invasive BC lesions. In this study, we retrospectively analysed 71 post-contrast DCE–MRI scans (24 in situ, 47 invasive cases). Radiomic features were extracted from manually segmented tumour regions using the PyRadiomics library, and a limited set of basic clinical variables was also included. Several ML classifiers were evaluated in a Leave-One-Out Cross-Validation (LOOCV) scheme. Feature selection was performed using two different strategies: Minimum Redundancy Maximum Relevance (MRMR), mutual information. Axial 3D rotation was used for data augmentation. Support Vector Machine (SVM), K Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) were the best-performing models, with an Area Under the Curve (AUC) ranging from 0.77 to 0.81. Notably, KNN achieved the best balance between sensitivity and specificity without the need for data augmentation. Our findings confirm that radiomic features extracted from DCE–MRI, combined with well-validated ML models, can effectively support the differentiation of in situ vs. invasive breast cancer. This approach is quite robust even in small datasets and may aid in improving preoperative planning. Further validation on larger cohorts and integration with additional imaging or clinical data are recommended.