Is single fraction the future of stereotactic body radiation therapy (SBRT)? A critical appraisal of the current literature

Local treatment for oligoprogressive metastatic sites of breast cancer: efficacy, toxicities and future perspectives

Metastatic breast cancer (MBC) is still an incurable disease, which eventually develops resistance mechanisms against systemic therapies. While most patients experience widespread disease progression during systemic treatment (ST), in some cases, progression may occur at a limited number of metastatic sites. Evidence from other malignancies suggests that local treatment with stereotactic ablative radiotherapy (SABR) of oligoprogressive disease (OPD) may allow effective disease control without the need to modify ST. Available evidence regarding local treatment of oligoprogressive breast cancer is limited, mostly consisting of retrospective studies. The only randomized data come from the randomized CURB trial, which enrolled patients with oligoprogressive disease, including both small cell lung cancer and breast cancer patients, and did not show a survival benefit from local treatment in the latter group. However, local treatment of oligoprogressive MBC is still considered in clinical practice, especially to delay the switch to more toxic STs. This review aims to identify patients who may benefit from this approach based on the current available knowledge, focusing also on the potential risks associated with the combination of radiotherapy (RT) and ST, as well as on possible future scenarios.

Efficient quality assurance for isocentric stability in stereotactic body radiation therapy using machine learning

This study aims to predict isocentric stability for stereotactic body radiation therapy (SBRT) treatments using machine learning (ML), covers the challenges of manual assessment and computational time for quality assurance (QA), and supports medical physicists to enhance accuracy. The isocentric parameters for collimator (C), gantry (G), and table (T) tests were conducted with the RUBY phantom during QA using TrueBeam linac for SBRT. This analysis combined statistical features from the IsoCheck EPID software. Five ML models, including logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB), and support vector machines (SVM), were used to predict the outcome of the QA procedure. 247 Winston-Lutz (WL) tests were collected from 2020 to 2022. In our study, both DT and RF achieved the highest score on test accuracy (Acc. test) ranging from 93.5% to 99.4%, and area under curve (AUC) values from 90 to 100% on three modes (C, G, and T). The precision, recall, and F1 scores indicate the DT model consistently outperforms other ML models in predicting isocenter stability deviation in QA. The QA assessment using ML models can assist error prediction early to avoid potential harm during SBRT and ensure safe and effective patient treatments.