Machine and Deep Learning-based Approaches to VMAT Plan Complexity Evaluation: A Short Scoping Review

Volumetric Modulated Arc Therapy (VMAT) is an advanced radiation therapy technique. Due to its complexity, ensuring accuracy and safety requires extensive Quality Assurance (QA) procedures. Machine Learning (ML) and Deep Learning (DL) offer promising tools to automate tasks, identify patterns, and predict outcomes in VMAT planning and QA. This can significantly improve efficiency and potentially enhance accuracy. This study aims to evaluate the complexity of VMAT plans using machine and deep learning techniques. Moreover, we review some existing research on ML/DL models for predicting patient-specific VMAT QA outcomes. The review also discuss current challenges and future directions in utilizing these models to optimize VMAT QA. Finally, to identify the most suitable model for predicting patient-specific VMAT QA, we recommend comparing the performance of various models on a common dataset using appropriate evaluation metrics.