Background: The data acquired during absolute or relative dose measurements will then be used for verification of proper linac operation, in the continuing quality assurance (QA) thorough the lifetime of the machine. Artificial intelligence (AI) has emerged as a transformative science in radiation therapy (RT), significantly improving the accuracy of dose measurements, and QA processes. AI-based solutions automate complex tasks, optimize treatment planning, and predict treatment outcomes, ensuring precise dose distributions, and finally patient safety. The integration of machine learning (ML) and deep learning (DL) techniques in dosimetry and QA enhances the efficiency and reliability of these processes, with various applications demonstrated in multiple case studies. The integration of
AI into radiation therapy has revolutionized various aspects of QA. AI-based solutions offer the potential to enhance dosimetry accuracy. Materials and Methods: This study explores the current applications, methodologies, and future directions of
AI in dosimetry and QA.
AI models have been applied to improve the accuracy of dosimetry. These methods could optimize dose distributions, and predict QA outcomes. Regarding QA process the
AI solutions can predict machine beam data, gamma passing rates, and other QA metrics for IMRT, and VMAT techniques. Several studies have demonstrated the effectiveness of AI-based solutions in dosimetry and QA. For example, in a study which carried out by Carleson et al. Results:
AI algorithms have been used to predict PSQA passing rates across different treatment planning systems and delivery machines, improving the consistency and reliability of QA processes. Additionally, according to the AAPM guideline it is highly recommended that further works is needed to apply
AI models in PSQA enabling standardized QA protocols across institutions as multicenter study in the future. Conclusion: AI-based solutions have the potential to significantly improve dosimetry and QA accuracy. By automating complex processes, enhancing accuracy, and streamlining workflows,
AI can contribute to better patient outcomes and more efficient treatment delivery. Continued research and development in this field is required to fully demonstrate the effectiveness of
AI in this field.
