Integration of AI and Machine Learning in Radiotherapy QA

Abstract

The use of machine learning and other sophisticated models to aid in prediction and decision making has become widely popular across a breadth of disciplines. Within the greater diagnostic radiology, radiation oncology, and medical physics communities promising work is being performed in tissue classification and cancer staging, outcome prediction, automated segmentation, treatment planning, and quality assurance as well as other areas. In this article, machine learning approaches are explored, highlighting specific applications in machine and patient-specific quality assurance (QA). Machine learning can analyze multiple elements of a delivery system on its performance over time including the multileaf collimator (MLC), imaging system, mechanical and dosimetric parameters. Virtual Intensity-Modulated Radiation Therapy (IMRT) QA can predict passing rates using different measurement techniques, different treatment planning systems, and different treatment delivery machines across multiple institutions. Prediction of QA passing rates and other metrics can have profound implications on the current IMRT process. Here we cover general concepts of machine learning in dosimetry and various methods used in virtual IMRT QA, as well as their clinical applications.

Artificial intelligence for prediction of measurement‐based patient‐specific quality assurance is ready for prime time

“…6 This approach has been extensively validated at different institutions. 7 ML IMRT PSQA can be implemented in three different ways with variable impact in our IMRT QA process: (a) To have plan-specific thresholds and increase the sensitivity of our QA program. For example, if a plan is predicted to result in a gamma passing rate equal to 91% but we measure 89% it might be okay to deliver it but if we predict 100% and we measure 92% it might not be.…”

Artificial intelligence should be part of medical physics graduate program curriculum

“…3 In its scale, scope, depth, and complexity, the change will be unprecedented. Specific to our own field, there is every indication that AI will redefine how things are done in the clinic, from commissioning and dosimetry, 14,15 imaging and image analysis, 16,17 dose calculation and planning, 18,19 image guidance, and dose delivery, 20 to outcome prediction. [21][22][23] While it is implausible for a student to enroll in all of the courses offered by a large program, I do not think that this should prevent us from offering the best possible education to our students.…”

“…In its scale, scope, depth, and complexity, the change will be unprecedented. Specific to our own field, there is every indication that AI will redefine how things are done in the clinic, from commissioning and dosimetry, 14,15 imaging and image analysis, 16,17 dose calculation and planning, 18,19 image guidance, and dose delivery, 20 to outcome prediction 21–23 …”

Virtual Patient-Specific Quality Assurance of IMRT Using UNet++: Classification, Gamma Passing Rates Prediction, and Dose Difference Prediction

“…With the development of machine learning and deep learning and its application in QA results prediction, the efficiency of patient-specific QA is expected to be improved (9)(10)(11)(12)(13)(14)(15)(16). Valdes, Lam, Li (9)(10)(11)(12) etc.…”

“…Previous prediction models based on machine learning or deep learning were only the results of dose verification but could not provide detailed information of dose difference (9)(10)(11)(12)(13)(14)(15)(16)(17)(18). Predicting the trend and position of dose difference is an important work in automatic patient-specific QA in the near future.…”