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.
Highlights
Machine learning (ML) has the potential to revolutionize the field of radiation oncology in many processes and workflows to improve the quality and efficiency of patient care (Feng et al, 2018)
Since the early ML models applied to machine and patientspecific quality assurance (QA) were reported in early 2016, a significant improvements have been seen in more recent models as machine learning techniques in radiotherapy QA matured
It is expected that future ML models built on the foundation of existing knowledge can continue to be refined
Summary
Machine learning (ML) has the potential to revolutionize the field of radiation oncology in many processes and workflows to improve the quality and efficiency of patient care (Feng et al, 2018). Zhao et al (in press) utilized 43 sets of commissioning and annual QA beam data from water tank measurements to build a machine learning model that could predict the percent depth doses (PDD) and profiles of other field sizes such as 4 × 4 cm2, 30 × 30 cm accurately within 1% accuracy with 10 × 10 cm data input This application would potentially streamline the data acquisition for the entire commissioning process in TPS as well as optimize periodic QA of Linacs to a minimum set of measurements. Grewal et al utilized 4,231 QA measurements with a train/test split of 90 and 10% to build models to predict OF and MU for uniform scanning proton beams with two learning algorithms—Gaussian process regression and shallow neural network (Grewal et al, 2020) They found that the prediction accuracy of machine and deep learning algorithms is higher than the empirical model currently used in the clinic. In order to implement virtual IMRT QA in a clinic the following workflow should be followed: (1) collect or access IMRT QA data, (2) extract all the parameters of the IMRT fields from plan files, (3) extract the features for the calculation of all TABLE 1 | Summary of studies on machine QA using machine learning techniques in a chronological order
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
