Automated Analysis of Treatment Log Files and Videos for MR-Guided Stereotactic Body Radiation Therapy Treatments of Thoracic and Abdominal Tumors

Abstract

<h3>Purpose/Objective(s)</h3> MR-guided stereotactic body radiation therapy (MRgSBRT) is a novel method of treating mobile tumors with robust real-time gating and on-table adaptive planning. Delivery log files and cine videos of the treatment generated by the software system can be a rich source of information for assessing MRgSBRT treatment sessions. We hypothesized that developing scripts for automated review of MRgSBRT treatments using delivery logs and cine videos would be feasible. We have included a summary of our findings from our initial experience using this automated analysis. <h3>Materials/Methods</h3> We conducted a retrospective review of patients undergoing MRgSBRT for treatment of liver, lung, and pancreas tumors. Custom Python scripts were written to automatically extract treatment delivery information from log files and export data neatly into to a spreadsheet. A separate Python script was written to extract information from delivery cine videos using optical character recognition (OCR), color thresholding, and morphological processing as well. <h3>Results</h3> Using our automated system we were able to extract the following data points from the log files: treatment site, date and time of treatment, tracking algorithm configuration, average treatment duration, total dose, fraction (fx) number, MU per fx, couch shifts, and need for plan re-optimization. Additionally, through automated analysis of treatment cine video files we were able to extract frame by frame information for tracking structure centroid displacement, beam on/off status, frame-frame similarity, and tracking confidence (TC) over the course of treatment. Table 1 is an example of the data output. <h3>Conclusion</h3> Automated analysis of MRgSBRT delivery log files and log videos is feasible and can serve as a rich resource for QA/QI to improve treatment efficiency on an MR-LINAC by quantifying a multitude of measurable parameters and formulating strategies to address any unrealized bottlenecks in the process. Future plans include expanding our automation to examine total patient time on table, monitor units per beam segment, and predicting internal tumor volumes (ITV) based on tracking target displacement obtained from the delivery videos.