12/10/2021
By Susan Pryputniewicz

The Biomedical Engineering and Biotechnology program invites you to attend a doctoral proposal defense by Matthew C. Schmidt on “Implementation of Safe and Efficient Automated Treatment Planning through Interpretation of Treatment Plan Templates and Determination of Essential Planning Inputs.”

Name: Matthew Charles Schmidt
Date: Wednesday, Dec. 22, 2021
Time: 11 a.m. – 1 p.m. EST
Location: This will be a virtual defense via Zoom. Those interested in attending should contact the student matthew.schmidt@wustl.edu and committee advisor erno_sajo@uml.edu at least 24 hours prior to the defense to request access to the meeting.

Committee Chair (Advisor): Erno Sajo, Ph.D., Professor, Department of Physics and Applied Physics, University of Massachusetts Lowell

Committee Members:

  • Marian Jandel, Ph.D., Assistant Professor, Department of Physics and Applied Physics, University of Massachusetts Lowell
  • Piotr Zygmanski, Ph.D., Research Professor, Department of Physics and Applied Physics, University of Massachusetts Lowell
  • Nels Knutson, Ph.D., Assistant Professor, Radiation Oncology, Washington University in St. Louis School of Medicine
  • Baozhou Sun, Ph.D., Assistant Professor, Radiation Oncology, Washington University in St. Louis School of Medicine
  • Francisco Reynoso, Ph.D., Assistant Professor, Radiation Oncology, Washington University in St. Louis School of Medicine

Abstract:

Introduction: Automation is a growing topic of discussion in all fields; radiation oncology is no exception. With automation comes the excitement and concern while facing the unknown landscape of clinical practice of the future. Clinical automation comes in the form of vendor provided tools, such as clinical scripting Application Programming Interfaces (APIs), focused on programmatic generation of treatment plan data. Widespread implementation of automated treatment planning in radiation therapy remains elusive due to variability in clinic and physician preferences making it difficult to ensure consistent plan parameters. This work aims to validate the safety of automation features in clinical practice and construct templates effective toward the implementation of automated templates.

Methods: Automation for linear accelerator (linac) quality assurance (QA) offers an opportunity to validate automation features without directly impacting patient plan quality. Automating the QA process includes two software components: the AutoQA Builder to generate daily, monthly, quarterly, and miscellaneous periodic linear accelerator QA plans within the Treatment Planning System (TPS) and the AutoQA Analysis to analyze images collected on the Electronic Portal Imaging Device (EPID) allowing for a rapid analysis of the acquired QA images. An open-source class library has been developed that interprets clinical templates within a commercial treatment planning system into a treatment plan for automated planning. Vendor provided clinical protocol templates are then utilized to generate plans of multiple treatment disease sites.

Proposal: By leveraging currently available technology, clinicians can utilize their data from disparate systems to build automated tools to assist in the tedious nature of treatment planning, commissioning, quality assurance and research-level data collection. The proposed work plans to identify a roadmap for the adoption of novel applications and services, centered on clinical automation and efficiency while discussing the benefits and safety concerns regarding the implementation of such technology.

All interested students and faculty members are invited to attend the online defense via remote access.