Dr. Arka Roy on Uncertainty Management in Radiotherapy via AI & Optimization

Friday, July 19, 2024 2:30 pm - 3:30 pm EDT (GMT -04:00)
seminar

Date: Friday, July 19, 2024 

Time: 2:30 pm - 3:30 pm

Location: E7 Faculty Hall


Title: Uncertainty Management in Radiotherapy via AI & Optimization

Abstract: In radiotherapy, uncertainties can reduce the quality of treatments; deterministic treatments can lead to suboptimal outcomes for the patient. Ultimately, this can cause over- or under-treatment, leading to dysfunctional organs from excessive radiation exposure or tumour metastasis from poor coverage and a failed treatment.

In this talk, we will explore methods from the areas of optimization under uncertainty and artificial intelligence (AI) that can account for two sources of uncertainties, some examples include:

  • Radioresistance
  • Contouring errors.

While standard AI methods and (naïve-) robust treatment planning can overcome this, they can also produce overly conservative or suboptimal decisions, especially when there are unpredictable changes during the treatment.

To overcome this, a predictive-prescriptive adaptive framework is proposed that can adapt to updated information during the treatment. Using this framework, we will explore the value of multiple diagnostics to update the treatment and derive optimal intervention policies that account for time-dependent uncertainties.  

Bio: Dr. Arka Roy is an Assistant Professor in the Management Science and Statistics department housed in the Alvarez College of Business at the University of Texas at San Antonio (UTSA). He is also a Core Faculty member of the new School of Data Science at UTSA. Previously, he was a faculty member in the Applied Statistics and Operations Research department at Bowling Green State University. In addition to his doctoral work at the School of Industrial Engineering at Purdue University, he conducted research as a Visiting Research Fellow in the Industrial Engineering and Management Sciences department at Northwestern University.

His research focuses on the use of optimization under uncertainty and data analytics to improve end-user outcomes in healthcare and in sustainable services. In healthcare, he closely collaborates with clinicians to develop robust models for cancer radiotherapy, data-driven tools for treatment evaluation and quality control, as well as scheduling models for diagnostics and operations. In infrastructure services, he seeks to inform decision-makers on providing sustainable, equitable and resilient services using analytics and optimization. His research has been published in leading medical, sustainability, and operations research journals. 

In addition to his research and teaching responsibilities, he serves as the Program Coordinator for the BBA in Business Analytics program at UTSA. Externally, he is an active member of the Institute for Operations Research and the Management Sciences (INFORMS), the Production and Operations Management Society (POMS), and the American Association of Physicists in Medicine (AAPM).