Dr. Munbodh is interested in the development of innovative analytical and computational approaches to allow a better understanding and more effective treatment of cancer. She conducts basic and clinical-translational research in oncology with a focus on the automated analysis of multi-modal medical data. Her research is interdisciplinary and relies on concepts from computer science, statistics, mathematics, oncology and data science.

Established areas of research include: 1) Predictive modeling of outcome and normal tissue toxicity following radiation therapy using data from a variety of modalities, and the study of the spatial sensitivity of normal tissues to radiation dose, and 2) The development of automated deep-learning based methods for the longitudinal study of tumors using medical images and other patient-related data.

More recently, she has initiated research in the use of graph-based theory to automate quality assurance processes in radiation oncology, the development of data-driven processes to improve clinical practice, and the use of digital health informatics to improve the experience of cancer patients undergoing radiation therapy. Dr. Munbodh has a strong interest in building multi- and inter-disciplinary collaborations within and across departments and institutions, and in connecting students and investigators.