Image Processing
We use state-of-the-art deep learning and machine learning algorithms to improve image quality, solve image processing problems such as image synthesis, segmentation, and classification to support clinical needs.
Automatic Treatment Planning
We aim to utilize large-scale data sets and deep learning algorithms to enable accurate and personalized radiation dose prediction and treatment plan optimization. Our research also includes the development of data-driven decision-making tools for radiation oncologists and treatment planners. We aim to improve the effectiveness and efficiency of radiation treatment while minimizing toxicity and side effects in patients.
Outcome Prediction
We use machine learning models to predict treatment outcomes, such as tumor control and survival rates, based on patient and treatment data.
Quality Assurance
We analyze and verify treatment plan and treatment machine quality and accuracy using machine learning techniques, and to detect and prevent errors and deviations.
Natural Language Processing
We utilize large-scale datasets and advanced analytics techniques, such as deep learning and natural language processing, to extract insights and knowledge from medical records and literature, and to improve clinical decision-making and practice.
Core Faculty
 | Kai Ding Associate Professor [email protected] Lab |
 | Rachel Ger Assistant Professor [email protected] |
 | Sarah Han-Oh Assistant Professor Vice Chief of Physics/Clinical-Baltimore [email protected] |
 | Tom Hrinivich Assistant Professor [email protected] |
 | Xun Jia Professor Chief of Medical Physics Division [email protected] |
 | Junghoon Lee Associate Professor [email protected] Lab |
 | Todd McNutt Associate Professor Director of Clinical Informatics Director of Medical Physics Residency [email protected] |
 | Michael Roumeliotis Assistant Professor Director of Brachytherapy Physics [email protected] |
