Research

What is Medical Physics?

Medical physics beginning with the discovery of X-rays in the 1890s is a field of applied physics that utilizes physics principles, knowledge, and methods to the prevention, diagnosis, and treatment of human diseases to enhance human health and well-being in practice and research.  Medical physics has been closely associated with X-ray photon and electron radiation therapy on linear accelerators. To help improve therapeutic accuracy, it deals with a variety of medical imaging modalities, such as computed tomography (CT), positron emission tomography (PET), magnetic resonance imaging (MRI), and ultrasound. It is believed that medical physics is entering a renaissance era with the rise of particle radiation therapy and artificial intelligence (AI) - machine learning and deep learning. The rapid transition requires medical physicists and researchers to have a concrete understanding of complicated techniques and knowledge behind such advances. 

Outcome Prediction

Therapeutic strategy might be variable depending on the reliable outcome modeling about toxicity and reseponse following the radiation therapy. Learning-based approach has been enhancing the predictive performance of the model for the treatment outcome, which involved the three-dimensional medical images and dose distribution as well as the patient-specific clinical information. Our group is interested in developing robust learning-based predictive model for the appropriate clinical applications.

Image Translation

There exist a variety of image generative networks available, which could be applied to the medical image processing, ranging from image reconstruction to image translation. MR-only radiotherapy, for instance, has been one of the most interesting topics in radiation therapy with no use of CT images for treatment planning, which was enabled by the generative networks translating MR to CT images. Our group is interested in developing such a network algorithm that can generate clinically feasible translated images, and achieving the artifcat correction possibly throughout the translation

Auto-Segmentation

Contouring normal organs and target volume is important, but labor-intensive. Deep learning-based autosegmentation recently helped boost efficiency in the preparation for radiation therapy. We have been interested in the normal organ autosegmentation, which are expanded to the target volume segmentation throughout the state-of-art network algorihtms such as vision transformer. 

It is important to note that the learning-based approach including machine learning and deep learning is based on the optimizing algorihtms, especially the iterative methods. Image reconstruction for medical imaging modalities and treatment planning for radiation therapy also work out through solving the inverse optimization problems. Our group is, in particular, interested in attaning sparse signal recovery with the Lp-norm (p≤1), and applying those to the treatment plan optimization, including heavy-ion radiation therapy.

Development of Deep Learning-Based Predictive Model for Radiotherapy Treatment Plan Deliverability by Visualizing Plan Parameters  


Development of Advanced Dose Calculation and Plan Optimization Algorihtm and System for Carbon Ion Radiation Therapy  


Development of Artificial-Intelligence Driven Radiotherapy-Purpose CT(CBCT) Image Processing Platform for Metal-Artfiact Reduction, Low-Dose Image Reconstruction, and Treatment Outcome Prediction  

 

  A New Deformable Image Registration (DIR) Algorithm Considering Deformation Discontinuity Based on L0-Norm Minimization