The research interests of Bradley J. Erickson, M.D., Ph.D., include computer-aided diagnosis and the use of computer technologies to extract information from medical images for diagnostic, prognostic and therapeutic purposes. This research includes the development and validation of algorithms that can detect progression, regression or risk of disease, and the prediction of molecular markers from medical images.

Dr. Erickson is also actively developing a system to promote team science, initially pursuing on imaging-focused research, but with connections to genomics, pathology and clinical data.

Focus areas

• Quantitative imaging. Work in this area involves applying methods to better characterize and treat disease using quantitative metrics such as volume or texture.
• Computer-aided diagnosis. Dr. Erickson is using methods of machine learning and deep learning to identify the most important information in images and reliably apply that information to the care of patients.
• Polycystic kidney disease (PKD). Imaging is used to measure and characterize the nature and progression of PKD.

Significance to patient care

Medical images have a wealth of information in them. Radiologists are responsible for extracting that information. The focus of much of Dr. Erickson's research is to make radiologists better at extracting and understanding that information, making imaging more efficient, reliable and consistent.