The research of Timothy L. Kline, Ph.D., focuses on the development of novel image acquisition and image processing techniques to study disease processes and improve patient care.
Dr. Kline is actively developing algorithms to automate image analysis methods, such as the segmentation of polycystic kidneys to automate measurement of total kidney volume. He is also searching for new imaging biomarkers of disease through both the development of new image acquisition protocols (such as methods to characterize microscopic cysts and fibrosis) and analysis techniques (such as texture analysis and deep learning methods).
- Imaging genomics. As part of the Radiology Informatics Lab, Dr. Kline applies classical machine learning and deep learning techniques to automate segmentation of both organs and tissue regions. He is also performing imaging genomics to identify imaging biomarkers that can identify the genomics of a disease.
- Polycystic kidney disease. In collaboration with the Mayo Translational Polycystic Kidney Disease Center, Dr. Kline is searching for new image-based biomarkers — such as texture analysis, multiparametric MRI, quantitative MRI — of polycystic kidney disease that are good indicators of prognosis, that correlate with clinical progression, and that have the ability to judge the effectiveness of interventions.
- Advanced MR imaging. Dr. Kline is working with model organisms of human disease to develop new image acquisition protocols and analysis methods within the Nuclear Magnetic Resonance (NMR) Core Facility.
- Microvascular geometry. Dr. Kline studies microvascular branching geometries using high-resolution micro-CT imaging in collaboration with the Physiological Imaging Research Lab.
Significance to patient care
Dr. Kline hopes that his advancements in automation and novel imaging classification techniques will help evolve individualized patient care. By standardizing routinely performed measurements and providing new image-based biomarkers, Dr. Kline's research significantly impacts the assessment of patient prognosis and allows providers to judge the effectiveness of interventions more quickly.
- Recipient, LRP Award, National Institutes of Health, 2016
- Recipient, Second Place Scientific Award, Society for Imaging Informatics in Medicine, 2015