This research develops quantitative image analysis software tools for detecting and precisely measuring anatomic changes in sequences of 3D medical image data, such as MRI or CT scans taken over time. Accurate structural change detection and identification will improve several medical applications, such as the experimental evaluation of drugs and treatments, precise monitoring of disease progression, and early disease diagnosis. The key objective of this research is to demonstrate that practical automated registration tools can be developed for handling the problems encountered in medical change detection applications: structures of complex 3D shape, tissue deformation, varying image resolution, and sensor distortion. This Phase I research program proposes to demonstrate the feasibility of automated image registration tools for detecting anatomic changes by: l) establishing bounds on attainable performance of the image-based anatomic change detection technique as a function of sensor resolution and other image acquisition parameters; 2) assessing the performance of our approach through extensive experimentation with phantom models and controlled imagery; and 3) identifying impact on specific applications. Following a successful validation study in Phase I, a proposed Phase II effort will continue with animal studies and increased interaction with clinicians to refine the change detection capabilities.
We propose to develop a 3D image analysis tool for quantifying structural changes in MR or CT images taken in subjects over time. By developing accurate and robust products whose performance is well-understood we aim to initially develop end-products that may be directly used by clinical researchers for drug efficacy trials, such as for multiple sclerosis and stroke. Such tools may also form the backbone of a commercial service in which disease diagnosis and treatment monitoring tests are performed.
