| Summary: | A robust multi-modal tool, for automated registration, bias correction, and tissue classification, has been implemented for large-scale heterogeneous multi-site longitudinal MR data analysis.This work focused on improving the an iterative optimization framework between bias-correction, registration, and tissue classification inspired from previous work.The primary contributions are robustness improvements from incorporation of following four elements: 1) utilize multi-modal and repeated scans, 2) incorporate high-deformable registration, 3) use extended set of tissue definitions, and 4) use of multi-modal aware intensity-context priors.The benefits of these enhancements were investigated by a series of experiments with both simulated brain data set (BrainWeb) and by applying to highly-heterogeneous data from a 32 site imaging study with quality assessments through the expert visual inspection.The implementation of this tool is tailored for, but not limited to, large-scale data processing with great data variation with a flexible interface.In this paper, we describe enhancements to a joint registration, bias correction, and the tissue classification, that improve the generalizability and robustness for processing multi-modal longitudinal MR scans collected at multi-sites.The tool was evaluated by using both simulated and simulated and human subject MRI images.With these enhancements, the results showed dramatic improvement in accuracy and robustness for large-scale heterogeneous MRI processing.
|
|---|