BAYESIAN RECONSTRUCTION FROM MULTICHANNEL K-SPACE DATA USING GRAPH-CUT ALGORITHM

Northern California Institute/Res/Edu, San Francisco CA

Investigators

Linked publications & trials

Abstract

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. A Graph Cut Algorithm For Brain Image Segmentation: This project aims to obtain novel algorithms and software for structural brain image segmentation. We will consider both single-modality as well as multi-modality data. The project will result in image segmentation into 3 tissue classes: white matter, gray matter and cerebro-spinal fluid. We will use a graph cut approach, which is a popular computer vision for segmentation tasks. Graph Cut Algorithm For Reconstruction of Parallel MRI: This project aims to develop a new algorithmic paradigm for the reconstruction of MR Parallel Imaging (MRPI) data by using recent advances in Computer Science and Graph Theory. Specifically, we will further develop and refine computationally efficient Bayesian methods for MRI that have the potential to overcome fundamental limits of traditional MR imaging. A graph-based formulation was recently proposed for the Parallel Imaging problem using MRF priors. This subproject will further refine this technique for specific applications in structural and dynamic brain imaging.