Algorithm:MIT

From NAMIC Wiki
Jump to: navigation, search
Home < Algorithm:MIT

Shape- and Atlas-Based Segmentation

The goal of this project is to augment the segmentation process with prior information on the shape of the anatomical structures (shape atlas) learned from previously segmented scans (using, for example, Principal Component Analysis). We are working on methods that integrate the shape atlases with segmentation algorithms.

Tissue Classification

This type of algorithms assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. More...

New: K.M. Pohl, J. Fisher, M. Shenton, R. W. McCarley, W.E.L. Grimson, R. Kikinis, and W.M. Wells. Logarithm odds maps for shape representation. Accepted to MICCAI 2006. More...

Description - Publications - Software - AHM 2006

Boundary Localization

This class of algorithms explicitly manipulates the representation of the object boundary to fit the strong gradients in the image, indicative of the object outline. Bias in the boundary evolution towards the likely shapes improves the robustness of the segmentation results when the intensity information alone is insufficient for boundary detection. More...

Description - Publications - Software

Registration Regularization

We are interested in the effects of registration regularization on segmentation accuracy in joint registration-segmentation. More...

DTI Analysis and Visualization

Our work in DTI analysis focuses on identifying new ways to provide an interpretation of the white matter connectivity and to utilize the information contained in the DTI images to create more comperehsive models of the brain architecture.

DTI Clustering

The goal of this project is to provide structural description of the white matter arcitecture as a partition into coherent fiber bundles and clusters. More...

New: Lauren O'Donnell and Carl-Fredrik Westin. High-Dimensional White Matter Atlas Generation and Group Analysis. Accepted to MICCAI 2006. More...

Description - Software - Software - AHM 2006 - PW 2006

Fiber Tract Modeling and Clustering

The goal of this work is to model the shape of the fiber bundles and use this model discription in clustering and statistical analysis of fiber tracts. More...

Description-Publications - Software

DTI-based Segmentation

Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. More...

New: Ulas Ziyan, David Tuch, Carl-Fredrik Westin. Segmentation of Thalamic Nuclei from DTI using Spectral Clustering. Accepted to MICCAI 2006. More...

Description - Publications - Software

fMRI Detection and Analysis

We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. More...

New: Wanmei Ou, Sandy Wells, Polina Golland. Bridging Spatial Regularization And Anatomical Priors in fMRI Detection. In preparation for submission to IEEE TMI. More...

Description - Publications - Software - PW 2006

Shape Analysis Across Populations

Our goal is to develop mathematical modeling approaches to modeling anatomical shape and its variability within and accross populations. More...

Description - Publications - Software - AHM 2006

Groupwise Registration

Collaborations with other groups in NAMIC

  • Algorithms:
    • Segmentation: joint development of the algorithms and GUI for shape-based hierarchical segmentation with BWH (Kilian Pohl, Steve Pieper).
    • Shape Analysis: joint pipeline I/O formulation and development with Kitware (Brad Davis) and UNC (Martin Styner).
    • fMRI Detection: joint integration of fMRI detectors into Slicer with BWH (Steve Pieper).
  • Clinical:
    • Continuing collaboration with Harvard on shape-based segmentation and DTI analysis.
    • New collaboration, enabled and facilitated by NAMIC, with Dartmouth on DTI and fMRI analysis.