Difference between revisions of "2010 Winter Project Week Musco Skeletal Segmentation"
| Line 25: | Line 25: | ||
1. Rapid segmentation of target structures into label maps. | 1. Rapid segmentation of target structures into label maps. | ||
<BR> | <BR> | ||
| − | 2. Generation of simulation-ready models from label maps of individual structures. | + | 2. Generation of simulation-ready models from existing atlas and label maps of individual structures. |
| Line 35: | Line 35: | ||
<i><u>Approach:</u></i> | <i><u>Approach:</u></i> | ||
<BR> | <BR> | ||
| + | Objective 1: We have adopted a multi-contrast MR methodology to segment knee bones and cartilage structures. The algorithm utilizes tissue intensity information from multiple MR contrasts to segment structures of interest. Inputs to the algorithm included n registered MR image sets. The algorithm created an n-dimensional space of voxel intensities associated with the n image sets. The user assigned seed points to the structures of interest, and the algorithm assigned a cluster center to each structure of interest. | ||
| + | |||
| + | |||
Multi-Contrast MR images are collected and seed points for each region of interest are taken as input. Cluster center and standard deviation are calculated for each ROI based on pixel intensities of the seed points. The pixels are clustered based on different pixel intensity values in multiple MR images to the nearest cluster center radius. | Multi-Contrast MR images are collected and seed points for each region of interest are taken as input. Cluster center and standard deviation are calculated for each ROI based on pixel intensities of the seed points. The pixels are clustered based on different pixel intensity values in multiple MR images to the nearest cluster center radius. | ||
Revision as of 01:02, 4 January 2010
Home < 2010 Winter Project Week Musco Skeletal Segmentation
Ideal Spgr Fat MR image
Ideal Spgr Water MR image
Segmentation Output
Bones
Cartilage
SpgrWater_Hip
SpgrFat_Hip
Hip Output
Key Investigators
- Stanford: Harish Doddi, Saikat Pal, Scott Delp
- Kitware: Luis Ibanez
Objective
The aim of this project is to develop a methodology for rapid segmentation of knee structures from magnetic resonance (MR) images for subject-specific modeling. The overall goal can be broken down into two specific objectives -
1. Rapid segmentation of target structures into label maps.
2. Generation of simulation-ready models from existing atlas and label maps of individual structures.
Approach, Plan
Approach:
Objective 1: We have adopted a multi-contrast MR methodology to segment knee bones and cartilage structures. The algorithm utilizes tissue intensity information from multiple MR contrasts to segment structures of interest. Inputs to the algorithm included n registered MR image sets. The algorithm created an n-dimensional space of voxel intensities associated with the n image sets. The user assigned seed points to the structures of interest, and the algorithm assigned a cluster center to each structure of interest.
Multi-Contrast MR images are collected and seed points for each region of interest are taken as input. Cluster center and standard deviation are calculated for each ROI based on pixel intensities of the seed points. The pixels are clustered based on different pixel intensity values in multiple MR images to the nearest cluster center radius.
For detailed approach, please visit http://www.na-mic.org/Wiki/index.php/Stanford_Simbios_group
Plan:
a. Smooth the existing segmented label maps
b. Build models for bones and cartilage from the existing segmented label maps.
Progress
Finished segmenting different regions of interest like bones, cartilage etc.
Created label maps from existing segmented output.
