Cortical thickness
Budget: ₹3,000 – ₹4,200 INR
Outline: In this challenge you will develop an algorithm to estimate cortical thickness map from a raw T1-weighted image. Cortical thickness map is the thickness of the gray matter of the brain at every point. It is defined as the distance between the white matter surface and the pial surface
Tips:
• Use nibabel libraries to load nifti image into python
• You will probably want to segment the white matter first. This will give you the starting point for your thickness estimation algorithm.
• Once you have the white matter segmentation, decide how you will go about estimating thickness. Something like the following:
o Find a vector orthogonal to the white matter surface
o Cast the vector outwards
o Use some heuristic to decide where the vector meets the pial surface (cortical thickness is then given by vector length
Summary: load raw_t1_subject_02.nii.gz into python. Segment the gray and white matter. Use some algorithm to find the cortical thickness at each point in the gray matter. Label all gray matter voxels with the cortical thickness value at that point. Output the labeled image (like in figure 02).
Tips:
• Use nibabel libraries to load nifti image into python
• You will probably want to segment the white matter first. This will give you the starting point for your thickness estimation algorithm.
• Once you have the white matter segmentation, decide how you will go about estimating thickness. Something like the following:
o Find a vector orthogonal to the white matter surface
o Cast the vector outwards
o Use some heuristic to decide where the vector meets the pial surface (cortical thickness is then given by vector length
Summary: load raw_t1_subject_02.nii.gz into python. Segment the gray and white matter. Use some algorithm to find the cortical thickness at each point in the gray matter. Label all gray matter voxels with the cortical thickness value at that point. Output the labeled image (like in figure 02).