https://github.com/fitushar/brain-tissue-segmentation-using-expectation-maximization

Medical Image Segmentation and Applications (MISA) LAB task.
https://github.com/fitushar/brain-tissue-segmentation-using-expectation-maximization

brain-tissue-segmentation dice expectation-maximization lab-task labtasks misa seg slice

Last synced: 3 months ago
JSON representation

Medical Image Segmentation and Applications (MISA) LAB task.

• Host: GitHub
• URL: https://github.com/fitushar/brain-tissue-segmentation-using-expectation-maximization
• Owner: fitushar
• Created: 2018-11-11T15:43:23.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-01-12T22:41:47.000Z (over 6 years ago)
• Last Synced: 2025-01-01T15:43:59.279Z (5 months ago)
• Topics: brain-tissue-segmentation, dice, expectation-maximization, lab-task, labtasks, misa, seg, slice
• Language: Python
• Size: 17 MB
• Stars: 1
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Brain-Tissue-Segmentation-Using-Expectation-Maximization

Medical Image Segmentation and Applications (MISA) LAB task.

Functions Used in two codes::

1. show_slice(img, slice_no):

    

    Inputs: Name of the Image Array, img=name.get_fdata()

            Slice number you want to knoe,Slice no = 24

    output: Plot Image.

2. gmm(x, mean, cov):

    

    Inputs:

        x (numpy.ndarray): nxd dimentional array. where n= number of samples

                                                        d= dimention

        mean (numpy.ndarray): d-dimentional mean value.

        cov (numpy.ndarray): dxd dimentional covariance matrix.

    

    output:

        (numpy.ndarray): Gaussian mixture for every point in feature space.

        

3. dice_similarity(Seg_img, GT_img,state):

     

     Inputs:

        Seg_img (numpy.ndarray): Segmented Image.

        GT_img (numpy.ndarray): Ground Truth Image.

        State: "nifti" if the images are nifti file

               "arr"   if the images are an ndarray

    

      output:

        Dice Similarity Coefficient: dice_CSF, dice_GM, dice_WM.

        

4. Dice_and_Visualization_of_one_slice(Seg_img, GT_img,state,number_of_slice):

    """Example Use: Dice_and_Visualization_of_one_slice(Seg,Label_img,"arr",30)"""

         

     Inputs:

        Seg_img (numpy.ndarray): Segmented Image.

        GT_img (numpy.ndarray): Ground Truth Image.

        State: "nifti" if the images are nifti file

               "arr"   if the images are an ndarray

    output:

        Dice Similarity Coefficient: dice_CSF, dice_GM, dice_WM.

        Ploting image