Models:
Samuel Callahan
SCallahan/
Brain-MRI-Segmentation
0
Downloads: 1
Diff of /README.md [8ff467] .. [85e292]

Switch to unified view

a/README.md b/README.md
1 
# Brain MRI Segmentation
 1 
# Brain MRI Segmentation
2 

  2
  





  3
  
The method we use comes from this paper:

  3
  
The method we use comes from this paper:






  4
  
[From neonatal to adult brain

  4
  
[From neonatal to adult brain






  5
  
mr image segmentation in a few seconds using 3d-like fully convolutional network and transfer learning](https://www.lrde.epita.fr/wiki/Publications/xu.17.icip)

  5
  
mr image segmentation in a few seconds using 3d-like fully convolutional network and transfer learning](https://www.lrde.epita.fr/wiki/Publications/xu.17.icip)





  6
  

  6
  





  7
  
Soft tissue segmentation.

  7
  
Soft tissue segmentation.





  8
  

  8
  





  9
  
This project was part of the Smart India Hackathon 2019 in which our team was the runner ups.

  9
  
This project was part of the Smart India Hackathon 2019 in which our team was the runner ups.






  10
  
The problem statement was **Brain MRI Segmentation using Machine Learning** given by **Department of Atomic Energy, Government of India**

  10
  
The problem statement was **Brain MRI Segmentation using Machine Learning** given by **Department of Atomic Energy, Government of India**





  11
  

  11
  





  12
  
This project could be used by medical professionals for medical purposes.

  12
  
This project could be used by medical professionals for medical purposes.





  13
  

  13
  





  14
  
![DAE](dae.png)

  14
  
![DAE](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/dae.png?raw=true)





  15
  

  15
  





  16
  
## Preprocessing

  16
  
## Preprocessing





  17
  

  17
  





  18
  
![preprocess](pres.jpg)

  18
  
![preprocess](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/pres.jpg?raw=true)





  19
  

  19
  





  20
  

  20
  





  21
  
![architecture](archi.jpg)

  21
  
![architecture](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/archi.jpg?raw=true)





  22
  

  22
  





  23
  
![VGG16](vgga.jpg)

  23
  
![VGG16](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/vgga.jpg?raw=true)





  24
  

  24
  





  25
  
## Why our model?

  25
  
## Why our model?





  26
  

  26
  





  27
  
• Since we are using transfer learning, a novel approach in this field, so we do not need to train our model from scratch which makes it very fast in training in comparison to other models.

  27
  
• Since we are using transfer learning, a novel approach in this field, so we do not need to train our model from scratch which makes it very fast in training in comparison to other models.





  28
  

  28
  





  29
  
• Stacking 3 successive 2D slices allows us to make a RGB image, another novel idea.This representation enables us to incorporate some 3D information, while avoiding the expensive computational and memory requirements of fully 3D FCN.

  29
  
• Stacking 3 successive 2D slices allows us to make a RGB image, another novel idea.This representation enables us to incorporate some 3D information, while avoiding the expensive computational and memory requirements of fully 3D FCN.





  30
  

  30
  





  31
  
• Using Transfer Learning we do not need many training images, so we could train our model very well only on a few training images.

  31
  
• Using Transfer Learning we do not need many training images, so we could train our model very well only on a few training images.





  32
  

  32
  





  33
  
• We are also using traditional data augmentation methods like rotating, cropping and flipping the images in training set for improving our model.

  33
  
• We are also using traditional data augmentation methods like rotating, cropping and flipping the images in training set for improving our model.





  34
  

  34
  





  35
  
## GUI and giving input

  35
  
## GUI and giving input





  36
  

  36
  





  37
  
![GUI](working.gif)

  37
  
![GUI](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/working.gif?raw=true)





  38
  

  38
  





  39
  

  39
  





  40
  
## Output

  40
  
## Output





  41
  

  41
  





  42
  
![gui](images/screen1.png)

  42
  
![gui](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/tree/master/images/screen1.png?raw=true)





  43
  

  43
  





  44
  
## Tumour prediction

  44
  
## Tumour prediction





  45
  

  45
  





  46
  
![tumour](pred2.jpg)

  46
  
![tumour](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/pred2.jpg?raw=true)





  47
  

  47
  





  48
  
## Other regions

  48
  
## Other regions





  49
  

  49
  





  50
  
![](pred1.jpg)

  50
  
![](https://github.com/vaibhavshukla182/Brain-MRI-Segmentation/blob/master/pred1.jpg?raw=true)





  51
  

  51
  





  52
  
## Contributors 

  52
  
## Contributors 






  53
  
[Vaibhav Shukla](https://github.com/vaibhavshukla182/)  

  53
  
[Vaibhav Shukla](https://github.com/vaibhavshukla182/)  






  54
  
[Abhijeet Singh](https://github.com/abhi40308)  

  54
  
[Abhijeet Singh](https://github.com/abhi40308)  






  55
  
[Omkar Ajnadkar](https://github.com/blackbird71SR)  

  55
  
[Omkar Ajnadkar](https://github.com/blackbird71SR)  






  56
  
[Govind Singh Rajpurohit](https://github.com/govind51)  

  56
  
[Govind Singh Rajpurohit](https://github.com/govind51)  






  57
  
[Ratna Priya](https://github.com/Ratna04priya)  

  57
  
[Ratna Priya](https://github.com/Ratna04priya)  






  58
  
[Sanath Singavarapu](https://github.com/Killer2499)  

  58
  
[Sanath Singavarapu](https://github.com/Killer2499)