This repo contains all the code base for my final year project. The Brain MRI Classification. This project aims to build an accurate and robust ML model for classification of normal and abnormal brain MRI images. The basic idea is to use Image Processing as well as Machine Learning Algorithms to implment a novel and improved model; which surpasses other state of the art models in literature. This repository has jupyter notebooks - providing detail notes on the topics - as well as MATLAB codes for implementing Image Processing algorithms to evaluate the best ones for the actual model.
- Basic Conversions, Reading and writing to images [chpt1-3]
- Image Filters and Image Enchancement (transformations) [chpt4-5]
- Filters preprocessing
- Transforms preprocessing
- Feature Extractions
- Basic Image handling, Filters and Feature Extraction
- Medain, Skewness, Standard Deviation, Kurtosis, Entropy
- Artificial Neurla Network
- Red, Green, Blue channel saved model
- Confusion matrix for testing and Training
- model
- Decision Tree
- Red, Green, Blue channel saved model
- Confusion matrix for testing and Training
- model
- Support Vector Machine
- Red, Green, Blue channel saved model
- Confusion matrix for testing and Training
- model
- Random Forest
- Red, Green, Blue channel saved model
- Confusion matrix for testing and Training
- model
- k-NN
- Red, Green, Blue channel saved model
- Confusion matrix for testing and Training
- model
- Naive Bayes
- Red, Green, Blue channel saved model
- Confusion matrix for testing and Training
- model
- Confusion matrix
- F1-score, Accuracy, Precision and Recall were calculated.
- Performance is evaluated on output from majority vote and the y_test
-
- The Dataset is three files (red, green and blue) in excel as well as csv formats. And a Labels file with the classes.
- For the model, we gave all three files to three classifiers alone with the labels file
- All the algorithms were give the same data files
-
OS X & Linux:
git clone https://github.com/qalmaqihir/BrainMRIProject.gitEach Jupyter notebook contains sufficeint information about the topics covered. While the MATLAB code has comments to guide the reader about the processes.
For more about each topic and the model, please refer to the Wiki.
Each commit has its own history...
Jawad Haider – @JawadHa49605912 – [email protected]
Distributed under the MIT license. See LICENSE for more information or check here.
- Fork it (https://github.com/qalmaqihir/BrainMRIProject/fork)
- Create your feature branch (
git checkout -b feature/fooBar) - Commit your changes (
git commit -am 'Add some fooBar') - Push to the branch (
git push origin feature/fooBar) - Create a new Pull Request
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent