# MRI_Image_Classifier

**Repository Path**: dididi_0924/MRI_Image_Classifier

## Basic Information

- **Project Name**: MRI_Image_Classifier
- **Description**: Re-Training an established Neural Network to classify MRI Image Data
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-07-01
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Tensorflow Multiple Scan vs. Single Scan MRI Image Classifier

Use this classifier to label images taken with Magnetic Resonance Imaging (MRI) that are either a single scan or a tile of multiple scans. TensorFlow for Poets: [CodeLab](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/?utm_campaign=chrome_series_machinelearning_063016&utm_source=gdev&utm_medium=yt-desc#0)

![imageOne](glioblastoma/single/Z.jpg)
![imageTwo](glioblastoma/multiple/images.jpg)

## Requirements

* [docker](https://www.docker.com/products/docker-toolbox)

## Usage 

1. Start the docker image `docker run -it -v ~/projects/dump/tf_files/:/tf_files/ gcr.io/tensorflow/tensorflow:latest-devel`
2. Run the label_image script to label the image. `python /tf_files/label_image.py <path_to_file>`

## Results

Single MRI Scan Image Test

![acc](results/Test_Single.png)

Multiple MRI Scan Image Test

![acc](results/Test_Multiple.png)


## Accuracy

![acc](results/Test_Accuracy.png)