Alzheimer Prediction

Given a MRI (Magnetic Resonance Image) of the human brain, returns the probability of contracting Alzheimer's disease in the coming years.

Table of Contents

• Overview
• Usage
• Contributing
• Team
• License

Overview

The early diagnosis of Alzheimer’s Disease (AD) and its prodromal form, Mild Cognitive Impairment (MCI), has been the subject of extensive research in recent years. Some recent studies have shown promising results in the diagnosis of AD and MCI using structural Magnetic Resonance Imaging (MRI) scans. In this paper, we propose the use of a Convolutional Neural Network (CNN) in the detection of AD and MCI. In particular, we used the 27-layered AlexNet for the binary classification on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset in a such particular way that allow us to achieve an overall accuracy up to 75% and outperform several classifiers from other studies. We tried 4 different methods:

• Method 1
• Method 2
• Method 3
• Method 4

Usage

Just download the code and the dataset from this repo and execute it with MATLAB.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Team

Stefano Ivancich	Luca Masiero
github.com/ivaste	github.com/TyllanDrake
Thesis (Method 4)	Thesis (Methods 1-3)
Presentation (Method 4)	Presentation (Methods 1-3)

License

• MIT license