Alzheimer’s Disease Detection Web App

A web application for predicting stages of Alzheimer’s disease using a deep learning model. The app accepts an MRI image and outputs the predicted stage of Alzheimer’s disease.

---

Features

• Upload an MRI image in .jpg format.
• Predicts one of the following stages of Alzheimer’s disease:
  • Non Demented
  • Very Mild Demented
  • Mild Demented
  • Moderate Demented
• Displays the prediction result in a user-friendly interface.
• Provides confidence scores for each class.
• Generates a Grad-CAM visualization to explain predictions.

Deployed Application

The web application is deployed and accessible at:

http://195.201.113.83:8000

Requirements

• Python 3.8+
• Flask

---

Setup and Installation

Download Trained Models

Due to file size limitations, the .h5 file for the Trained model is not included directly in the repository. Instead, it has been uploaded to Google Drive.

1. Download the Trained model from the following link: Download Trained Models

2. Extract the zip file into the models/ directory:

   unzip models.zip -d models/

Ensure that the extracted .h5 file is located at models/fine_tuned_vgg16.h5.

---

Linux

1. Clone the Repository:

   git clone <repository-url>
   cd <repository-folder>

2. Create a Virtual Environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install Dependencies:

   pip install -r requirements.txt

4. Download and Extract Model: Follow the steps in the Download Trained Models section.

5. Run the Flask App:

   flask run --host=0.0.0.0 --port=8000

6. Access the Web App: Open your browser and navigate to http://127.0.0.1:8000/ or the deployed IP if hosting externally.

---

Windows

1. Clone the Repository:

   git clone <repository-url>
   cd <repository-folder>

2. Create a Virtual Environment:

   python -m venv venv
   venv\Scripts\activate

3. Install Dependencies:

   pip install -r requirements.txt

4. Download and Extract Model: Follow the steps in the Download Trained Models section.

5. Run the Flask App:

   flask run --host=0.0.0.0 --port=8000

6. Access the Web App: Open your browser and navigate to http://127.0.0.1:8000/ or the deployed IP if hosting externally.

---

Project Structure

<repository-folder>/
|
|-- app.py             # Main Flask application
|-- templates/         # HTML templates
|-- static/            # Static files (CSS, JS, images)
|-- model/             # Trained models files
|-- notebooks/         # Jupyter notebooks used for model training
|-- requirements.txt   # Python dependencies