Semantic Segmentation of DFU Images

Overview

This repository contains code for performing semantic segmentation on Diabetic Foot Ulcer (DFU) images. It includes two primary experiments:

1. Central Experiment: This approach utilizes a centralized machine learning model.
2. Federated Experiment: This experiment demonstrates a federated learning approach to the same problem.

Installation

Prerequisites

• Python 3.8
• Pip package manager

Setup

1. Clone the repository:

git clone https://github.com/Mahdi-s/dfu_image_segmentation.git

3. Install the required dependencies:

pip install -r requirements.txt

Dataset download

Please download the dataset of DFU images provided by Medetec from the following link: DFU dataset

Usage

Central Experiment

The central_experiment.ipynb notebook contains the code for the central experiment. To run this notebook:

1. Navigate to the cloned repository directory.
2. Open the Jupyter Notebook:

jupyter notebook central_experiment.ipynb

3. Run the cells in the notebook to perform the experiment.

Federated Experiment

The federated_experiment.ipynb notebook includes the code for the federated learning experiment. Follow these steps to run it:

1. Ensure the requirements are installed as mentioned above.
2. Open the Jupyter Notebook:

jupyter notebook federated_experiment.ipynb

3. Execute the cells within the notebook to see federated learning in action.

Contributing

Contributions, issues, and feature requests are welcome.

License

Distributed under the MIT License.

Contact

Mahdi Saeedi - mahdisaeediv@gmail.com