Enhanced MRI Brain Tumor Detection and Classification via Topological Data Analysis and Low-Rank Tensor Decomposition
This repository is the official code for the paper "Enhanced MRI Brain Tumor Detection and Classification via Topological Data Analysis and Low-Rank Tensor Decomposition" by Serena Grazia De Benedictis, Grazia Gargano and Gaetano Settembre.
Link to full article here.
If you find the project codes useful for your research, please consider citing
@ARTICLE{braintumor_tda,
author={De Benedictis, Serena Grazia and Gargano, Grazia and Settembre, Gaetano},
journal={Journal of Computational Mathematics and Data Science},
title={Enhanced MRI Brain Tumor Detection and Classification via Topological Data Analysis and Low-Rank Tensor Decomposition},
year={2024},
volume={},
number={},
pages={},
keywords={Brain tumors classification, Brain tumors detection, Magnetic resonance imaging, Topological data analysis, Machine learning, low-rank approximation, Tucker Decomposition},
doi={}
}
The code relies on the following Python 3.9.XX + libs. Packages needed are:
- Ripser
- Tensorly
- OpenCV
- Numpy
- Matplotlib
- Scikit-learn
All dependencies in requirements.txt
Create python env and install all needed dependencies:
conda create -n "braintumor" python=3.9
conda activate braintumor
pip install -r requirements.txt
The dataset used is available here (from Kaggle.com).
The entire content of this repository is released as free (as in "libre") under the GNU GPL v3 only License or the CC BY-SA 4.0 License as follows:
- All the source code is released under the GNU GPL v3 only;
- All the content (either textual, visual or audio) is released under the CC BY-SA 4.0.