https://github.com/ap6yc/mri-tl-ml
A study of the efficacy of transfer learning methods versus "traditional" machine learning methods (i.e., separate feature extraction and learner architectures).
https://github.com/ap6yc/mri-tl-ml
Last synced: over 1 year ago
JSON representation
A study of the efficacy of transfer learning methods versus "traditional" machine learning methods (i.e., separate feature extraction and learner architectures).
- Host: GitHub
- URL: https://github.com/ap6yc/mri-tl-ml
- Owner: AP6YC
- License: mit
- Created: 2020-12-07T18:00:46.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2020-12-11T22:32:00.000Z (over 5 years ago)
- Last Synced: 2025-02-02T15:31:27.828Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 6.21 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# MRI-TL-ML
A study of the efficacy of transfer learning methods versus "traditional" machine learning methods (i.e., separate feature extraction and learner architectures).
This project is a submission of Sasha Petrenko for his MATH5001: Mathematics of Medical Imaging course and the Missouri University of Science and Technology.
## Usage
1. Download the dataset at https://figshare.com/articles/dataset/brain_tumor_dataset/1512427
2. Extract all of the data to a single folder.
3. Preprocess the images with the script `matlab/preprocessing.m`, pointing to the correct directory.
4. Create a python environment (e.g., `conda`) and install the requirements under `requirements.txt`.
5. Run the notebook `notebooks/tl-mri.ipyng`.
6. View the figures and results in `results/`.
## Author
* Sasha Petrenko