https://github.com/cosbidev/vce_cesm
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
✓DOI references
Found 2 DOI reference(s) in README -
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.2%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: cosbidev
- License: mit
- Language: Python
- Default Branch: main
- Size: 199 KB
Statistics
- Stars: 2
- Watchers: 0
- Forks: 0
- Open Issues: 1
- Releases: 0
Metadata Files
README.md
A Deep Learning Approach for Virtual Contrast Enhancement in Contrast Enhanced Spectral Mammography
This repository contains the code used to run experiments related to Virtual Contrast Enhancement CESM.
Installation
Clone the repository
bash
git clone
cd VCE_CESM
Install dependencies
Using virtualenv
1) First, create a Python virtual environment (optional) using the following command:
bash
python -m venv ve-vce_cesm
2) Activate the virtual environment using the following command:
bash
source ve-vce_cesm/bin/activate
3) Install the dependencies using the following command:
bash
pip install -r requirements.txt
The code is organized into three folders: 1) "configs": contains YAML files used to set experiment parameters. 2) "data": contains "raw" and "processed" folders. The "processed" folder contains TXT files with paths to dataset images, while the "raw" folder should contain images without preprocessing. 3) "src": contains "model" and "utils" folders. The "model" folder includes subfolders for Autoencoder, CycleGAN, and PixPix, each containing specific model code. The "utils" folder includes the "utils.py" generic utility code and the "util_data.py" code for image processing.
For each model (Autoencoder, CycleGAN, and Pix2Pix), you can run training, transfer learning, or testing code. These codes are located in the "src -> model -> Autoencoder/CycleGAN/Pix2Pix" folders. 1) Running the training code trains the model on the public dataset. Experiment parameters can be set using the configuration files "autoencodertrain.yaml", "cyclegantrain.yaml", or "pix2pixtrain.yaml". 2) Running the transfer learning code loads a pre-trained model on the public dataset and retrains it on the FPUCBM dataset. Experiment parameters, including the pre-trained model to load, can be set using the configuration files "autoencodertranlearn.yaml", "cyclegantranlearn.yaml", or "pix2pixtranlearn.yaml". 3) Running the test code tests the trained model on the desired dataset. Experiment parameters, including the test dataset, can be set using the configuration files "autoencodertest.yaml", "cyclegantest.yaml", or "pix2pixtest.yaml".
Contact
For questions and comments, feel free to contact: aurora.rofena@unicampus.it, valerio.guarrasi@unicampus.it
Citation
If you use our code in your study, please cite as:
bash
@article{rofena2024deep,
title={A deep learning approach for virtual contrast enhancement in contrast enhanced spectral mammography},
author={Rofena, Aurora and Guarrasi, Valerio and Sarli, Marina and Piccolo, Claudia Lucia and Sammarra, Matteo and Zobel, Bruno Beomonte and Soda, Paolo},
journal={Computerized Medical Imaging and Graphics},
pages={102398},
year={2024},
publisher={Elsevier}
}
You can download the article at:
A Deep Learning Approach for Virtual Contrast Enhancement in Contrast Enhanced Spectral Mammography
License
The code is distributed under a MIT License
Owner
- Name: CoSBi.dev
- Login: cosbidev
- Kind: organization
- Location: Università Campus Bio-Medico di Roma
- Website: https://www.unicampus.it/ricerca/unita-di-ricerca/sistemi-di-elaborazione-e-bioinformatica
- Repositories: 3
- Profile: https://github.com/cosbidev
GitHub Events
Total
- Issues event: 2
- Watch event: 2
Last Year
- Issues event: 2
- Watch event: 2
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 1
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 1
- Total pull request authors: 0
- Average comments per issue: 0.0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 1
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 1
- Pull request authors: 0
- Average comments per issue: 0.0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- LuoJWstudent (1)
- emrekeles-arch (1)