https://github.com/cosbidev/vce_cesm

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
Last synced: 10 months ago · JSON representation

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
Created about 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License

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

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)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels