xfetus - python-based library for synthesis of ultrasound fetal imaging (👶 🧠 🤖) ⚠️ WIP ⚠️

xfetus is a python-based library to syntheses fetal ultrasound images using GAN, transformers and diffusion models. It also includes methods to quantify the quality of image synthesis (FID, PSNR, SSIM, and Visual Turing Tests) along with related publications.

Installation

pip install xfetus

Examples

See examples path with further instructions to run notebooks for data curation, classification, and models.

Development

You can develop locally:

Generate your SSH keys as suggested here (or here)
Clone the repository by typing (or copying) the following line in a terminal at your selected path in your machine:

cd && mkdir -p $HOME/repositories/budai4medtech && cd  $HOME/repositories/budai4medtech
git clone git@github.com:budai4medtech/xfetus.git

Presentation

Good practices in AI/ML for Ultrasound Fetal Brain Imaging Synthesis for the deep learning and computer vision Journal Club on 1st of June 2023, 15:00 GMT.

Articles

Citations

BibTeX to cite

@misc{iskandar-midl2023,
      author={
      	Michelle Iskandar and 
      	Harvey Mannering and 
      	Zhanxiang Sun and 
      	Jacqueline Matthew and 
      	Hamideh Kerdegari and 
      	Laura Peralta and 
      	Miguel Xochicale},
      title={Towards Realistic Ultrasound Fetal Brain Imaging Synthesis}, 
      year={2023},
      eprint={2304.03941},
      archivePrefix={arXiv},
      publisher = {arXiv},
      url = {https://arxiv.org/abs/2304.03941},
      copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

@misc{bautista-miua2022,
  author = {Bautista, Thea and 
            Matthew, Jacqueline and 
            Kerdegari, Hamideh and 
            Peralta, Laura and 
            Xochicale, Miguel},
  title = {Empirical Study of Quality Image Assessment for Synthesis of Fetal Head Ultrasound Imaging with DCGANs},  
  year = {2022},
  eprint={2206.01731},
  archivePrefix={arXiv},
  publisher = {arXiv},
  url = {https://arxiv.org/abs/2206.01731},
  copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}