Skip to content

Latest commit

 

History

History
42 lines (34 loc) · 1.59 KB

README.md

File metadata and controls

42 lines (34 loc) · 1.59 KB
Raw

Performance Evaluation of Deep Learning Models for Image Classification Over Small Datasets: Diabetic Foot Case Study

This project is designed to replicate the experiments of the paper "Performance Evaluation of Deep Learning Models for Image Classification Over Small Datasets: Diabetic Foot Case Study". Because the data used in the work is not public, this repository uses MedMNIST Breast Ultrasound as dataset. In order to reproduce the data scarcity problem, a random undersampling is applied to the dataset.

Prerequisites

  • Anaconda
  • Git
  • PyTorch
    • version 1.8.0 or above
  • Torchvision
  • Matplotlib
  • Pandas

Submodules

This repository contains the following submodules:

In order to download the submodules in the cloning process, use the following instruction:

git clone --recurse-submodules [repository url]

References

If you find our library useful in your research, please consider citing us:

@article{hernandez2022performance,
  title={Performance Evaluation of Deep Learning Models for Image Classification Over Small Datasets: Diabetic Foot Case Study},
  author={Hernandez-Guedes, Abian and Santana-Perez, Idafen and Arteaga-Marrero, Natalia and Fabelo, Himar and Callico, Gustavo M and Ruiz-Alzola, Juan},
  journal={IEEE Access},
  volume={10},
  pages={124373--124386},
  year={2022},
  publisher={IEEE}
}

TODO

  • Explaining that MedMNIST Breast Ultrasound is used
  • Explanation of the notebooks