# A Two-Stage Federated Transfer Learning Framework in Medical Images Classification on Limited Data: A COVID-19 Case Study

arXiv: https://arxiv.org/abs/2203.12803 · HTML: https://mlsanity.com/paper/2203.12803/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 75 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Can AI help in screening Viral and COVID-19 pneumonia?](https://mlsanity.com/paper/2003.13145/) (2020)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks](https://mlsanity.com/paper/2003.10849/) (2020)
- [Blockchain-Federated-Learning and Deep Learning Models for COVID-19 detection using CT Imaging](https://mlsanity.com/paper/2007.06537/) (2020)
- [Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge](https://mlsanity.com/paper/2101.07511/) (2021)
- [Dynamic Fusion based Federated Learning for COVID-19 Detection](https://mlsanity.com/paper/2009.10401/) (2020)
- [Experiments of Federated Learning for COVID-19 Chest X-ray Images](https://mlsanity.com/paper/2007.05592/) (2020)
- [Federated Learning for COVID-19 Detection with Generative Adversarial Networks in Edge Cloud Computing](https://mlsanity.com/paper/2110.07136/) (2021)
- [COVID-19 Classification of X-ray Images Using Deep Neural Networks](https://mlsanity.com/paper/2010.01362/) (2020)

## Built on by (most cited first, 2 of 2)

- [FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification](https://mlsanity.com/paper/2302.12662/) (2023)
- [Model-Contrastive Federated Domain Adaptation](https://mlsanity.com/paper/2305.10432/) (2023)

## Abstract (arXiv)

COVID-19 pandemic has spread rapidly and caused a shortage of global medical resources. The efficiency of COVID-19 diagnosis has become highly significant. As deep learning and convolutional neural network (CNN) has been widely utilized and been verified in analyzing medical images, it has become a powerful tool for computer-assisted diagnosis. However, there are two most significant challenges in medical image classification with the help of deep learning and neural networks, one of them is the difficulty of acquiring enough samples, which may lead to model overfitting. Privacy concerns mainly bring the other challenge since medical-related records are often deemed patients' private information and protected by laws such as GDPR and HIPPA. Federated learning can ensure the model training is decentralized on different devices and no data is shared among them, which guarantees privacy. However, with data located on different devices, the accessible data of each device could be limited. Since transfer learning has been verified in dealing with limited data with good performance, therefore, in this paper, We made a trial to implement federated learning and transfer learning techniques using CNNs to classify COVID-19 using lung CT scans. We also explored the impact of dataset distribution at the client-side in federated learning and the number of training epochs a model is trained. Finally, we obtained very high performance with federated learning, demonstrating our success in leveraging accuracy and privacy.