Covid-19 Early Detection for Imbalanced or Low number of Data using a Regularized Cost-Sensitive CapsNet

Congrats and thanks to my colleagues, Dr. Malihe Javidi, Dr. Sara Naybandi Atashi, and Mr. Saeid Abbaasi, for our recently accepted paper about Covid-19. Our paper with the title of “Covid-19 Early Detection for Imbalanced or Low number of Data using a Regularized Cost-Sensitive CapsNet” is accepted for publication in prestigious and outstanding Scientific Reports – Nature publication.

 

Abstract

With the presence of novel coronavirus disease at the end of 2019, several approaches were proposed to help physicians detect the disease, such as using deep learning to recognize lung involvement based on the pattern of pneumonia. These approaches rely on analyzing the CT images and exploring the Covid-19 pathologies in the lung. Most of the successful methods are based on the deep learning technique, which is state-of-the-art. Nevertheless, the big drawback of the deep approaches is their need for many samples, which is not always possible. This work proposes a combined deep architecture that benefits both employed architectures of DenseNet and CapsNet. To more generalize the deep model, we propose a regularization term with much fewer parameters. The network convergence significantly improved, especially when the number of training data is small. We also propose a novel Cost-sensitive loss function for imbalanced data that makes our model feasible for the condition with a limited number of positive data. Our novelties make our approach more intelligent and potent in real-world situations with imbalanced data, popular in hospitals. We analyzed our approach on two publicly available datasets, HUST and Covid-CT, with different protocols. In the first protocol of HUST, we followed the original paper setup and outperformed it. With the second protocol of HUST, we show our approach superiority concerning imbalanced data. Finally, with three different validations of the Covid-CT, we provide evaluations in the presence of a low number of data along with a comparison with state-of-the-art.

 

Link to the paper on the nature.com: https://doi.org/10.1038/s41598-021-97901-4 (Open access)

Direct link to the paper on the nature.com: www.nature.com/articles/s41598-021-97901-4 (Open access)

The source code on GitHub: https://github.com/Javidi31/COVID19_Reg_Caps_Dense/tree/master

 

 

 Please cite our paper if you find it useful

Covid-19 Early Detection for Imbalanced or Low number of Data using a Regularized Cost-Sensitive CapsNet
Malihe Javidi, Saeid Abbaasi, Sara Naybandi Atashi, Mahdi Jampour
Sci Rep 11, (2021).


Home  |  Contact me  |  About me  | Mahdi Jampour 2008 ©