A fuzzy fine-tuned model for COVID-19 diagnosis

Esmi, Nima; Golshan, Yasaman; Asadi, Sara; Shahbahrami, A.; Gaydadjiev, G.

doi:10.1016/j.compbiomed.2022.106483

A fuzzy fine-tuned model for COVID-19 diagnosis

Title

A fuzzy fine-tuned model for COVID-19 diagnosis

Author

Esmi, Nima (University Medical Center Groningen)
Golshan, Yasaman (University of Guilan)
Asadi, Sara (University of Guilan)
Shahbahrami, A. (TU Delft Computer Engineering; University Medical Center Groningen; University of Guilan)
Gaydadjiev, G. (TU Delft Quantum Circuit Architectures and Technology; University Medical Center Groningen)

Date

2023

Abstract

The COVID-19 disease pandemic spread rapidly worldwide and caused extensive human death and financial losses. Therefore, finding accurate, accessible, and inexpensive methods for diagnosing the disease has challenged researchers. To automate the process of diagnosing COVID-19 disease through images, several strategies based on deep learning, such as transfer learning and ensemble learning, have been presented. However, these techniques cannot deal with noises and their propagation in different layers. In addition, many of the datasets already being used are imbalanced, and most techniques have used binary classification, COVID-19, from normal cases. To address these issues, we use the blind/referenceless image spatial quality evaluator to filter out inappropriate data in the dataset. In order to increase the volume and diversity of the data, we merge two datasets. This combination of two datasets allows multi-class classification between the three states of normal, COVID-19, and types of pneumonia, including bacterial and viral types. A weighted multi-class cross-entropy is used to reduce the effect of data imbalance. In addition, a fuzzy fine-tuned Xception model is applied to reduce the noise propagation in different layers. Quantitative analysis shows that our proposed model achieves 96.60% accuracy on the merged test set, which is more accurate than previously mentioned state-of-the-art methods.

Subject

Blind/Referenceless image spatial quality evaluator
COVID-19
Deep learning
Fuzzy pooling
Weighted multi-class cross-entropy

To reference this document use:

http://resolver.tudelft.nl/uuid:0ad7e254-d858-4914-a0e1-744ac32afecf

DOI

https://doi.org/10.1016/j.compbiomed.2022.106483

Embargo date

2023-06-26

ISSN

0010-4825

Source

Computers in Biology and Medicine, 153