Hybrid-COVID: a novel hybrid 2D/3D CNN based on cross-domain adaptation approach for COVID-19 screening from chest X-ray images.

Khaled Bayoudh,Fayçal Hamdaoui,Abdellatif Mtibaa

doi:10.1007/s13246-020-00957-1

Khaled Bayoudh, Fayçal Hamdaoui + Show 1 more

Open Access

https://doi.org/10.1007/s13246-020-00957-1

Copy DOI

Abstract

The novel Coronavirus disease (COVID-19), which first appeared at the end of December 2019, continues to spread rapidly in most countries of the world. Respiratory infections occur primarily in the majority of patients treated with COVID-19. In light of the growing number of COVID-19 cases, the need for diagnostic tools to identify COVID-19 infection at early stages is of vital importance. For decades, chest X-ray (CXR) technologies have proven their ability to accurately detect respiratory diseases. More recently, with the availability of COVID-19 CXR scans, deep learning algorithms have played a critical role in the healthcare arena by allowing radiologists to recognize COVID-19 patients from their CXR images. However, the majority of screening methods for COVID-19 reported in recent studies are based on 2D convolutional neural networks (CNNs). Although 3D CNNs are capable of capturing contextual information compared to their 2D counterparts, their use is limited due to their increased computational cost (i.e. requires much extra memory and much more computing power). In this study, a transfer learning-based hybrid 2D/3D CNN architecture for COVID-19 screening using CXRs has been developed. The proposed architecture consists of the incorporation of a pre-trained deep model (VGG16) and a shallow 3D CNN, combined with a depth-wise separable convolution layer and a spatial pyramid pooling module (SPP). Specifically, the depth-wise separable convolution helps to preserve the useful features while reducing the computational burden of the model. The SPP module is designed to extract multi-level representations from intermediate ones. Experimental results show that the proposed framework can achieve reasonable performances when evaluated on a collected dataset (3 classes to be predicted: COVID-19, Pneumonia, and Normal). Notably, it achieved a sensitivity of 98.33%, a specificity of 98.68% and an overall accuracy of 96.91%

Highlights

The novel Coronavirus (COVID-19), which originated in Wuhan, China at the end of 2019, has become a serious threat worldwide to public health [1]
We emphasize that the proposed Hybrid-COVID is a 2D/3D hybrid architecture designed to detect patients suspected of having COVID-19 by analyzing chest X-ray (CXR) images for early screening of the disease
The proposed transfer learning-based framework consists of a hybrid 2D/3D convolutional neural networks (CNNs) architecture that allows the automatic detection of COVID-19 using CXR modality

Summary

Introduction

The novel Coronavirus (COVID-19), which originated in Wuhan, China at the end of 2019, has become a serious threat worldwide to public health [1]. The real-time reverse transcriptase-polymerase chain reaction (RT-PCR) test can detect and screen the presence of the virus with a high-level of sensitivity. This kind of test has often been used as the main screening process for COVID-19 by directly identifying the existence of the virus. Some centers have a limited number of RT-PCR kits available and there is a high risk of receiving false-negative RT-PCR results over time [5]. It is very time-consuming and expensive especially when the collected specimens need to be processed by external specialized laboratories. This makes it very difficult to perform RT-PCR testing for a large number of suspected patients in as short a time as possible

Methods

Results

Discussion

Conclusion