A novel multi-stage residual feature fusion network for detection of COVID-19 in chest X-ray images

Fang, Zhenyu and Ren, Jinchang and MacLellan, Calum and Li, Huihui and Zhao, Huimin and Hussain, Amir and Fortino, Giancarlo (2021) A novel multi-stage residual feature fusion network for detection of COVID-19 in chest X-ray images. IEEE Transactions on Molecular, Biological, and Multi-Scale Communications. ISSN 2332-7804 (https://doi.org/10.1109/TMBMC.2021.3099367)

[thumbnail of Fang-etal-TMBMC-2021-A-novel-multi-stage-residual-feature-fusion-network-for-detection-of-COVID-19-in-chest-X-ray-images]
Preview
Text. Filename: Fang_etal_TMBMC_2021_A_novel_multi_stage_residual_feature_fusion_network_for_detection_of_COVID_19_in_chest_X_ray_images.pdf
Accepted Author Manuscript

Download (3MB)| Preview

Abstract

To suppress the spread of COVID-19, accurate diagnosis at an early stage is crucial, chest screening with radiography imaging plays an important role in addition to the real-time reverse transcriptase polymerase chain reaction (RT-PCR) swab test. Due to the limited data, existing models suffer from incapable feature extraction and poor network convergence and optimization. Accordingly, a multi-stage residual network, MSRCovXNet, is proposed for effective detection of COVID-19 from chest x-ray (CXR) images. As a shallow yet effective classifier with the ResNet-18 as the feature extractor, MSRCovXNet is optimized by fusing two proposed feature enhancement modules (FEM), i.e. low-level and high-level feature maps (LLFMs and HLFMs), which contain respectively more local information and rich semantic information, respectively. For effective fusion of these two features, a single-stage FEM (MSFEM) and a multi-stage FEM (MSFEM) are proposed to enhance the semantic feature representation of the LLFMs and the local feature representation of the HLFMs, respectively. Without ensembling other deep learning models, our MSRCovXNet has a precision of 98.9% and a recall of 94% in detection of COVID-19, which outperforms several state-of-the-art models. When evaluated on the COVIDGR dataset, an average accuracy of 82.2% is achieved, leading other methods by at least 1.2%.