TY - JOUR
T1 - A novel multi-stage residual feature fusion network for detection of COVID-19 in chest X-ray images
AU - Fang, Zhenyu
AU - Ren, Jinchang
AU - MacLellan, Calum
AU - Li, Huihui
AU - Zhao, Huimin
AU - Hussain, Amir
AU - Fortino, Giancarlo
N1 - © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2022/3/31
Y1 - 2022/3/31
N2 - 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%.
AB - 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%.
KW - chest x-ray imaging
KW - COVID-19
KW - data models
KW - feature enhancement module
KW - feature extraction
KW - MSRCovXNet
KW - pulmonary diseases
KW - ResNet-18.
KW - testing
KW - training
KW - X-ray imaging
U2 - 10.1109/TMBMC.2021.3099367
DO - 10.1109/TMBMC.2021.3099367
M3 - Article
AN - SCOPUS:85111564795
VL - 8
SP - 17
EP - 27
JO - IEEE Transactions on Molecular, Biological, and Multi-Scale Communications
JF - IEEE Transactions on Molecular, Biological, and Multi-Scale Communications
IS - 1
ER -