TY - JOUR
T1 - Deep learning attention-guided radiomics for COVID-19 chest radiograph classification
AU - Yang, Dongrong
AU - Ren, Ge
AU - Ni, Ruiyan
AU - Huang, Yu Hua
AU - Lam, Ngo Fung Daniel
AU - Sun, Hongfei
AU - Wan, Shiu Bun Nelson
AU - Wong, Man Fung Esther
AU - Chan, King Kwong
AU - Tsang, Hoi Ching Hailey
AU - Xu, Lu
AU - Wu, Tak Chiu
AU - Kong, Feng Ming
AU - Wáng, Yì Xiáng J.
AU - Qin, Jing
AU - Chan, Lawrence Wing Chi
AU - Ying, Michael
AU - Cai, Jing
N1 - Funding Information:
Funding: This work was supported in part by Health and Medical Research Fund (HMRF COVID190211), the Food and Health Bureau, The Government of the Hong Kong Special Administrative Region, and Shenzhen-Hong Kong-Macau S&T Program (Category C) (No. SGDX20201103095002019), Shenzhen Basic Research Program (No. JCYJ20210324130209023), Shenzhen Science and Technology Innovation Committee.
Funding Information:
reporting checklist. Available at https://qims.amegroups. com/article/view/10.21037/qims-22-531/rc Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims. amegroups.com/article/view/10.21037/qims-22-531/ coif). YXJW serves as the Editor-in-Chief of Quantitative Imaging in Medicine and Surgery. JC reports that he receives grants from Health and Medical Research Fund (HMRF COVID190211), the Food and Health Bureau, The Government of the Hong Kong Special Administrative Region, and Shenzhen-Hong Kong-Macau S&T Program (Category C) (No. SGDX20201103095002019), Shenzhen Basic Research Program (No. JCYJ20210324130209023), Shenzhen Science and Technology Innovation Committee.
Publisher Copyright:
© Quantitative Imaging in Medicine and Surgery. All rights reserved.
PY - 2023/2
Y1 - 2023/2
N2 - Background: Accurate assessment of coronavirus disease 2019 (COVID-19) lung involvement through chest radiograph plays an important role in effective management of the infection. This study aims to develop a two-step feature merging method to integrate image features from deep learning and radiomics to differentiate COVID-19, non-COVID-19 pneumonia and normal chest radiographs (CXR). Methods: In this study, a deformable convolutional neural network (deformable CNN) was developed and used as a feature extractor to obtain 1,024-dimensional deep learning latent representation (DLR) features. Then 1,069-dimensional radiomics features were extracted from the region of interest (ROI) guided by deformable CNN’s attention. The two feature sets were concatenated to generate a merged feature set for classification. For comparative experiments, the same process has been applied to the DLR-only feature set for verifying the effectiveness of feature concatenation. Results: Using the merged feature set resulted in an overall average accuracy of 91.0% for three-class classification, representing a statistically significant improvement of 0.6% compared to the DLR-only classification. The recall and precision of classification into the COVID-19 class were 0.926 and 0.976, respectively. The feature merging method was shown to significantly improve the classification performance as compared to using only deep learning features, regardless of choice of classifier (P value <0.0001). Three classes’ F1-score were 0.892, 0.890, and 0.950 correspondingly (i.e., normal, non-COVID-19 pneumonia, COVID-19). Conclusions: A two-step COVID-19 classification framework integrating information from both DLR and radiomics features (guided by deep learning attention mechanism) has been developed. The proposed feature merging method has been shown to improve the performance of chest radiograph classification as compared to the case of using only deep learning features.
AB - Background: Accurate assessment of coronavirus disease 2019 (COVID-19) lung involvement through chest radiograph plays an important role in effective management of the infection. This study aims to develop a two-step feature merging method to integrate image features from deep learning and radiomics to differentiate COVID-19, non-COVID-19 pneumonia and normal chest radiographs (CXR). Methods: In this study, a deformable convolutional neural network (deformable CNN) was developed and used as a feature extractor to obtain 1,024-dimensional deep learning latent representation (DLR) features. Then 1,069-dimensional radiomics features were extracted from the region of interest (ROI) guided by deformable CNN’s attention. The two feature sets were concatenated to generate a merged feature set for classification. For comparative experiments, the same process has been applied to the DLR-only feature set for verifying the effectiveness of feature concatenation. Results: Using the merged feature set resulted in an overall average accuracy of 91.0% for three-class classification, representing a statistically significant improvement of 0.6% compared to the DLR-only classification. The recall and precision of classification into the COVID-19 class were 0.926 and 0.976, respectively. The feature merging method was shown to significantly improve the classification performance as compared to using only deep learning features, regardless of choice of classifier (P value <0.0001). Three classes’ F1-score were 0.892, 0.890, and 0.950 correspondingly (i.e., normal, non-COVID-19 pneumonia, COVID-19). Conclusions: A two-step COVID-19 classification framework integrating information from both DLR and radiomics features (guided by deep learning attention mechanism) has been developed. The proposed feature merging method has been shown to improve the performance of chest radiograph classification as compared to the case of using only deep learning features.
KW - chest radiograph
KW - classification
KW - Coronavirus disease 2019 (COVID-19)
KW - deep learning
KW - radiomics
UR - http://www.scopus.com/inward/record.url?scp=85147155108&partnerID=8YFLogxK
U2 - 10.21037/qims-22-531
DO - 10.21037/qims-22-531
M3 - Journal article
AN - SCOPUS:85147155108
SN - 2223-4292
VL - 13
SP - 572
EP - 584
JO - Quantitative Imaging in Medicine and Surgery
JF - Quantitative Imaging in Medicine and Surgery
IS - 2
ER -