Deep learning attention-guided radiomics for COVID-19 chest radiograph classification

Quantitative Imaging in Medicine and Surgery

article

Dongrong Yang¹  Ge Ren¹  Ruiyan Ni¹  Yu-Hua Huang¹  Ngo Fung Daniel Lam¹  Hongfei Sun¹  Shiu Bun Nelson Wan²  Man Fung Esther Wong²  King Kwong Chan³  Hoi Ching Hailey Tsang³  Lu Xu³  Tak Chiu Wu³  Feng-Ming (Spring) Kong⁴  Yì Xiáng J. Wáng⁵  Jing Qin⁶  Lawrence Wing Chi Chan¹  Michael Ying¹  Jing Cai¹ 

[1] Department of Health Technology and Informatics, The Hong Kong Polytechnic University;Department of Radiology, Pamela Youde Nethersole Eastern Hospital;Department of Radiology and Imaging, Queen Elizabeth Hospital;Department of Clinical Oncology, The University of Hong Kong;Deparment of Imaging and Interventional Radiology, The Chinese University of Hong Kong;School of Nursing, The Hong Kong Polytechnic University

关键词: Coronavirus disease 2019 (COVID-19);    radiomics;    deep learning;    chest radiograph;    classification;   

DOI  :  10.21037/qims-22-531

学科分类：外科医学

来源: AME Publications

【 摘 要 】

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.

【 授权许可】

All Rights reserved