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

Abstract

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.

Research and implementation of multi-disease diagnosis on chest X-ray based on vision transformer

“…Second, in the selected key regions ablation experiment setup, the number of heads in the multi-head self-attention module was set to 12. This setting was chosen because previous studies ( 13 - 16 ) have shown that different heads in the multi-head self-attention mechanism represent semantic information in different dimensions. Therefore, in the key region selection module, for each attention head, the regions with the highest attention weights were selected as the key regions.…”

A lightweight neural network for lung nodule detection based on improved ghost module

“…With the development of medical imaging technology, traditional detection methods are difficult to adapt to the current large and complex data sets, while the steps of manual extraction of features are complicated and cannot effectively mine the rich information in images. The neural network deep learning method is based on a powerful feature recognition function that can, by learning and analyzing a large amount of data, automatically find and extract regular features to achieve superior classification and diagnostic results (12)(13)(14). Recent deep learning-based approaches, especially CNNs, automatically learn powerful 3D features in an end-toend manner with promising generalization performance, primarily for detection and classification in the diagnosis of lung nodules (15).…”

Dynamic Chest Radiograph Simulation Technique with Deep Convolutional Neural Networks: A Proof-of-Concept Study

“…By leveraging the capabilities of artificial intelligence (AI), researchers are able to extract a significantly greater amount of information compared to relying solely on observations with the human eye [7]. Approaches like image enhancement [8][9][10][11], organ segmentation [12][13][14], and feature extraction [15][16][17] have been investigated and have achieved promising results. Previous studies have considered whether chest X-rays contain rich three-dimensional and functional information that could be extracted by AI to provide extra information that would improve clinical diagnosis [18].…”