Search

• A novel multi-kernel-size spatial-channel attention model for COVID-19 detection • The proposed method enables early diagnosis from chest X-ray images. • Evaluation with real-world data demonstrates improved accuracy at 98.2 Novel coronavirus 2019 (COVID-19) has spread rapidly around the world and is threatening the health and lives of people worldwide. Early detection of COVID-19 positive patients and timely isolation of the patients are essential to prevent its spread. Chest X-ray images of COVID-19 patients often show the characteristics of multifocality, bilateral hairy glass turbidity, patchy network turbidity, etc. It is crucial to design a method to automatically identify COVID-19 from chest X-ray images to help diagnosis and prognosis. Existing studies for the classification of COVID-19 rarely consider the role of attention mechanisms on the classification of chest X-ray images and fail to capture the cross-channel and cross-spatial interrelationships in multiple scopes. This paper proposes a multi-kernel-size spatial-channel attention method to detect COVID-19 from chest X-ray images. Our proposed method consists of three stages. The first stage is feature extraction. The second stage contains two parallel multi-kernel-size attention modules: multi-kernel-size spatial attention and multi-kernel-size channel attention. The two modules capture the cross-channel and cross-spatial interrelationships in multiple scopes using multiple 1D and 2D convolutional kernels of different sizes to obtain channel and spatial attention feature maps. The third stage is the classification module. We integrate the chest X-ray images from three public datasets: COVID-19 Chest X-ray Dataset Initiative, ActualMed COVID-19 Chest X-ray Dataset Initiative, and COVID-19 radiography database for evaluation. Experimental results demonstrate that the proposed method improves the performance of COVID-19 detection and achieves an accuracy of 98.2%. [ABSTRACT FROM AUTHOR]

• Proposed automatic COVID screening (ACoS) system for detection of infected patients. • Random image augmentation is applied to incorporate the variability in the images. • Applied hierarchical (two phase) classification to segregate three classes. • Majority vote based classifier ensemble is used to combine model's prediction. • Proposed method show promising potential to detect nCOVID-19 infected patients. Novel coronavirus disease (nCOVID-19) is the most challenging problem for the world. The disease is caused by severe acute respiratory syndrome coronavirus-2 (SARS-COV-2), leading to high morbidity and mortality worldwide. The study reveals that infected patients exhibit distinct radiographic visual characteristics along with fever, dry cough, fatigue, dyspnea, etc. Chest X-Ray (CXR) is one of the important, non-invasive clinical adjuncts that play an essential role in the detection of such visual responses associated with SARS-COV-2 infection. However, the limited availability of expert radiologists to interpret the CXR images and subtle appearance of disease radiographic responses remains the biggest bottlenecks in manual diagnosis. In this study, we present an automatic COVID screening (ACoS) system that uses radiomic texture descriptors extracted from CXR images to identify the normal, suspected, and nCOVID-19 infected patients. The proposed system uses two-phase classification approach (normal vs. abnormal and nCOVID-19 vs. pneumonia) using majority vote based classifier ensemble of five benchmark supervised classification algorithms. The training-testing and validation of the ACoS system are performed using 2088 (696 normal, 696 pneumonia and 696 nCOVID-19) and 258 (86 images of each category) CXR images, respectively. The obtained validation results for phase-I (accuracy (ACC) = 98.062%, area under curve (AUC) = 0.956) and phase-II (ACC = 91.329% and AUC = 0.831) show the promising performance of the proposed system. Further, the Friedman post-hoc multiple comparisons and z-test statistics reveals that the results of ACoS system are statistically significant. Finally, the obtained performance is compared with the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]