COVID-19 Diagnosis from Chest X-ray Images Using a Robust Multi-Resolution Analysis Siamese Neural Network with Super-Resolution Convolutional Neural Network

Abstract

Chest X-ray (CXR) is becoming a useful method in the evaluation of coronavirus disease 19 (COVID-19). Despite the global spread of COVID-19, utilizing a computer-aided diagnosis approach for COVID-19 classification based on CXR images could significantly reduce the clinician burden. There is no doubt that low resolution, noise and irrelevant annotations in chest X-ray images are a major constraint to the performance of AI-based COVID-19 diagnosis. While a few studies have made huge progress, they underestimate these bottlenecks. In this study, we propose a super-resolution-based Siamese wavelet multi-resolution convolutional neural network called COVID-SRWCNN for COVID-19 classification using chest X-ray images. Concretely, we first reconstruct high-resolution (HR) counterparts from low-resolution (LR) CXR images in order to enhance the quality of the dataset for improved performance of our model by proposing a novel enhanced fast super-resolution convolutional neural network (EFSRCNN) to capture texture details in each given chest X-ray image. Exploiting a mutual learning approach, the HR images are passed to the proposed Siamese wavelet multi-resolution convolutional neural network to learn the high-level features for COVID-19 classification. We validate the proposed COVID-SRWCNN model on public-source datasets, achieving accuracy of 98.98%. Our screening technique achieves 98.96% AUC, 99.78% sensitivity, 98.53% precision, and 98.86% specificity. Owing to the fact that COVID-19 chest X-ray datasets are low in quality, experimental results show that our proposed algorithm obtains up-to-date performance that is useful for COVID-19 screening.

Pathological changes or technical artefacts? The problem of the heterogenous databases in COVID-19 CXR image analysis

“…They enable better visual analysis, interpretation, and decision-making in areas where higher-resolution imagery is crucial. In the context of medical imaging, they were already used to reduce the interference associated with the way the examination is performed [48] , [49] , to improve the perceptibility of details [50] , [51] , [52] and, as in our case, to replace the bicubic up-sampling method with a more sophisticated technique [53] . When comparing nUMAP embeddings of CXR images up-sampled using super-resolution and classical methods ( Fig.…”

Progressive attention integration-based multi-scale efficient network for medical imaging analysis with application to COVID-19 diagnosis

“…It is noticeable that performance of the DL-based models can be severely affected by the imperfect medical imaging data, for example, in the chest X-ray images, the organic entity may merely occupy 50% space, whereas the rest background part contains much useless and redundant information, which causes the waste of computational resources and leads to inefficient feature extraction [11] . Similarity in imaging results of different diseases also impedes the accurate recognition of relevant conditions [12] .…”

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

“…The learningbased method uses the convolutional neural network (CNN) to establish a nonlinear mapping relationship between LR and HR images. In the past 2 years, superresolution reconstruction methods based on deep learning models have also been gradually applied to the task of HR CXR image acquisition (44)(45)(46). The models include deep recursive neural network (DRCN) (47), HR Network (HRNet) (48), and super-resolution generative adversarial network (SRGAN) (49).…”