COVID-19 Diagnosis from Chest X-Ray Images Using a Robust Multi-Resolution Analysis Siamese Neural Network with Super Resolution Convolutional Neural Network: Algorithm Development and Validation (Preprint)

Abstract

The chest x-ray (CXR) is becoming a useful method in the evaluation of coronavirus disease-19 (COVID-19). Despite the global COVID-19 uprising, utilizing computer-aided diagnosis approach for COVID-19 classification based on CXR images could significantly reduce clinician burden. There is no dispute that low resolution, noisy and irrelevant annotations in chest x-ray images is a major constraint to the performance of AI-based COVID-19 diagnosis. While 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) images of 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. Since the datasets are collected from different sources with varying resolutions and the input layer of a convolutional neural network requires that the input size of the images in the training distribution must be fixed, therefore we extend the super resolution convolutional neural network by introducing an adaptive scaling operation to resize the images to a fixed resolution prior to the enhancement operation. 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 an accuracy of 99.6%, precision of 99.7%, and F1 score of 99.9%. Our screening technique achieved 99.8 % AUC, 99.7% sensitivity and 99.6% specificity.

Owing to the fact that COVID-19 chest x-ray dataset are low in quality, experimental results show that our proposed algorithm obtained up-to-date performance which is useful for COVID-19 screening.