Convolutional Sparse Support Estimator-Based COVID-19 Recognition From X-Ray Images

Abstract

Coronavirus disease (COVID-19) has been the main agenda of the whole world ever since it came into sight. X-ray imaging is a common and easily accessible tool that has great potential for COVID-19 diagnosis and prognosis. Deep learning techniques can generally provide state-of-the-art performance in many classification tasks when trained properly over large data sets. However, data scarcity can be a crucial obstacle when using them for COVID-19 detection. Alternative approaches such as representation-based classification [collaborative or sparse representation (SR)] might provide satisfactory performance with limited size data sets, but they generally fall short in performance or speed compared to the neural network (NN)-based methods. To address this deficiency, convolution support estimation network (CSEN) has recently been proposed as a bridge between representation-based and NN approaches by providing a noniterative real-time mapping from query sample to ideally SR coefficient support, which is critical information for class decision in representation-based techniques. The main premises of this study can be summarized as follows: 1) A benchmark X-ray data set, namely QaTa-Cov19, containing over 6200 X-ray images is created. The data set covering 462 X-ray images from COVID-19 patients along with three other classes; bacterial pneumonia, viral pneumonia, and normal. 2) The proposed CSEN-based classification scheme equipped with feature extraction from state-of-the-art deep NN solution for X-ray images, CheXNet, achieves over 98% sensitivity and over 95% specificity for COVID-19 recognition directly from raw X-ray images when the average performance of 5-fold cross validation over QaTa-Cov19 data set is calculated. 3) Having such an elegant COVID-19 assistive diagnosis performance, this study further provides evidence that COVID-19 induces a unique pattern in X-rays that can be discriminated with high accuracy. Index Terms-Coronavirus disease (COVID-19) recognition, representation-based classification, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, transfer learning. I. INTRODUCTIONC ORONAVIRUS disease 2019 (COVID-19) has been declared as a pandemic by the World Health Organization (WHO) a few months after its first appearance. It has infected more than 70 million people, caused a few million causalities, and has so far paralyzed mobility all around the world. The spreading rate of COVID-19 is so high that the

COVID-19 infection localization and severity grading from chest X-ray images

“…99.7% Spe. 99.6% [ 31 ] COVID-19 (462) Non-COVID (2,485) Healthy (1,579) Feature extraction model CheXNet Classification model Convolutional Support Estimation Network Class. Sens.…”

“…Recently, many studies have proposed Deep Learning approaches to automate COVID-19 detection from chest X-ray images [ [26] , [27] , [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] ] with high performance. Ozturk et al [ 26 ] presented a modified version of DarkNet for binary classification (COVID-19 vs Normal) and multi-class classification (COVID-19 vs Non-COVID pneumonia vs Normal).…”

“…DenseNet201 showed the best classification performance with 99.7% and 97.9% sensitivity values for binary and multi-class schemes, respectively. Yamac et al [ 31 ] utilized CheXNet as a feature extractor while a proposed classifier, Convolution Support Estimation Network (CSEN), discriminates the target CXR as COVID-19, Bacterial pneumonia, Viral Pneumonia, or Normal. The network produced satisfactory results with 98% sensitivity over the benchmark QaTa-COV19 dataset that includes 462 COVID-19 CXR images.…”

COVID-19 Detection Using Deep Learning Algorithm on Chest X-ray Images

“…In [ 49 ], a benchmark X-ray data collection, dubbed QaTa-Cov19, was produced. It contained about 6200 X-ray pictures.…”

“…However, it is known that neural network models require a large amount of data in order to be trained and tested. In the studies [ 35 , 36 , 37 , 39 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 49 , 51 , 52 , 53 , 55 , 56 ], researchers have worked with a small number of chest X-ray data (75–6200 data) for training and testing purposes of COVID-19 detection and achieved varying accuracy (89.2–98%). However, due to the lack of proper training of the models primarily because of using such limited datasets, the credibility of the outcome is questionable.…”