A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19) (original) (raw)
Related papers
Asian Journal of Applied Sciences
Today, humans live in the era of rapid growth in electronic devices that are based on artificial intelligence, including the significant growth in the manufacture of machines that perform intelligent human tasks to solve complex situations. Artificial intelligence will significantly influence the development of many domains, especially the medical domain, which relies heavily on artificial intelligence techniques in diagnosing disease data and manufacturing drugs and vaccines. Artificial intelligence has unexpectedly advanced in helping physicians and healthcare workers save many lives, especially during the spread of the COVID-19 virus. This article reviews some literature that have applied deep learning techniques to detect COVID-19 based on chest x-rays and CT-scans images. This article concluded that deep learning techniques have a fundamental and significant role in diagnosing a big dataset of images and assisting specialists in determining whether a person is infected (positiv...
Using Deep Learning Algorithms to Diagnose Coronavirus Disease (COVID-19)
International Journal of Advanced Computer Science and Applications
With the rapid development in the area of Machine Learning (ML) and Deep learning, it is important to exploit these tools to contribute to mitigating the effects of the coronavirus pandemic. Early diagnosis of the presence of this virus in the human body can be crucially helpful to healthcare professionals. In this paper, three well-known Convolutional Neural Network deep learning algorithms (VGGNet 16, GoogleNet and ResNet50) are applied to measure their ability to distinguish COVID-19 patients from other patients and to evaluate the best performance among these algorithms with a large dataset. Two stages are conducted, the first stage with 14994 x-ray images and the second one with 33178. Each model has been applied with different batch sizes 16, 32 and 64 in each stage to measure the impact of data size and batch size factors on the accuracy results. The second stage achieved accuracy better than the first one and the 64 batch size gain best results than the 16 and 32. ResNet50 achieves a high rate of 99.31, GoogleNet model achieves 95.55, while VGG16 achieves 96.5. Ultimately, the results affect the process of expediting the diagnosis and referral of these treatable conditions, thereby facilitating earlier treatment, and resulting in improved clinical outcomes.
A deep learning algorithm to detect coronavirus (COVID-19) disease using CT images
PeerJ Computer Science, 2021
Background COVID-19 pandemic imposed a lockdown situation to the world these past months. Researchers and scientists around the globe faced serious efforts from its detection to its treatment. Methods Pathogenic laboratory testing is the gold standard but it is time-consuming. Lung CT-scans and X-rays are other common methods applied by researchers to detect COVID-19 positive cases. In this paper, we propose a deep learning neural network-based model as an alternative fast screening method that can be used for detecting the COVID-19 cases by analyzing CT-scans. Results Applying the proposed method on a publicly available dataset collected of positive and negative cases showed its ability on distinguishing them by analyzing each individual CT image. The effect of different parameters on the performance of the proposed model was studied and tabulated. By selecting random train and test images, the overall accuracy and ROC-AUC of the proposed model can easily exceed 95% and 90%, respec...
Electronics
COVID-19 is a transferable disease inherited from the SARS-CoV-2 virus. A total of 594 million people have been infected, and 6.4 million human beings have died due to COVID-19. The fastest way to diagnose the disease is by radiography. Deep learning has been the most popular technique for image classification during the last decade. This paper aims to examine the contributions of machine learning for the detection of COVID-19 using Deep Learning and explores the overall application of convolutional neural networks of some famous state-of-the-art deep learning pre-trained models. In this research, our objective is to explore the various image classification strategies for CXIs and the application of deep learning models for optimization and feature selection. The study presented in this article shows that the accuracy of deep learning models when detecting COVID-19 on the basis of chest X-ray images ranges from 93 percent to above 99 percent.
USE OF DEEP LEARNING TO DIAGNOSE COVID-19 BASED ON COMPUTED TOMOGRAPHY IMAGES
Revista HOLOS, 2021
The newly identified Coronavirus pneumonia, later called COVID-19, is highly transmissible and pathogenic. The most common symptoms of this disease are dry cough, sore throat, and fever. Symptoms can progress to a severe form of pneumonia with critical complications, including septic shock, pulmonary edema, acute respiratory distress syndrome, and multiple organ failure. A major obstacle in controlling the spread of this disease is the inefficiency and scarcity of medical tests. Increasing efforts have been made to develop deep learning (DL) methods to diagnose COVID-19 based on tomography images. These computer-aided diagnostic systems can assist in the early detection of abnormalities in COVID-19 and facilitate the monitoring of disease progression, potentially reducing mortality rates. In this study, we compared the popular resource extraction structures based on deep learning for the automatic classification of COVID-19. To obtain a more precise method, which is an essential learning component, a set of deep convolutional neural networks (CNN) was chosen to train our model. The performance of the proposed method was validated using a COVID-19 dataset with computed tomography (CT) images. This dataset is available to the public and contains hundreds of positive CT scans for the disease. DL methods were performed and the best classified CNN was able to achieve excellent diagnostic results for COVID-19.
Limitations and challenges on the diagnosis of COVID-19 using radiology images and deep learning
Elsevier Pub., Data Science for COVID-19, 2021
The world is facing a great threat nowadays. The COVID-19 virus outbreak that occurred in Wuhan in China in December 2019 continues to increase in the middle of 2020. Within the scope of this epidemic, different contents of data are published and products for improving the treatment process. One of the major symptoms of COVID-19 epidemic disease, which was revealed by the World Health Organization, is intense cough and breathing difficulties. Chest X-ray (CXR) and computing tomography (CT) images of patients infected with COVID-19 are also a type of data that allows data scientists to work with healthcare professionals during this struggle. Fast evaluation of these images by experts is important in the days when the epidemic has suffered. This chapter focuses on artificial intelligence (AI) for a successful and rapid diagnostic recommendation as part of these deadly epidemic prevention efforts that have emerged. As a study case, a dataset of 373 CXR images, 139 of which were COVID-19 infected, collected from open sources, was used for diagnosis with deep learning approaches of COVID-19. The use of EfficientNet, an up-to-date and robust deep learning model for education, offers the possibility to become infected with an accuracy of 94.7%. Nevertheless, some limitations must be considered when producing AI solutions by making use of medical data. Using these results, a perspective is provided on the limitations of deep learning models in the diagnosis of COVID-19 from radiology images for data quality, amount of data, data privacy, explainability, and robust solutions.
Deep learning techniques for detection of covid-19 using chest x-rays
Advances in systems science and applications, 2021
The COVID-19 pandemic situation keeps on ruining and affecting the wellbeing and prosperity of the worldwide population and due to this situation, the doctors around the world are working restlessly, as the coronavirus is increasing exponentially and the situation for testing has become quite a problematic and with restricted testing units, it’s impossible for every patient to be tested with available facilities. Effective screening of infected patients through chest X-ray images is a critical step in combating COVID-19. With the help of deep learning techniques, it is possible to train various radiology images and detect COVID-19. The dataset used in our research work is gathered from different sources and a specific new dataset is generated. The proposed methodology implemented is beneficial to the medical practitioner for the diagnosis of coronavirus infected patients where predictions can be done automated using deep learning. The deep learning algorithms that are used to predic...
Sensors, 2022
COVID-19 has evolved into one of the most severe and acute illnesses. The number of deaths continues to climb despite the development of vaccines and new strains of the virus have appeared. The early and precise recognition of COVID-19 are key in viably treating patients and containing the pandemic on the whole. Deep learning technology has been shown to be a significant tool in diagnosing COVID-19 and in assisting radiologists to detect anomalies and numerous diseases during this epidemic. This research seeks to provide an overview of novel deep learning-based applications for medical imaging modalities, computer tomography (CT) and chest X-rays (CXR), for the detection and classification COVID-19. First, we give an overview of the taxonomy of medical imaging and present a summary of types of deep learning (DL) methods. Then, utilizing deep learning techniques, we present an overview of systems created for COVID-19 detection and classification. We also give a rundown of the most we...
Comparative Study of Deep Learning Models for COVID-19 Diagnosis
2021
Corona Virus Disease 2019(COVID-19) spread far and wide in numerous nations in early 2020, causing the world to face an existential health crisis. This pandemic continues to have a devastating effect on the global population and by now it has infected more than a few million individuals around the world. One significant obstacle in controlling the spreading of this virus is that the initial system for addressing this infectious disease was not clear. A basic advancement in the struggle opposite the COVID-19 pandemic is early screening and dependable diagnosis utilizing computerized detection of lung infections. Computed Tomography (CT) scans and X-rays imagery offers great potential help to clinical specialists tackling COVID-19. An efficient Deep Learning diagnosis application needs to be developed so that accurate and precise prediction can be done for the disease. This paper introduces dataset analysis and comparative evaluation of deep learning models for creating disease diagno...
IEEE Access
The novel coronavirus disease 2019 (COVID-19) added tremendous pressure on healthcare services worldwide. COVID-19 early detection is of the utmost importance to control the spread of the coronavirus pandemic and to reduce pressure on health services. There have been many approaches to detect COVID-19; the most commonly used one is the nasal swab technique. Before that was available chest X-ray radiographs were used. X-ray radiographs are a primary care method to reveal lung infections, which allows physicians to assess and plan a course of treatment. X-ray machines are prevalent, which makes this method a preferable first approach for the detection of new diseases. However, this method requires a radiologist to assess each chest X-ray image. Therefore, different automated methods using machine learning techniques have been proposed to assist in speeding up diagnoses and improving the decision-making process. In this paper, we review deep learning approaches for COVID-19 detection using chest X-ray images. We found that the majority of deep learning approaches for COVID-19 detection use transfer learning. A discussion of the limitations and challenges of deep learning in radiography images is presented. Finally, we provide potential improvements for higher accuracy and generalisability when using deep learning models for COVID-19 detection. 15 INDEX TERMS Machine learning, pneumonia, radiology, diagnostic imaging, COIVD-19. I. INTRODUCTION 16 The novel coronavirus disease 2019 (COVID-19) rapidly 17 spread quickly causing a global pandemic. The first inci-18 dence of the virus was identified in early December 2019 in 19 Wuhan, the People's Republic of China. Strong measures 20 were applied to control the spread of infection. Some of these 21 measures included shutdowns, isolation, and close monitor-22 ing of contacts, which have caused economic crisis, reces-23 sion, and affected the mental well-being of many individuals 24 around the world [1], [2], [3]. The World Health Organiza-25 tion (WHO) declared the COVID-19 outbreak as a global 26 pandemic on March 11 th , 2020 [4]. The death toll of the 27 The associate editor coordinating the review of this manuscript and approving it for publication was Derek Abbott. resulting pandemic was 5.04 million confirmed death and 249.54 million confirmed cases of infection worldwide as of November 6, 2021 [5]. The first few months of the pandemic were challenging for hospitals, medical teams, and governments to control and test millions of infected people. Healthcare systems could not keep up with the significant number of infected cases, and in some countries, the healthcare system collapsed under the COVID-19 surge. The rapid spread of the virus increased the need for early detection of positive COVID-19 cases and faster diagnosis [6] to help control and better understand the pandemic. Reverse Transcription Polymerase Chain Reaction test (RT-PCR) is the current standard tool used to detect COVID-19 infection. However, RT-PCR is a time-consuming and expensive process and it has reported VOLUME 10, 2022 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ 48 facilities. Other new methods based on chest X-rays, which 49 are less expensive and more widely available, have shown 50 potential improvements in detecting COVID-19. 51 Inspecting a chest X-ray to diagnose COVID-19 add 52 to the burden of radiologists as they review and interpret 53 lung X-ray images. Although this approach requires time 54 from a radiologist to interpret the images, X-ray evidence 55 may be more accurate as opposed to reverse transcrip-56 tion polymerase chain reaction (RT-PCR) [9]. To aid the 57 diagnosis of COVID-19, researchers have proposed sev-58 eral automated methods based on machine learning algo-59 rithms to analyze X-rays of COVID-19 cases. Automating 60 the COVID-19 diagnostic process using X-ray images acts 61 as a decision-supporting tool assisting radiologists as well as 62 promoting the early detection and treatment of COVID-19. 63 There have been previous papers that have reviewed 64 machine learning techniques for COVID-19 detection [10], 65 [11], [12], [13], [14], [15]. However, these previous reviews 66 covered older research papers. In this comprehensive review 67 article, we review recent peer-reviewed articles published 68 from January 2020 through the end of 2021. We classify the 69 reviewed papers into two categories: transfer learning and 70 training from scratch. A graph of the reviewed papers in each 71 category is shown in Figure 1. An appendix is provided to 72 explain the different deep learning architectures used in the 73 reviewed papers. 74 II. DEEP LEARNING 75 Recently, deep learning-based approaches became one of 76 the most popular algorithms in machine learning. These 77 approaches have outperformed and achieved state-of-the-78 art performance in many learning-based research problems [16], [17], [18]. The popularity of deep learning started in late 2012, when a deep-learning approach based on convolutional neural networks (CNNs) outperformed all other methods in the best-known computer-vision competition, ImageNet [19]. Such networks (i.e., CNNs) are designed to take advantage of a two-dimensional input, employing a series of convolutional layers for extracting features at different spatial locations. They have achieved cutting-edge results for many vision tasks, including object recognition [19], [20], scene classification [21], [22], [23], and 3D image understanding [24], [25]. medical physics-based criteria may apply to all datasets. The 176 quality of the images in terms of scan protocol such as kVp 177 and mAs, the field of view, angle of images along with 178 different machine manufacturers may have a prominent effect 179 on the quality of the image and the reproducibility of the 180 scans. Figure 3, shows some examples of COVID-19 positive 181 and negative X-ray images. 182 CoronaHack Chest X-ray dataset [38] contains 58 (1%) 183 patients with confirmed COVID-19 patients in the training 184 set, so the data is skewed toward non-positive outcomes. The 185 rest of the infected patients had pneumonia in either viral 186 or bacterial causes. This may lead to bias in classification 187 outcomes. A much larger COVID-19 outcome data is needed 188 for this dataset. The data does not show any patient demo-189 graphics, especially whether all COVID-19 patients in the 190 dataset had pneumonia symptoms. 191 In another dataset presented in [36], some chest X-ray 192 images (Pneumonia) dataset show inconsistency in terms of 193 age, the field of view, and image parameters. Some images 194 have artifacts because of the placement of cables and devices 195 during the scan. Such artifacts may affect the validity of the 196 classifier models during training and testing. 197 The NIH dataset [42] is a well-established and documented 198 pneumonia imaging data that may be used as a preliminary 199 check for researchers to test their approach. Some concerns 200 raised in the previous two datasets are the type of X-ray used; 201 single or dual-energy and image parameter. 202 IV. DETECTION OF COVID-19 USING DEEP LEARNING 203 Different approaches for COVID-19 detection using chest 204 radiology images and deep learning have been proposed. 205 In this section, we review the proposed methods for 206 COVID-19 detection using chest X-ray images. Moreover, 207 we provide a classification of deep learning approaches 208 262 ing models. Another fine-tuning approach was presented by 263 El-Gannour et al. in [53]. The authors evaluated transfer learning of models pre-trained on the ImageNet dataset for 265 COVID-19 classification using a chest X-ray images dataset.