COVID-19 Chest X-ray Research Articles

Data science and the role of Artificial Intelligence in achieving the fast diagnosis of Covid-19.

The rapid spread of novel coronavirus (namely Covid-19) worldwide has alarmed a pandemic since its outbreak in the city of Wuhan, China in December 2019. While the world still tries to wrap its head around as to how to contain the rapid spread of the novel coronavirus, the pandemic has already claimed several thousand lives throughout the world. Yet, the diagnosis of virus spread in humans has proven complexity. A blend of computed tomography imaging, entire genome sequencing, and electron microscopy have been at first adapted to screen and distinguish SARS-CoV-2, the viral etiology of Covid-19. There are a less number of Covid-19 test kits accessible in hospitals because of the expanding cases every day. Accordingly, it is required to utensil a self-exposure framework as a fast substitute analysis to contain Covid-19 spreading among individuals considering the world at large. In the present work, we have elaborated a prudent methodology that helps identify Covid-19 infected people among the normal individuals by utilizing CT scan and chest x-ray images using Artificial Intelligence (AI). The strategy works with a dataset of Covid-19 and normal chest x-ray images. The image diagnosis tool utilizes decision tree classifier for finding novel corona virus infected person. The percentage accuracy of an image is analyzed in terms of precision, recall score and F1 score. The outcome depends on the information accessible in the store of Kaggle and Open-I according to their approved chest X-ray and CT scan images. Interestingly, the test methodology demonstrates that the intended algorithm is robust, accurate and precise. Our technique accomplishes the exactness focused on the AI innovation which provides faster results during both training and inference.

Accurate Diagnosis of COVID-19 Based on Deep Neural Networks and Chest X-Ray Images. (Dept.E (Electronics ))

The present study aims at preventing spread out of COVID-19 by early detection of infected cases using chest X-ray images and convolutional neural networks. Covid-19 chest X-ray dataset were collected from public sources as well as through agreements with hospitals and physicians with the consent of their patients. A deep learning algorithm based on convolutional neural networks (CNN) was implemented utilizing X-ray images to diagnose COVID-19. ResNet50, short for Residual Networks, is a classic neural network that was used as a backbone for the classification task. It accelerates the speed of training of the deep networks and reduces the effect of vanishing gradient problems. Images were first resized and then pre-processed to increase sharpness, contrast, and clarity. Images were fed into a deep neural network to predict the probability of COVID-19 infectious. The deep learning calculation acquired an area under the curve (AUC) of the receiver operating characteristics (ROC) of 0.9888, 96.2% sensitivity, 98% accuracy, and 100% specificity. Moreover, the algorithm can be easily modified to add extra images (normal and COVID-19) to improve performance. The proposed system introduces a great help to all nations to screen and diagnose COVID-19 as a faster alternative compared with conventional method that uses PCR

Accurate Diagnosis of COVID-19 Based on Deep Neural Networks and Chest X-Ray Images

The present study aims at preventing spread out of COVID-19 by early detection of infected cases using chest X-ray images and convolutional neural networks. Covid-19 chest X-ray dataset were collected from public sources as well as through agreements with hospitals and physicians with the consent of their patients. A deep learning algorithm based on convolutional neural networks (CNN) was implemented utilizing X-ray images to diagnose COVID-19. ResNet50, short for Residual Networks, is a classic neural network that was used as a backbone for the classification task. It accelerates the speed of training of the deep networks and reduces the effect of vanishing gradient problems. Images were first resized and then pre-processed to increase sharpness, contrast, and clarity. Images were fed into a deep neural network to predict the probability of COVID-19 infectious. The deep learning calculation acquired an area under the curve (AUC) of the receiver operating characteristics (ROC) of 0.9888, 96.2% sensitivity, 98% accuracy, and 100% specificity. Moreover, the algorithm can be easily modified to add extra images (normal and COVID-19) to improve performance. The proposed system introduces a great help to all nations to screen and diagnose COVID-19 as a faster alternative compared with conventional method that uses PCR.

COVID-19 Detection from Chest X-Ray Images Using CNNs Models: Further Evidence from Deep Transfer Learning

In this study we revisit the identification of COVID-19 from chest x-ray images using Deep Learning. We collect a relatively large COVID-19 dataset comparing with previous studies that contains 309 real COVID-19 chest x-ray images. We prepare also 2000 chest x-ray images of pneumonia cases and 1000 images of healthy chest cases. Deep Transfer Learning is used to detect abnormalities in our images dataset. We fine-tune three pre-trained deep convolutional neural networks (CNNs) models on a training dataset; DenseNet 121, NASNetLarge and NASNetMobile. The evaluation of our models on a test dataset shows that these models achieve a sensitivity rate of around 99.45 % on average, and a specificity rate of around 99.5 % on average. These results could be helpful for an automatic diagnosis of COVID-19 infections, but the clinical diagnosis stills always necessary.

CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization

With the recent outbreak of COVID-19, fast diagnostic testing has become one of the major challenges due to the critical shortage of test kit. Pneumonia, a major effect of COVID-19, needs to be urgently diagnosed along with its underlying reasons. In this paper, deep learning aided automated COVID-19 and other pneumonia detection schemes are proposed utilizing a small amount of COVID-19 chest X-rays. A deep convolutional neural network (CNN) based architecture, named as CovXNet, is proposed that utilizes depthwise convolution with varying dilation rates for efficiently extracting diversified features from chest X-rays. Since the chest X-ray images corresponding to COVID-19 caused pneumonia and other traditional pneumonias have significant similarities, at first, a large number of chest X-rays corresponding to normal and (viral/bacterial) pneumonia patients are used to train the proposed CovXNet. Learning of this initial training phase is transferred with some additional fine-tuning layers that are further trained with a smaller number of chest X-rays corresponding to COVID-19 and other pneumonia patients. In the proposed method, different forms of CovXNets are designed and trained with X-ray images of various resolutions and for further optimization of their predictions, a stacking algorithm is employed. Finally, a gradient-based discriminative localization is integrated to distinguish the abnormal regions of X-ray images referring to different types of pneumonia. Extensive experimentations using two different datasets provide very satisfactory detection performance with accuracy of 97.4% for COVID/Normal, 96.9% for COVID/Viral pneumonia, 94.7% for COVID/Bacterial pneumonia, and 90.2% for multiclass COVID/normal/Viral/Bacterial pneumonias. Hence, the proposed schemes can serve as an efficient tool in the current state of COVID-19 pandemic. All the architectures are made publicly available at: https://github.com/Perceptron21/CovXNet.

Reporting radiographers' interpretation and use of the British Society of Thoracic Imaging's coding system when reporting COVID-19 chest x-rays

IntroductionThe United Kingdom (UK) has experienced one of the worst initial waves of the COVID-19 pandemic. Clinical signs help guide initial diagnosis, though definitive diagnosis is made using the laboratory technique reverse transcription polymerase chain reaction (RT-PCR). The chest x-ray (CXR) is used as the primary imaging investigation in the United Kingdom (UK) for patients with suspected COVID-19. In some hospitals these CXRs may be reported by a radiographer. MethodsRetrospective review of CXR reports by radiographers for suspected COVID-19 patients attending the Emergency Department (ED) of a hospital in the UK. Interpretation and use of the British Society of Thoracic Imaging (BSTI) coding system was assessed. Report description and code use were cross-checked. Report and code usage were checked against the RT-PCR result to determine accuracy. Report availability was checked against the availability of the RT-PCR result. A confusion matrix was utilised to determine performance. The data were analysed manually using Excel. ResultsSample size was 320 patients; 54.1% male patients (n = 173), 45.9% female patients (n = 147). The correct code matched report descriptions in 316 of the 320 cases (98.8%). In 299 of the 320 cases (93.4%), the reports were available before the RT-PCR swab result. CXR sensitivity for detecting COVID-19 was 85% compared to 93% for the initial RT-PCR. ConclusionReporting radiographers can adequately utilise and apply the BSTI classification system when reporting COVID-19 CXRs. They can recognise the classic CXR appearances of COVID-19 and those with normal appearances. Future best practice includes checking laboratory results when reporting CXRs with ambiguous appearances. Implications for practiceUtilisation of reporting radiographers to report CXRs in any future respiratory pandemic should be considered a service-enabling development.

Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review

The challenge of learning a new concept, object, or a new medical disease recognition without receiving any examples beforehand is called Zero-Shot Learning (ZSL). One of the major issues in deep learning-based methodologies such as in Medical Imaging, Autonomous Systems and other real-world applications is the requirement of feeding a large annotated and labelled datasets, prepared by an expert human to train the network model. ZSL is known for having minimal human intervention by mainly relying only on previously known concepts and current auxiliary information. This is ever-growing research for the cases where we have very limited or no datasets available and at the same time, the detection/recognition system has human-like characteristics in learning new concepts. Therefore, it makes it applicable in real-world scenarios, from developing autonomous vehicles to medical imaging and COVID-19 Chest X-Ray (CXR) based diagnosis. In this review paper, we present the definition of the problem, we review over fundamentals, and the challenging steps of Zero-Shot Learning, including state-of-the-art categories of solutions as well as our recommended solution, motivations behind each approach, and their advantages over each category to guide the researchers to proceed with the best techniques and practices based on their applications. Inspired from different settings and extensions, we introduce a novel and broaden solution called one$\slash$few-shot learning. We then review through different image datasets inducing medical and non-medical images, the variety of splits, and the evaluation protocols proposed so far. Finally, we discuss the recent applications and future directions of ZSL. We aim to convey a useful intuition through this paper towards the goal of handling complex computer vision learning tasks more similar to the way humans learn. We mainly focus on two applications in the current modern yet challenging era: copping with an early and fast diagnosis of COVID-19 cases in the 2020 pandemic, as well as helping to develop safer autonomous systems, such as self-driving cars and ambulances.

Weakly Labeled Data Augmentation for Deep Learning: A Study on COVID-19 Detection in Chest X-Rays.

The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic resulting in over 2.7 million infected individuals and over 190,000 deaths and growing. Assertions in the literature suggest that respiratory disorders due to COVID-19 commonly present with pneumonia-like symptoms which are radiologically confirmed as opacities. Radiology serves as an adjunct to the reverse transcription-polymerase chain reaction test for confirmation and evaluating disease progression. While computed tomography (CT) imaging is more specific than chest X-rays (CXR), its use is limited due to cross-contamination concerns. CXR imaging is commonly used in high-demand situations, placing a significant burden on radiology services. The use of artificial intelligence (AI) has been suggested to alleviate this burden. However, there is a dearth of sufficient training data for developing image-based AI tools. We propose increasing training data for recognizing COVID-19 pneumonia opacities using weakly labeled data augmentation. This follows from a hypothesis that the COVID-19 manifestation would be similar to that caused by other viral pathogens affecting the lungs. We expand the training data distribution for supervised learning through the use of weakly labeled CXR images, automatically pooled from publicly available pneumonia datasets, to classify them into those with bacterial or viral pneumonia opacities. Next, we use these selected images in a stage-wise, strategic approach to train convolutional neural network-based algorithms and compare against those trained with non-augmented data. Weakly labeled data augmentation expands the learned feature space in an attempt to encompass variability in unseen test distributions, enhance inter-class discrimination, and reduce the generalization error. Empirical evaluations demonstrate that simple weakly labeled data augmentation (Acc: 0.5555 and Acc: 0.6536) is better than baseline non-augmented training (Acc: 0.2885 and Acc: 0.5028) in identifying COVID-19 manifestations as viral pneumonia. Interestingly, adding COVID-19 CXRs to simple weakly labeled augmented training data significantly improves the performance (Acc: 0.7095 and Acc: 0.8889), suggesting that COVID-19, though viral in origin, creates a uniquely different presentation in CXRs compared with other viral pneumonia manifestations.

Detection and identification of COVID -19 based on chest medical image by using convolutional neural networks

Covid-19 pandemic has caused major out-break all around the world. This pandemic out-break requires lot of testing, which is a tedious process. Deep learning is a successful method that has evolved in image category in the past few years. In this work to detects the presence of coronavirus by using deep learning approach. Here, convolutional neural networks with specific focus on to classify Covid-19 chest radiography images. The database comprises Covid-19, normal and viral pneumonia chest X-ray images with 800 different samples under each class. We evaluated the model on 500 images and the networks has achieved a sensitivity rate of 95% and specificity rate of 97%. The DenseNet121 Architecture performed slightly better, compared to other state of art networks. The performance achieved by the method proposed is very encouraging and the accuracy rates can be improved further with larger datasets. Apart from sensitivity and specificity rates, the proposed model is also compared on receiver operating characteristic (ROC), and area under the curve (AUC) of each model. The model is implemented on the TensorFlow framework with the datasets that are publicly available for research community.

COVID-19 Detection from Chest X-ray Images using CNNs Models: Further Evidence from Deep Transfer Learning

Introduction: The early automatic diagnosis of the novel coronavirus (COVID-19) disease could be very helpful to reduce its spread around the world. In this study, we revisit the identification of COVID-19 from chest X-ray images using deep learning. Methods: We collected a relatively large COVID-19 dataset—compared with previous studies—containing 309 real COVID-19 chest X-ray images. We also prepared 2,000 chest X-ray images of pneumonia cases and 1,000 images of healthy controls. Deep transfer learning was used to detect abnormalities in our image dataset. We fine-tuned three, pre-trained convolutional neural network (CNN) models on a training dataset: DenseNet 121, NASNetLarge, and NASNet-Mobile. Results: The evaluation of our models on a test dataset showed that these models achieved an average sensitivity rate of approximately 99.45% and an average specificity rate of approximately 99.5%. Conclusion: A larger dataset of COVID-19 X-ray images could lead to more accurate and reliable identification of COVID-19 infections using deep transfer learning. However, the clinical diagnosis of COVID-19 disease is always necessary.

Detection of COVID-19 chest X-ray using support vector machine and convolutional neural network

This study aims to detect whether patients examined are healthy, Coronavirus positive, or just have pneumonia based on chest X-ray data using Convolutional Neural Network method as feature extraction and Support Vector Machine as a classification method or called Convolutional Support Vector Machine. Experiments carried out were comparing the kernel used, feature selection methods, architecture in feature extraction, and separated classes. Our instrument reached the accuracy of 97.33% in the separation of 3 classes (normal, pneumonia, COVID19) and 100% in the separation of 2 classes, that is (normal, COVID19) and (pneumonia, COVID19), respectively. Based on these results, it can be concluded that the feature selection method can improve gained accuracy ±98%.