ABSTRACT
COVID-19 is a type of disease that transmits a new variant of virus known as Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) in the same novel coronavirus family as SARS-CoV and Middle East Respiratory Syndrome Coronovirus (MERS-COV). A fast method to detect the disease is essential to prevent larger transmission and to look after the infected patients. The Chest X-ray, one of the detection methods of COVID-19 can be used in the examination process of suspected cases. In this paper, a COVID-19 detection model through chest x-ray images is proposed by using Grey Level Co-occurrence Matrix (GLCM) with Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Backpropagation Artificial Neural Network (BP-ANN) classifiers. In this case, Principal Component Analysis (PCA) will be added as a mean to optimize features extraction process. The aim of this work is to find the best classifier for predicting chest x-ray images as normal, pneumonia, or COVID-19 suspect. The BP-ANN emerged as the best classifier with 85,5% accuracy, 85,8% precision, and 86,1% recall. © 2023 Author(s).
ABSTRACT
A COVID-19 patient suffers from blockage of breathing and chest pain at a critical condition due to the formation of fibrosis in the lungs and needs emergency lifesaving treatment. Before starting an adequate treatment, a confirmed diagnosis of COVID-19 is a mandatory criterion. For a patient with critical respiratory syndrome, rapid and precise diagnosis is a prime challenge. Different manual methods of clinical diagnosis are in practice. However, these manual techniques suffer from serious drawbacks such as poor sensitivity, false negative results, and high turn-around time. The diagnosis based on the radiographic image (X-ray or computed tomography) of infected lungs is another clinical method for rapid diagnosis of COVID-19. However, it requires an expert radiologist for precise diagnosis. Instead of a prolonged clinical process, an alternative way of rapid diagnosis is the only way of some lifesaving. As an elegant solution, some radiographic image-based automated diagnostic systems have been suggested using deep learning techniques. However, they suffer from some unavoidable limitations concerned with deep learning. This paper suggests a user-friendly system for instant diagnosis of COVID-19 using radiographic images of infected lungs of a critical patient. The model is designed based on classical image processing techniques and machine learning techniques that have provided low complexity but a very high accuracy of 98.51%. In this pandemic situation, such a simple and instantaneous diagnostic system can become a silver lining to compensate for the scarcity of expert radiologists. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
A COVID-19 patient suffers from blockage of breathing and chest pain at a critical condition due to the formation of fibrosis in the lungs and needs emergency lifesaving treatment. Before starting an adequate treatment, a confirmed diagnosis of COVID-19 is a mandatory criterion. For a patient with critical respiratory syndrome, rapid and precise diagnosis is a prime challenge. Different manual methods of clinical diagnosis are in practice. However, these manual techniques suffer from serious drawbacks such as poor sensitivity, false negative results, and high turn-around time. The diagnosis based on the radiographic image (X-ray or computed tomography) of infected lungs is another clinical method for rapid diagnosis of COVID-19. However, it requires an expert radiologist for precise diagnosis. Instead of a prolonged clinical process, an alternative way of rapid diagnosis is the only way of some lifesaving. As an elegant solution, some radiographic image-based automated diagnostic systems have been suggested using deep learning techniques. However, they suffer from some unavoidable limitations concerned with deep learning. This paper suggests a user-friendly system for instant diagnosis of COVID-19 using radiographic images of infected lungs of a critical patient. The model is designed based on classical image processing techniques and machine learning techniques that have provided low complexity but a very high accuracy of 98.51%. In this pandemic situation, such a simple and instantaneous diagnostic system can become a silver lining to compensate for the scarcity of expert radiologists. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
BACKGROUND: Given the current pandemic, differentiation between pneumonia induced by COVID-19 or influenza viruses is of utmost clinical significance in the patients' management. For this purpose, this study was conducted to develop sensitive artificial intelligence (AI) models to assist radiologists to decisively differentiate pneumonia due to COVID-19 versus influenza viruses. METHODS: Cross sectional chest CT images (N=12744) from well-evaluated cases of pneumonias induced by COVID-19 or H1N1 Influenza viruses, and normal individuals were collected. We examined the computer tomographic (CT) chest images from 137 individuals. Various pre-trained convolutional neural network models, such as ResNet-50, InceptionV3, Wide ResNet, SqueezNet, VGG 16 and VGG 19 were fine-tuned on our datasets. The datasets were used for training (60%), validation (20%), and testing (20%) of the final models. Also, the predictive power and means of precision and recall were determined for each model. RESULTS: Fine-tuned ResNet-50 model differentiated the pneumonia due to COVID-19 or H1N1 influenza virus with accuracies of 96.7% and 92%, respectively This model outperformed all others, i.e., InceptionV3, Wide ResNet, SqueezNet, VGG 16 and VGG 19. CONCLUSION: Fine-tuned and pre-trained image classifying models of AI enable radiologists to reliably differentiate the pneumonia induced by COVID-19 versus H1N1 influenza virus. For this purpose, ResNet-50 followed by InceptionV3 models proved more promising than other AI models. Also in the supplements, we share the source codes and our fine-tuned models for use by researchers and clinicians globally toward the critical task of image differentiation of patients infected with COVID-19 versus H1N1 Influenza viruses.
ABSTRACT
OBJECTIVE: The study sought to test the possibility of differentiating chest x-ray images of coronavirus disease 2019 (COVID-19) against other pneumonia and healthy patients using deep neural networks. MATERIALS AND METHODS: We construct the radiography (x-ray) imaging data from 2 publicly available sources, which include 5508 chest x-ray images across 2874 patients with 4 classes: normal, bacterial pneumonia, non-COVID-19 viral pneumonia, and COVID-19. To identify COVID-19, we propose a FLANNEL (Focal Loss bAsed Neural Network EnsembLe) model, a flexible module to ensemble several convolutional neural network models and fuse with a focal loss for accurate COVID-19 detection on class imbalance data. RESULTS: FLANNEL consistently outperforms baseline models on COVID-19 identification task in all metrics. Compared with the best baseline, FLANNEL shows a higher macro-F1 score, with 6% relative increase on the COVID-19 identification task, in which it achieves precision of 0.7833 ± 0.07, recall of 0.8609 ± 0.03, and F1 score of 0.8168 ± 0.03. DISCUSSION: Ensemble learning that combines multiple independent basis classifiers can increase the robustness and accuracy. We propose a neural weighing module to learn the importance weight for each base model and combine them via weighted ensemble to get the final classification results. In order to handle the class imbalance challenge, we adapt focal loss to our multiple classification task as the loss function. CONCLUSION: FLANNEL effectively combines state-of-the-art convolutional neural network classification models and tackles class imbalance with focal loss to achieve better performance on COVID-19 detection from x-rays.