Detection of novel coronavirus from chest X-rays using deep convolutional neural networks

Abstract

With over 172 Million people infected with the novel coronavirus (COVID-19) globally and with the numbers increasing exponentially, the dire need of a fast diagnostic system keeps on surging. With shortage of kits, and deadly underlying disease due to its vastly mutating and contagious properties, the tired physicians need a fast diagnostic method to cater the requirements of the soaring number of infected patients. Laboratory testing has turned out to be an arduous, cost-ineffective and requiring a well-equipped laboratory for analysis. This paper proposes a convolutional neural network (CNN) based model for analysis/detection of COVID-19, dubbed as CovCNN, which uses the patient’s chest X-ray images for the diagnosis of COVID-19 with an aim to assist the medical practitioners to expedite the diagnostic process amongst high workload conditions. In the proposed CovCNN model, a novel deep-CNN based architecture has been incorporated with multiple folds of CNN. These models utilize depth wise convolution with varying dilation rates for efficiently extracting diversified features from chest X-rays. 657 chest X-rays of which 219 were X-ray images of patients infected from COVID-19 and the remaining were the images of non-COVID-19 (i.e. normal or COVID-19 negative) patients. Further, performance evaluation on the dataset using different pre-trained models has been analyzed based on the loss and accuracy curve. The experimental results show that the highest classification accuracy (98.4%) is achieved using the proposed CovCNN model.

Detection of Diabetic Retinopathy using Convolutional Neural Networks

“…To expedite the diagnostic process and provide accurate predictions, a Convolutional Neural Network (CNN) approach has been developed. CNN technology, already proven effective in various domains such as healthcare [1,2] and intelligent automation [3], is leveraged in this study. By harnessing its capabilities, the CNN model is applied to diagnose diabetic retinopathy from eye images and classify them based on severity accurately.…”

A Novel Technique for Detecting Various Thyroid Diseases Using Deep Learning

“…It employs two-dimensional convolutional layers, making it ideal for processing 2D data such as pictures. In [4] authors have proposed a CNN based model for analysis/ detection of COVID-19, to assist the medical practitioners to expedite the diagnostic process amongst high workload conditions. It does away with the necessity for manual feature extraction, removing the need to identify the features that are utilized to classify images.…”

A deep learning-based COVID-19 classification from chest X-ray image: case study

“…Deep learning based automated COVID‑19 Screening Chest X‑ray Classification is designed by Shelke et al can further classify mild, medium, and severe COVID‑19 [ 2 ]. Convolutional neural network architectures like ResNet101, Xception, InceptionV3, InceptionResNetV2, VGG16, and VGG19 are used for COVID-19 classification from chest x-ray images [ 3 ]. Hammoudi et al developed hierarchical classification of COVID-19 from pneumonia viral classification with comparative study for performance evaluation and exceeded 84% of average accuracy [ 7 ].…”

“…Artificial intelligence techniques can be used to detect the presence and degree of illness based on the major difference between X-ray images of an infected and non-infected person [ 2 ]. The majority of existing research on COVID-19 detection focuses on pre-trained models and standard CNN architecture rather than customized architecture [ 3 ]. The early detection of COVID-19 heavily relies on the analysis of lung images.…”