Coronavirus (COVID-19) detection from chest radiology images using convolutional neural networks

Gilanie, Ghulam; Bajwa, Usama Ijaz; Waraich, Mustansar Mahmood; Asghar, Mutyyba; Kousar, Rehana; Kashif, Adnan; Aslam, Rabab Shereen; Qasim, Muhammad; Rafique, Hamza

doi:10.1016/j.bspc.2021.102490

Cited by 61 publications

(32 citation statements)

References 8 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are 12 state-of-the-art CNN models from recent COVID-19 works that have been selected to be the performance benchmark for the proposed Residual-Shuffle-Net. All 12 models have utilized CNN classifiers for their COVID-19 detection system based on input from X-ray images, which are Hussain et al [22], Narin et al [9], and Gilanie et al [40]. Five of the methods have used existing popular models, in which the models have been properly defined by the original authors, while the other seven methods have been selected because of their networks' details were fully explained in their paper.…”

Section: Methodsmentioning

confidence: 99%

“…They have also utilized a two-stage training, whereby the first stage focuses on the general classification of various pneumonia cases, and the second stage only focuses on differentiating between a COVID-19 case or not. The network introduced by Gilanie et al [40] is unique in the sense that all convolution kernels are in the size of 5x5, which makes it less optimal for Tensorflow application. Their straightforward network consists of eight layers of convolution operator without applying any batch normalization technique.…”

Section: Convolutional Neural Network For Covid-19 Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Residual-Shuffle Network with Spatial Pyramid Pooling Module for COVID-19 Screening

et al. 2021

View full text Add to dashboard Cite

Since the start of the COVID-19 pandemic at the end of 2019, more than 170 million patients have been infected with the virus that has resulted in more than 3.8 million deaths all over the world. This disease is easily spreadable from one person to another even with minimal contact, even more for the latest mutations that are more deadly than its predecessor. Hence, COVID-19 needs to be diagnosed as early as possible to minimize the risk of spreading among the community. However, the laboratory results on the approved diagnosis method by the World Health Organization, the reverse transcription-polymerase chain reaction test, takes around a day to be processed, where a longer period is observed in the developing countries. Therefore, a fast screening method that is based on existing facilities should be developed to complement this diagnosis test, so that a suspected patient can be isolated in a quarantine center. In line with this motivation, deep learning techniques were explored to provide an automated COVID-19 screening system based on X-ray imaging. This imaging modality is chosen because of its low-cost procedures that are widely available even in many small clinics. A new convolutional neural network (CNN) model is proposed instead of utilizing pre-trained networks of the existing models. The proposed network, Residual-Shuffle-Net, comprises four stacks of the residual-shuffle unit followed by a spatial pyramid pooling (SPP) unit. The architecture of the residual-shuffle unit follows an hourglass design with reduced convolution filter size in the middle layer, where a shuffle operation is performed right after the split branches have been concatenated back. Shuffle operation forces the network to learn multiple sets of features relationship across various channels instead of a set of global features. The SPP unit, which is placed at the end of the network, allows the model to learn multi-scale features that are crucial to distinguish between the COVID-19 and other types of pneumonia cases. The proposed network is benchmarked with 12 other state-of-the-art CNN models that have been designed and tuned specially for COVID-19 detection. The experimental results show that the Residual-Shuffle-Net produced the best performance in terms of accuracy and specificity metrics with 0.97390 and 0.98695, respectively. The model is also considered as a lightweight model with slightly more than 2 million parameters, which makes it suitable for mobile-based applications. For future work, an attention mechanism can be integrated to target certain regions of interest in the X-ray images that are deemed to be more informative for COVID-19 diagnosis.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Convolutional Neural Network For Covid-19 Detectionmentioning

confidence: 99%

Residual-Shuffle Network with Spatial Pyramid Pooling Module for COVID-19 Screening

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Deep learning models have rapidly become a methodology for analyzing X-ray images [47][48][49]. As shown in [50,51], the most successful type of deep learning model for X-ray image analysis to date is CNN. CNNs consist of many layers that transform their input with convolution filters of a small extent.…”

Section: Deep Convolution Neural Networkmentioning

confidence: 99%

Real‑time COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithm

Khishe²,

Mohammadi

et al. 2021

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Real-time detection of COVID-19 using radiological images has gained priority due to the increasing demand for fast diagnosis of COVID-19 cases. This paper introduces a novel two-phase approach for classifying chest X-ray images. Deep Learning (DL) methods fail to cover these aspects since training and fine-tuning the model's parameters consume much time. In this approach, the first phase comes to train a deep CNN working as a feature extractor, and the second phase comes to use Extreme Learning Machines (ELMs) for real-time detection. The main drawback of ELMs is to meet the need of a large number of hidden-layer nodes to gain a reliable and accurate detector in applying image processing since the detective performance remarkably depends on the setting of initial weights and biases. Therefore, this paper uses Chimp Optimization Algorithm (ChOA) to improve results and increase the reliability of the network while maintaining real-time capability. The designed detector is to be benchmarked on the COVID-Xray-5k and COVIDetectioNet datasets, and the results are verified by comparing it with the classic DCNN, Genetic Algorithm optimized ELM (GA-ELM), Cuckoo Search optimized ELM (CS-ELM), and Whale Optimization Algorithm optimized ELM (WOA-ELM). The proposed approach outperforms other comparative benchmarks with 98.25% and 99.11% as ultimate accuracy on the COVID-Xray-5k and COVIDetectioNet datasets, respectively, and it led relative error to reduce as the amount of 1.75% and 1.01% as compared to a convolutional CNN. More importantly, the time needed for training deep ChOA-ELM is only 0.9474 milliseconds, and the overall testing time for 3100 images is 2.937 seconds.

show abstract

“…To expand the size of the small set of COVID-19 images, one of the promising methods is data augmentation [11] , [13] . Continuous efforts are made employing various machine learning (ML) algorithms where the database of increased number of images are used [21] , [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] . Chandra et al.…”

Section: Introductionmentioning

confidence: 99%

“…Two more CNN models are conceived by Gilanie et al. [25] and Das et al. [26] for automated detection of COVID-19 CXR images.…”

Section: Introductionmentioning

confidence: 99%

An optimized KELM approach for the diagnosis of COVID-19 from 2D-SSA reconstructed CXR Images

Mohanty

Dora

2021

Optik

View full text Add to dashboard Cite

The COVID-19 is proved to be the most infectious disease of the current century with a high mortality rate world-wide. The current RT-PCR test standard for the diagnosis of COVID-19 is an invasive and time-consuming procedure, whereas the chest X-ray (CXR) images provide a non-invasive and time/cost-effective method for COVID-19 diagnosis. The current existing deep learning methods for the detection and diagnosis of CXR images provide biased results for the small size dataset available. Hence, in the present work, a conventional yet efficient method is proposed classifying the CXR images into COVID-19 , Pneumonia , and Normal . The proposed approach pre-processes the CXR images using 2D singular spectrum analysis (SSA) for image reconstruction which enhances the feature inputs to the classifier. The features are extracted from the reconstructed images using a block-based GLCM approach. Then, a grasshopper-based Kernel extreme learning machine (KELM) is proposed which finds the optimal features and kernel parameters of KELM at the same instance. From the experimental analysis, it is seen that the present work outperforms that of other competent schemes in terms of classification accuracy with a minimal set of features extracted from the first 2 eigen components of the 2D-SSA reconstructed image with 5 × 5 decomposition.

show abstract

Coronavirus (COVID-19) detection from chest radiology images using convolutional neural networks

Cited by 61 publications

References 8 publications

Residual-Shuffle Network with Spatial Pyramid Pooling Module for COVID-19 Screening

Residual-Shuffle Network with Spatial Pyramid Pooling Module for COVID-19 Screening

Real‑time COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithm

An optimized KELM approach for the diagnosis of COVID-19 from 2D-SSA reconstructed CXR Images

Contact Info

Product

Resources

About