Convolutional capsule network for <scp>COVID</scp>‐19 detection using radiography images

Tiwari, Shamik; Jain, Anurag

doi:10.1002/ima.22566

Cited by 50 publications

(41 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The papers reported in [12] implemented as pre-trained CNNs for the detection of COVID-19 from x-ray images, such as MobileNet-v2 [13] , ResNet-v2 [14] VGG-19 [15] and Inception [16] . The two pretraining CNNs used two data sets, which consisted of COVID-19 images, viral pneumonia, bacterial pneumonia, and solid conditions, in the case of 2 and 3 classifications.…”

Section: Literature Surveymentioning

confidence: 99%

COVID-19 prediction through X-ray images using transfer learning-based hybrid deep learning approach

Kumar

Shakya

Kurup

et al. 2022

Materials Today: Proceedings

View full text Add to dashboard Cite

Over the past few months, the campaign against COVID-19 has developed into one of the world's most sought anti-toxin treatment scheme. It is fundamental to distinguish cases of COVID-19 precisely and quickly to help avoid this pandemic from taking a wrong turn with a proper medical reasoning and solution. While Reverse-Transcription Polymerase Chain Reaction (RT-PCR) has been useful in detection of corona virus, chest X-Ray techniques has proven to be more successful and beneficial at detection of the effects of virus. With the increase in COVID patients and the X-Rays done, it is currently possible to classify the X-Ray reports with transfer learning. This paper presents a novel approach, i.e., Hybrid Convolutional Neural Network (HDCNN), which integrates Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) architecture for the finding of COVID-19 using the chest X-Ray. The transfer learning approach, namely slope weighted activation class planning (Grad-CAMs), is used with HDCNN to display images responsible for taking decisions. In this study, HDCNN is compared with other CNNs such as Inception-v3, ShuffleNet, SqueezeNet, VGG-19 and DenseNet. As a result, HDCNN has achieved an accuracy of 98.20%, precision of 97.31%, recall of 97.1% and F1 score of 0.97. Compared to other current deep learning models, the HDCNN has achieved better results, and this can be used for diagnosis purpose after proper approvals.

show abstract

Section: Literature Surveymentioning

confidence: 99%

COVID-19 prediction through X-ray images using transfer learning-based hybrid deep learning approach

Kumar

Shakya

Kurup

et al. 2022

Materials Today: Proceedings

View full text Add to dashboard Cite

show abstract

“…CNN is one such type of deep neural network, which is also known as the ConvNet model. It mainly comprises three layers, namely (1) convolution layer, (2) pooling layer, and (3) dense layer (fully connected layer) [31]- [32]. The first layer i.e., the convolutional layer, is an essential building block of ConvNet.…”

Section: Convolutional Neural Network (Convnet)mentioning

confidence: 99%

Phonocardiogram Signal Based Multi-Class Cardiac Diagnostic Decision Support System

et al. 2021

Self Cite

View full text Add to dashboard Cite

A phonocardiogram (PCG) signal represents sounds and murmurs made by vibrations caused during a cardiac cycle. Acoustic wave generated through the beat of the cardiac cycle propagates through the chest wall. It can be easily recorded by a low-cost small handheld digital device called a stethoscope. It provides information like heart rate, intensity, tone, quality, frequency, and location of various components of cardiac sound. Due to these characteristics, phonocardiogram signals can be used to detect heart status at an early stage in a non-invasive manner. In previous studies, the convolutional neural network (ConvNet) is the most studied architecture, which was fed by three main features, namely Mel frequency cepstral (MFC), chroma energy normalized statistics (CENS), and constant-Q transform (CQT). In this paper, the authors have presented a hybrid constant-Q transform (HCQT) based CNN system for heart sound beat classification. CQT, variable-Q transform (VQT), and HCQT are extracted from each phonocardiogram signal as the acoustic features, including the dominant MFCC features, feed into five-layer regularized ConvNets. After analyzing the literature in the same domain, it can be stated that this is the first time HCQT is being utilized for PCG signals. Experimental results have shown that HCQT is more effective relative to the conventional CQT and other investigated features. Also, the accuracies of the system proposed in this work on the validation datasets are 96% in multi-class classification, which outperforms the proposed work relative to other models significantly.

show abstract

“…Authors conclude that their presented model with more than 96% score (in all parameters like Precision, Recall, F-Score, Specificity and Accuracy). In just recently published study researchers, Tiwari et al [ 42 ] suggested a system based on visual geometry group capsule network (VGG-CapsNet) to screen COVID-19 disease based on input images. The composed dataset contains around 2900 images belonging to three classes (normal, pneumonia and COVID-19).…”

Section: Introductionmentioning

confidence: 99%

Radiologist-Level Two Novel and Robust Automated Computer-Aided Prediction Models for Early Detection of COVID-19 Infection from Chest X-ray Images

et al. 2021

View full text Add to dashboard Cite

COVID-19 is an ongoing pandemic that is widely spreading daily and reaches a significant community spread. X-ray images, computed tomography (CT) images and test kits (RT-PCR) are three easily available options for predicting this infection. Compared to the screening of COVID-19 infection from X-ray and CT images, the test kits(RT-PCR) available to diagnose COVID-19 face problems such as high analytical time, high false negative outcomes, poor sensitivity and specificity. Radiological signatures that X-rays can detect have been found in COVID-19 positive patients. Radiologists may examine these signatures, but it's a time-consuming and error-prone process (riddled with intra-observer variability). Thus, the chest X-ray analysis process needs to be automated, for which AI-driven tools have proven to be the best choice to increase accuracy and speed up analysis time, especially in the case of medical image analysis. We shortlisted four datasets and 20 CNN-based models to test and validate the best ones using 16 detailed experiments with fivefold cross-validation. The two proposed models, ensemble deep transfer learning CNN model and hybrid LSTMCNN, perform the best. The accuracy of ensemble CNN was up to 99.78% (96.51% average-wise), F1-score up to 0.9977 (0.9682 average-wise) and AUC up to 0.9978 (0.9583 average-wise). The accuracy of LSTMCNN was up to 98.66% (96.46% average-wise), F1-score up to 0.9974 (0.9668 average-wise) and AUC up to 0.9856 (0.9645 average-wise). These two best pre-trained transfer learning-based detection models can contribute clinically by offering the patients prediction correctly and rapidly.

show abstract

Convolutional capsule network for COVID‐19 detection using radiography images

Cited by 50 publications

References 34 publications

COVID-19 prediction through X-ray images using transfer learning-based hybrid deep learning approach

COVID-19 prediction through X-ray images using transfer learning-based hybrid deep learning approach

Phonocardiogram Signal Based Multi-Class Cardiac Diagnostic Decision Support System

Radiologist-Level Two Novel and Robust Automated Computer-Aided Prediction Models for Early Detection of COVID-19 Infection from Chest X-ray Images

Contact Info

Product

Resources

About