An efficient method of detection of COVID-19 using Mask R-CNN on chest X-Ray images

Podder, Soumyajit; Bhattacharjee, Swarupananda; Roy, Arijit

doi:10.3934/biophy.2021022

Cited by 21 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initially Covid-19 is detected using a pre-trained Mask R-CNN algorithm with a base classifier of ResNet-50, which were trained for 100 epochs. Various ResNet models were compared for detecting covid-19 as shown in Table 5 , where ResNet-50 performs well when compared other models ( Podder et al, 2021 ).…”

Section: Experimentation and Results Discussionmentioning

confidence: 99%

“…Initially Chest CT images were taken as input image, the Feature-Pyramid-Network helps to extract the essential features in the chest image. In general Mask R-CNN performs pixel level segmentation, here the Chest CT image is segmented into pixel and classifies the images accurately ( Podder et al, 2021 ). The feature maps directly send the extracted feature to ROI Align as well as to the Region Proposal Network (RPN).…”

Section: Proposed Approachmentioning

confidence: 99%

“…Meta-based few-shot learning: Previous works used meta-learning to construct a model or optimizer that can rapidly modify and update the values for adaptation to the unseen tasks outlined by Podder et al (2021) in order to address the data insufficiency in few-shot learning. Ye et al (2020) , for instance, talked about the Meta Network, which gathered meta-level information for quick generalization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prognosticating various acute covid lung disorders from COVID-19 patient using chest CT Images

Suganya

Kalpana

2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Section: Experimentation and Results Discussionmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prognosticating various acute covid lung disorders from COVID-19 patient using chest CT Images

Suganya

Kalpana

2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…To identify abnormalities in X-ray scans, the suggested models were trained for multiclass classification. The authors in [ 44 ] employed the Mask R-CNN approach on the X-ray dataset in order to categorize patients with and without the COVID-19 infection. Five-fold cross-validation was used to train the Mask R-CNN for 100 epochs.…”

Section: Literature Reviewmentioning

confidence: 99%

LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images

Shamrat

Azam

Karim

et al. 2022

JPM

View full text Add to dashboard Cite

In recent years, lung disease has increased manyfold, causing millions of casualties annually. To combat the crisis, an efficient, reliable, and affordable lung disease diagnosis technique has become indispensable. In this study, a multiclass classification of lung disease from frontal chest X-ray imaging using a fine-tuned CNN model is proposed. The classification is conducted on 10 disease classes of the lungs, namely COVID-19, Effusion, Tuberculosis, Pneumonia, Lung Opacity, Mass, Nodule, Pneumothorax, and Pulmonary Fibrosis, along with the Normal class. The dataset is a collective dataset gathered from multiple sources. After pre-processing and balancing the dataset with eight augmentation techniques, a total of 80,000 X-ray images were fed to the model for classification purposes. Initially, eight pre-trained CNN models, AlexNet, GoogLeNet, InceptionV3, MobileNetV2, VGG16, ResNet 50, DenseNet121, and EfficientNetB7, were employed on the dataset. Among these, the VGG16 achieved the highest accuracy at 92.95%. To further improve the classification accuracy, LungNet22 was constructed upon the primary structure of the VGG16 model. An ablation study was used in the work to determine the different hyper-parameters. Using the Adam Optimizer, the proposed model achieved a commendable accuracy of 98.89%. To verify the performance of the model, several performance matrices, including the ROC curve and the AUC values, were computed as well.

show abstract

“…Apostolopoulos et al [32] [37] using CXR images. The Mask R-CNN DL network is proposed to classify the COVID-19 by Soumyajit P., et al [38]. For segmenting the Lung fields of the CXR images, LF-SegNet was developed by Mittal, A. et al [39].…”

Section: Related Workmentioning

confidence: 99%

Optimized chest X-ray image semantic segmentation networks for COVID-19 early detection

Gopatoti

Vijayalakshmi

2022

XST

View full text Add to dashboard Cite

BACKGROUND: Although detection of COVID-19 from chest X-ray radiography (CXR) images is faster that PCR sputum testing, the accuracy of detecting COVID-19 from CXR images is lacking in the existing deep learning models. OBJECTIVE: This study aims to classify COVID-19 and normal patients from CXR images using semantic segmentation networks for detecting and labeling COVID-19 infected lung lobes in CXR images. METHODS: For semantically segmenting infected lung lobes in CXR images for COVID-19 early detection, three structurally different deep learning (DL) networks such as SegNet, U-Net and hybrid CNN with SegNet plus U-Net, are proposed and investigated. Further, the optimized CXR image semantic segmentation networks such as GWO SegNet, GWO U-Net, and GWO hybrid CNN are developed with the grey wolf optimization (GWO) algorithm. The proposed DL networks are trained, tested, and validated without and with optimization on the openly available dataset that contains 2,572 COVID-19 CXR images including 2,174 training images and 398 testing images. The DL networks and their GWO optimized networks are also compared with other state-of-the-art models used to detect COVID-19 CXR images. RESULTS: All optimized CXR image semantic segmentation networks for COVID-19 image detection developed in this study achieved detection accuracy higher than 92%. The result shows the superiority of optimized SegNet in segmenting COVID-19 infected lung lobes and classifying with an accuracy of 98.08% compared to optimized U-Net and hybrid CNN. CONCLUSION: The optimized DL networks has potential to be utilised to more objectively and accurately identify COVID-19 disease using semantic segmentation of COVID-19 CXR images of the lungs.

show abstract

An efficient method of detection of COVID-19 using Mask R-CNN on chest X-Ray images

Cited by 21 publications

References 26 publications

Prognosticating various acute covid lung disorders from COVID-19 patient using chest CT Images

Prognosticating various acute covid lung disorders from COVID-19 patient using chest CT Images

LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images

Optimized chest X-ray image semantic segmentation networks for COVID-19 early detection

Contact Info

Product

Resources

About