Skip to content
2000
  • E-ISSN:

Abstract

Introduction:

Millions of people have been infected with COVID-19, which has spread quickly worldwide since the start of 2020, resulting in numerous fatalities. Identification of infected individuals is essential to control the spread of the virus.

Aims:

In this study, we propose a hybrid architecture that combines Convolutional Neural Networks (CNNs) with Recurrent Neural Networks (RNNs) and leverages transfer learning to enhance the accuracy of COVID-19 detection from X-ray images.

Methods:

The proposed work utilizes 4 pre-trained CNN architectures, namely, InceptionnetV3, Densenet121, Inception-ResNet V2, and VGG19, to extract high-level features from the input X-ray images. These features are then fed into the second component, an RNN-based network, which captures the temporal dependencies within the extracted features. To evaluate the performance of the proposed architecture, a comprehensive dataset consisting of X-ray images from COVID-19 positive cases, non-COVID-19 pneumonia cases, and healthy individuals is used. Gradient class activation map (Grad-CAM) analysis has been applied to the obtained results to provide heat-map pictures specific to each class and coloured visualizations of the COVID-19-infected areas in CXR images.

Results:

: Experimental results demonstrate that the proposed hybrid CNN-RNN architecture achieves promising results in COVID-19 detection from X-ray images. The model exhibits high accuracy, precision, recall, area under the receiver operating characteristics (ROC) curve (AUC), and F1-score, outperforming other state-of-the-art methods.

Conclusion:

The combination of CNNs and RNNs enables the model to effectively capture spatial and temporal information, leading to improved performance in COVID-19 detection. The proposed hybrid architecture with transfer learning from X-ray images provides a robust and efficient solution for COVID-19 detection. The model can potentially assist healthcare professionals in making accurate and timely diagnoses, thereby contributing to the global efforts to combat the COVID-19 pandemic. In the present work, VGG19-RNN architecture outperformed all other networks in terms of accuracy. The most effective training and validation accuracy for the VGG19-RNN architecture is 99% & 97.70%, respectively, and the loss was 0.02 & 0.09 at epoch 100.

This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmim/10.2174/1573405620666230817092337
2023-10-11
2025-01-10
Loading full text...

Full text loading...

/deliver/fulltext/cmim/20/1/e170823219874.html?itemId=/content/journals/cmim/10.2174/1573405620666230817092337&mimeType=html&fmt=ahah

References

  1. RehmanN. ZiaM.S. MerajT. RaufH.T. DamaševičiusR. El-SherbeenyA.M. El-MeligyM.A. A self-activated cnn approach for multi-class chest-related COVID-19 detection.Appl. Sci. (Basel)20211119902310.3390/app11199023
    [Google Scholar]
  2. AslanM.F. SabanciK. DurduA. UnlersenM.F. COVID-19 diagnosis using state-of-the-art CNN architecture features and Bayesian Optimization.Comput. Biol. Med.202214210524410.1016/j.compbiomed.2022.10524435077936
    [Google Scholar]
  3. El-KenawyE.S.M. IbrahimA. MirjaliliS. EidM.M. HusseinS.E. Novel feature selection and voting classifier algorithms for COVID-19 classification in CT images.IEEE Access2020817931717933510.1109/ACCESS.2020.302801234976558
    [Google Scholar]
  4. OhY. ParkS. YeJ.C. Deep learning COVID-19 features on CXR using limited training data sets.IEEE Trans. Med. Imaging20203982688270010.1109/TMI.2020.299329132396075
    [Google Scholar]
  5. AlakusT.B. TurkogluI. Comparison of deep learning approaches to predict COVID-19 infection.Chaos Solitons Fractals202014011012010.1016/j.chaos.2020.11012033519109
    [Google Scholar]
  6. KrishnaS.T. KalluriH.K. Deep Learning and Transfer Learning Approaches for Image Classification.J Rec Tech Eng201975S4427432
    [Google Scholar]
  7. ArdakaniA.A. KanafiA.R. AcharyaU.R. KhademN. MohammadiA. Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks.Comput. Biol. Med.202012110379510.1016/j.compbiomed.2020.10379532568676
    [Google Scholar]
  8. Al-RakhamiM.S. IslamM.M. IslamM.Z. AsrafA. SodhroA.H. DingW. 2021Diagnosis of COVID-19 from X-rays using combined CNN-RNN architecture with transfer learning.MedRxiv202008
    [Google Scholar]
  9. WangR. LiangX. ZhuX. XieY. A feasibility of respiration prediction based on deep Bi-LSTM for real-time tumor tracking.IEEE Access20186512625126810.1109/ACCESS.2018.2869780
    [Google Scholar]
  10. NingrumD.N.A. YuanS.P. KungW.M. WuC.C. TzengI.S. HuangC.Y. LiJ.Y.C. WangY.C. Deep learning classifier with patient’s metadata of dermoscopic images in malignant melanoma detection.J. Multidiscip. Healthc.20211487788510.2147/JMDH.S30628433907414
    [Google Scholar]
  11. AbdouM.A. Literature review: Efficient deep neural networks techniques for medical image analysis.Neural Comput. Appl.20223485791581210.1007/s00521‑022‑06960‑9
    [Google Scholar]
  12. KhanI.U. AslamN. A deep-learning-based framework for automated diagnosis of COVID-19 using X-ray images.Information (Basel)202011941910.3390/info11090419
    [Google Scholar]
  13. JaiswalA. BistA.S. Analysis of deep learning algorithms on COVID-19 radiography database.Int J Adv Sci Tech2020291112681275
    [Google Scholar]
  14. NourM. CömertZ. PolatK. A novel medical diagnosis model for COVID-19 infection detection based on deep features and Bayesian optimization.Appl. Soft Comput.20209710658010.1016/j.asoc.2020.10658032837453
    [Google Scholar]
  15. ChowdhuryM.E.H. RahmanT. KhandakarA. MazharR. KadirM.A. MahbubZ.B. IslamK.R. KhanM.S. IqbalA. EmadiN.A. ReazM.B.I. IslamM.T. Can AI help in screening viral and COVID-19 pneumonia?IEEE Access2020813266513267610.1109/ACCESS.2020.3010287
    [Google Scholar]
  16. AsifS. WenhuiY. JinH. JinhaiS. 2020Classification of COVID-19 from chest X-ray images using deep convolutional neural network.2020 IEEE 6th International Conference on Computer and Communications (ICCC)Chengdu202010.1109/ICCC51575.2020.9344870
    [Google Scholar]
  17. ToğaçarM. ErgenB. CömertZ. COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches.Comput. Biol. Med.202012110380510.1016/j.compbiomed.2020.10380532568679
    [Google Scholar]
  18. UcarF. KorkmazD. COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images.Med. Hypotheses202014010976110.1016/j.mehy.2020.10976132344309
    [Google Scholar]
  19. OzturkT. TaloM. YildirimE.A. BalogluU.B. YildirimO. Rajendra AcharyaU. Automated detection of COVID-19 cases using deep neural networks with X-ray images.Comput. Biol. Med.202012110379210.1016/j.compbiomed.2020.10379232568675
    [Google Scholar]
  20. KhanA.I. ShahJ.L. BhatM.M. CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images.Comput. Methods Programs Biomed.202019610558110.1016/j.cmpb.2020.10558132534344
    [Google Scholar]
  21. SardarR. SharmaA. GuptaD. Machine learning assisted prediction of prognostic biomarkers associated with COVID-19, using clinical and proteomics data.Front. Genet.20211263644110.3389/fgene.2021.63644134093642
    [Google Scholar]
  22. NarinA. KayaC. PamukZ. Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks.Pattern Anal. Appl.20212431207122010.1007/s10044‑021‑00984‑y33994847
    [Google Scholar]
  23. AhujaS. PanigrahiB.K. DeyN. RajinikanthV. GandhiT.K. Deep transfer learning-based automated detection of COVID-19 from lung CT scan slices.Appl. Intell.202151157158510.1007/s10489‑020‑01826‑w34764547
    [Google Scholar]
  24. SinghM. BansalS. AhujaS. DubeyR.K. PanigrahiB.K. DeyN. Transfer learning–based ensemble support vector machine model for automated COVID-19 detection using lung computerized tomography scan data.Med. Biol. Eng. Comput.202159482583910.1007/s11517‑020‑02299‑233738639
    [Google Scholar]
  25. HuY. WongY. WeiW. DuY. KankanhalliM. GengW. A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition.PLoS One20181310e020604910.1371/journal.pone.020604930376567
    [Google Scholar]
  26. NasirJ.A. KhanO.S. VarlamisI. Fake news detection: A hybrid CNN-RNN based deep learning approach.International Journal of Information Management Data Insights20211110000710.1016/j.jjimei.2020.100007
    [Google Scholar]
  27. PatelPRASHANT Chest X-ray (Covid-19 & Pneumonia) Dataset contains chest x-ray images of Covid-19, Pneumonia and normal patient2020https://www.kaggle.com/prashant268/chest-xray-covid19-pneumonia
  28. WangS. KangB. MaJ. ZengX. XiaoM. GuoJ. CaiM. YangJ. LiY. MengX. XuB. A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19).MedRxiv202010.1101/2020.02.14.20023028
    [Google Scholar]
  29. MengJ. TanZ. YuY. WangP. LiuS. TL-Med: A two-stage transfer learning recognition model for medical images of COVID-19.Biocybern Biomed Eng.202242384285510.1016/j.bbe.2022.04.005
    [Google Scholar]
  30. MajeedT. RashidR. AliD. AsaadA. Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays.Phy. Eng. Sci. Med.20204341289130310.1007/s13246‑020‑00934‑833025386
    [Google Scholar]
  31. GargT. GargM. MahelaOP GargA.R. Convolutional Neural Networks with Transfer Learning for Recognition of COVID-19: A Comparative Study of Different Approaches.AI202014
    [Google Scholar]
  32. RahamanM.M. LiC. YaoY. KulwaF. RahmanM.A. WangQ. QiS. KongF. ZhuX. ZhaoX. Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches.J. XRay Sci. Technol.202028582183910.3233/XST‑20071532773400
    [Google Scholar]
  33. SimonyanK. ZissermanA. Very Deep ConvNets for Large-Scale Image Recognition.arXiv:1409.15562014
    [Google Scholar]
  34. SalehinejadH. SankarS. BarfettJ. ColakE. ValaeeS. Recent advances in recurrent neural networks.arXiv:1801.010782017
    [Google Scholar]
  35. LiW. KiaghadiA. DawsonC. Exploring the best sequence LSTM modeling architecture for flood prediction.Neural Comput. Appl.202133115571558010.1007/s00521‑020‑05334‑3
    [Google Scholar]
  36. GrosseR. Lecture 15: Exploding and vanishing gradients.University of Toronto Computer Science2017
    [Google Scholar]
  37. SherstinskyA. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network.Physica D202040413230610.1016/j.physd.2019.132306
    [Google Scholar]
  38. KamalA.H. JishanM.A. MansoorN. The automated bangla caption generator based on deep learning.2020 International Conference on Decision Aid Sciences and Application (DASA)Sakheer202082282610.1109/DASA51403.2020.9317108
    [Google Scholar]
  39. Arias-GarzónD. Alzate-GrisalesJ.A. Orozco-AriasS. Arteaga-ArteagaH.B. Bravo-OrtizM.A. Mora-RubioA. Saborit-TorresJ.M. SerranoJ.Á.M. de la Iglesia VayáM. Cardona-MoralesO. Tabares-SotoR. COVID-19 detection in X-ray images using convolutional neural networks.Mach Learn Appl.20216100138
    [Google Scholar]
  40. HorryM.J. ChakrabortyS. PaulM. UlhaqA. PradhanB. SahaM. ShuklaN. Unsupervised Deep Learning.Artificial Intelligence for Sustainable Development: Theory, Practice and Future Applications.SpringerCham2020
    [Google Scholar]
  41. HamliliF.Z. BeladghamM. KhelifiM. BouidaA. Transfer learning with Resnet-50 for detecting COVID-19 in chest X-ray images.Indonesian J Electric Eng Comp Sci20222531458146810.11591/ijeecs.v25.i3.pp1458‑1468
    [Google Scholar]
  42. ElpeltagyM. SallamH. Automatic prediction of COVID− 19 from chest images using modified ResNet50.Multimedia Tools Appl202180172645126463
    [Google Scholar]
  43. IslamM.Z. IslamM.M. AsrafA. Automatic prediction of COVID− 19 from chest images using modified ResNet50.Multimed Tools Appl.202180172645126463
    [Google Scholar]
  44. AlbahliS. AyubN. ShirazM. Coronavirus disease (COVID-19) detection using X-ray images and enhanced DenseNet.Appl. Soft Comput.202111010764510.1016/j.asoc.2021.10764534191925
    [Google Scholar]
  45. MondalM.R.H. BharatiS. PodderP. CO-IRv2: Optimized InceptionResNetV2 for COVID-19 detection from chest CT images.PloS one20211610e0259179
    [Google Scholar]
  46. DebS.D. JhaR.K. JhaK. TripathiP.S. A multi model ensemble based deep convolution neural network structure for detection of COVID19.Biomed. Signal Process. Control20227110312610.1016/j.bspc.2021.10312634493940
    [Google Scholar]
  47. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks.Commun. ACM2017606849010.1145/3065386
    [Google Scholar]
  48. DeshwalD. SangwanP. KumarD. 2020A Structured Approach towards Robust Database Collection for Language Identification.2020 21st International Arab Conference on Information Technology (ACIT)Giza202010.1109/ACIT50332.2020.9299963
    [Google Scholar]
  49. DeshwalD. SangwanP. A Comprehensive Study of Deep Neural Networks for Unsupervised Deep Learning.Artificial Intelligence for Sustainable Development: Theory, Practice and Future Applications.ChamSpringer202110112610.1007/978‑3‑030‑51920‑9_7
    [Google Scholar]
  50. DeshwalD. SangwanP. DahiyaN. NehraN. DahiyaA. A comprehensive approach for performance evaluation of Indian language identification systems.J. Intell. Fuzzy Syst.20224355369538510.3233/JIFS‑210186
    [Google Scholar]
  51. ApostolopoulosI.D. MpesianaT.A. Covid-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks.Phy. Eng. Sci. Med.202043263564010.1007/s13246‑020‑00865‑432524445
    [Google Scholar]
  52. HemdanE.E.D. ShoumanM.A. KararM.E. COVIDX-Net: A framework of deep learning classifiers to diagnose COVID-19 in x-ray images. arXiv:2003.1105520201
    [Google Scholar]
  53. RenS. HeK. GirshickR. SunJ. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.Advances in Neural Information Processing Systems.MIT PressMassachusetts2016
    [Google Scholar]
  54. RedmonJ. DivvalaS. GirshickR. FarhadiA. You Only Look Once: Unified, Real-Time Object Detection.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Las Vegas201677978810.1109/CVPR.2016.91
    [Google Scholar]
  55. RedmonJ. FarhadiA. 2017YOLO9000: Better, Faster, Stronger.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)San Juan201765176525
    [Google Scholar]
  56. RedmonJ. FarhadiA. 2018YOLOv3: An Incremental Improvement.arXiv:1804.027672018
    [Google Scholar]
  57. BochkovskiyA. WangC.Y. LiaoH.Y.M. YOLOv4: Optimal Speed and Accuracy of Object Detection.arXiv:2004.109342020
    [Google Scholar]
/content/journals/cmim/10.2174/1573405620666230817092337
Loading
/content/journals/cmim/10.2174/1573405620666230817092337
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test