Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

The novel coronavirus pandemic has caused a global health crisis, placing immense strain on healthcare systems worldwide. Chest X-ray technology has emerged as a critical tool for the diagnosis and treatment of COVID-19. However, the manual interpretation of chest X-ray films has proven to be inefficient and time-consuming, necessitating the development of an automated classification system.

Objective

In response to the challenges posed by the COVID-19 pandemic, we aimed to develop a deep learning model that accurately classifies chest X-ray images, specifically focusing on lung regions, to enhance the efficiency and accuracy of COVID-19 and pneumonia diagnosis.

Methods

We have proposed a novel deep network called “FocusNet” for precise segmentation of lung regions in chest radiographs. This segmentation allows for the accurate extraction of lung contours from chest X-ray images, which are then input into the classification network, ResNet18. By training the model on these segmented lung datasets, we sought to improve the accuracy of classification.

Results

The performance of our proposed system was evaluated on three types of lung regions in normal individuals, COVID-19 patients, and those with pneumonia. The average accuracy of the segmentation model (FocusNet) in segmenting lung regions was found to be above 90%. After re-classification of the segmented lung images, the specificities and sensitivities for normal, COVID-19, and pneumonia were excellent, with values of 98.00%, 99.00%, 99.50%, and 98.50%, 100.00%, and 99.00%, respectively. ResNet18 achieved impressive area under the curve (AUC) values of 0.99, 1.00, and 0.99 for classifying normal, COVID-19, and pneumonia, respectively, on the segmented lung datasets. Moreover, the AUC values of the three groups increased by 0.02, 0.02, and 0.06, respectively, when compared to the direct classification of unsegmented original images. Overall, the accuracy of lung region classification after processing the datasets was 99.3%.

Conclusion

Our deep learning-based automated chest X-ray classification system, incorporating lung region segmentation using FocusNet and subsequent classification with ResNet18, has significantly improved the accuracy of diagnosing respiratory lung diseases, including COVID-19. The proposed approach has great potential to revolutionize the diagnosis of COVID-19 and other respiratory lung diseases, offering a valuable tool to support healthcare professionals during health crises.

© 2024 Ding et al.
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/cmir/10.2174/0115734056271185231121074341
2024-01-01
2025-06-25

  • From This Site

    /content/journals/cmir/10.2174/0115734056271185231121074341
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. LandryM.D. GeddesL. Park MosemanA. LeflerJ.P. RamanS.R. WijchenJ. Early reflection on the global impact of COVID19, and implications for physiotherapy.Physiotherapy2020107A1A310.1016/j.physio.2020.03.00332312528
     [Google Scholar]
  2. FangY. ZhangH. XieJ. LinM. YingL. PangP. JiW. Sensitivity of chest CT for COVID-19: Comparison to RT-PCR.Radiology20202962E115E11710.1148/radiol.202020043232073353
     [Google Scholar]
  3. NgM.Y. LeeE.Y.P. YangJ. YangF. LiX. WangH. LuiM.M. LoC.S.Y. LeungB. KhongP.L. HuiC.K.M. YuenK. KuoM.D. Imaging profile of the COVID-19 Infection: Radiologic findings and literature review.Radiol. Cardiothorac. Imaging202021e20003410.1148/ryct.202020003433778547
     [Google Scholar]
  4. AiT. YangZ. HouH. ZhanC. ChenC. LvW. TaoQ. SunZ. XiaL. Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases.Radiology20202962E32E4010.1148/radiol.202020064232101510
     [Google Scholar]
  5. ChenZ. ZhouQ. KhanA. JillJ. XiongR. LiuX. New trends of deep learning in clinical cardiology.Curr. Bioinform.202116795496210.2174/1574893615999200719234517
     [Google Scholar]
  6. RousanL.A. ElobeidE. KarrarM. KhaderY. Chest x-ray findings and temporal lung changes in patients with COVID-19 pneumonia.BMC Pulm. Med.202020124510.1186/s12890‑020‑01286‑532933519
     [Google Scholar]
  7. BrognaB. BignardiE. BrognaC. VolpeM. LombardiG. RosaA. GagliardiG. CapassoP.F.M. GravinoE. MaioF. PaneF. PicarielloV. BuonoM. ColucciL. MustoL.A. A pictorial review of the role of imaging in the detection, management, histopathological correlations, and complications of COVID-19 pneumonia.Diagnostics (Basel)202111343710.3390/diagnostics1103043733806423
     [Google Scholar]
  8. RajinikanthV DeyN RajA HassanienAE SantoshKC SriM Harmony-search and otsu based system for coronavirus disease (COVID-19) detection using lung CT scan images.arXiv2020
     [Google Scholar]
  9. ShiF. WangJ. ShiJ. WuZ. WangQ. TangZ. HeK. ShiY. ShenD. Review of artificial intelligence techniques in imaging data acquisition, segmentation, and diagnosis for COVID-19.IEEE Rev. Biomed. Eng.20211441510.1109/RBME.2020.298797532305937
     [Google Scholar]
  10. DandilE. CakirogluM. EksiZ. OzkanM. KurtO.K. CananA. Artificial neural network-based classification system for lung nodules on computed tomography scans. 6th international conference on soft computing and pattern recognition (SoCPaR). Tunis, TUNISIA2014382386
     [Google Scholar]
  11. KuruvillaJ. GunavathiK. Lung cancer classification using neural networks for CT images.Comput. Methods Programs Biomed.2014113120220910.1016/j.cmpb.2013.10.01124199657
     [Google Scholar]
  12. ManikandanT. BharathiN. Lung cancer detection using fuzzy auto-seed cluster means morphological segmentation and SVM classifier.J. Med. Syst.201640718110.1007/s10916‑016‑0539‑927299354
     [Google Scholar]
  13. AnthimopoulosM. ChristodoulidisS. EbnerL. ChristeA. MougiakakouS. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network.IEEE Trans. Med. Imaging20163551207121610.1109/TMI.2016.253586526955021
     [Google Scholar]
  14. SunW. ZhengB. QianW. Computer aided lung cancer diagnosis with deep learning algorithms.Conference on Medical Imaging - Computer-Aided DiagnosisSan Diego, CA2016
     [Google Scholar]
  15. ZhouQ. ZhuW. LiF. YuanM. ZhengL. LiuX. Transfer learning of the resnet-18 and densenet-121 model used to diagnose intracranial hemorrhage in CT scanning.Curr. Pharm. Des.202228428729510.2174/138161282766621121314335734961458
     [Google Scholar]
  16. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks.Commun. ACM2017606849010.1145/3065386
     [Google Scholar]
  17. LeCunY. BengioY. HintonG. Deep learning.Nature2015521755343644410.1038/nature1453926017442
     [Google Scholar]
  18. TaloM. YildirimO. BalogluU.B. AydinG. AcharyaU.R. Convolutional neural networks for multi-class brain disease detection using MRI images.Comput. Med. Imaging Graph.20197810167310.1016/j.compmedimag.2019.10167331635910
     [Google Scholar]
  19. CelikY. TaloM. YildirimO. KarabatakM. AcharyaU.R. Automated invasive ductal carcinoma detection based using deep transfer learning with whole-slide images.Pattern Recognit. Lett.202013323223910.1016/j.patrec.2020.03.011
     [Google Scholar]
  20. Cruz-RoaA. BasavanhallyA. GonzalezF. GilmoreH. FeldmanM. GanesanS. Automatic detection of invasive ductal carcinoma in whole slide images with Convolutional Neural Networks. 2nd Conference on Medical Imaging - Digital Pathology.San Diego, CA2014
     [Google Scholar]
  21. RajpurkarP IrvinJ ZhuK YangB MehtaH DuanT CheXNet: Radiologist-level pneumonia detection on chest x-rays with deep learning. 2017
     [Google Scholar]
  22. GaálG MagaB LukácsA. Attention U-net based adversarial architectures for chest X-ray lung segmentation. 2020
     [Google Scholar]
  23. SouzaJ.C. Bandeira DinizJ.O. FerreiraJ.L. França da SilvaG.L. Corrêa SilvaA. de PaivaA.C. An automatic method for lung segmentation and reconstruction in chest X-ray using deep neural networks.Comput. Methods Programs Biomed.201917728529610.1016/j.cmpb.2019.06.00531319957
     [Google Scholar]
  24. GeC ZhangL XieL KongR ZhangH ChangS. COVID-19 imaging-based ai research - A literature review.Curr. Med. Imaging202218496508
     [Google Scholar]
  25. BrasG. FernandesV. de PaivaA.C. BrazG.Junior RiveroL. Transfer learning method evaluation for automatic pediatric chest x-ray image segmentation. 27th International Conference on Systems, Signals and Image Processing (IWSSIP).Electr Network2020128133
     [Google Scholar]
  26. HorvathA. HorvathG. Segmentation of Chest X-ray radiographs, a new robust solution.5th European Conference of the International Federation for Medical and Biological Engineering. Budapest, HUNGARY2011655658
     [Google Scholar]
  27. GozesO. GreenspanH. Bone structures extraction and enhancement in chest radiographs via cnn trained on synthetic data. IEEE 17th International Symposium on Biomedical Imaging (ISBI).Iowa, IA2020858861
     [Google Scholar]
  28. GozesO. GreenspanH. Lung structures enhancement in chest radiographs via CT based FCNN training.3rd International Workshop on Reconstruction and Analysis of Moving Body Organs (RAMBO) / 4th International Workshop on Breast Image Analysis (BIA) / 1st International Workshop on Thoracic Image Analysis (TIA). Granada, SPAIN2018147158
     [Google Scholar]
  29. AnnangiP. ThiruvenkadamS. RajaA. XuH. SunX. MaoL. A region based active contour method for x-ray lung segmentation using prior shape and low level features.7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Rotterdam, NETHERLANDS2010892895
     [Google Scholar]
  30. UrinbayevK. OrazbekY. NurambekY. MirzakhmetovA. VarolH.A. End-to-end deep diagnosis of X-ray images. 42nd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC). Montreal, Canada202021822185
     [Google Scholar]
  31. MonowarK.F. HasanM.A.M. ShinJ. Lung opacity classification with convolutional neural networks using chest X-rays. 11th International Conference on Electrical and Computer Engineering (ICECE). Buet, Electr Network2020169172
     [Google Scholar]
  32. AguN.N. WuJ.T. ChaoH. LourentzouI. SharmaA. MoradiM. AnaXNet: Anatomy aware multi-label finding classification in chest X-ray.International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). Electr Network2021804813
     [Google Scholar]
  33. BhagatV. BhaumikS. Data augmentation using generative adversarial networks for pneumonia classification in chest Xrays.2019 Fifth International Conference on Image Information Processing (ICIIP)201910.1109/ICIIP47207.2019.8985892
     [Google Scholar]
  34. PS.A.B. AnnavarapuC.S.R. Deep learning-based improved snapshot ensemble technique for COVID-19 chest X-ray classification.Appl. Intell.20215153104312010.1007/s10489‑021‑02199‑434764590
     [Google Scholar]
  35. ZhouZ QiL YangX NiD ShiY. Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization.2021
     [Google Scholar]
  36. LiuY. SheG. ChenS. Magnetic resonance image diagnosis of femoral head necrosis based on ResNet18 network.Comput. Methods Programs Biomed.202120810625410.1016/j.cmpb.2021.10625434260970
     [Google Scholar]
  37. ZhengL. WangH. MeiL. ChenQ. ZhangY. ZhangH. Artificial intelligence in digital cariology: A new tool for the diagnosis of deep caries and pulpitis using convolutional neural networks.Ann. Transl. Med.20219976310.21037/atm‑21‑11934268376
     [Google Scholar]
  38. PetrovD. MarshallN. VancoillieL. CockmartinL. BosmansH. Anthropomorphic ResNet18 for multi-vendor DBT image quality evaluation.Conference on Medical Imaging - Image Perception, Observer Performance, and Technology Assessment, Medical Imaging.Houston, TX202010.1117/12.2549000
     [Google Scholar]
  39. 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]
  40. RahmanT. KhandakarA. QiblaweyY. TahirA. KiranyazS. Abul KashemS.B. IslamM.T. Al MaadeedS. ZughaierS.M. KhanM.S. ChowdhuryM.E.H. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images.Comput. Biol. Med.202113210431910.1016/j.compbiomed.2021.10431933799220
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056271185231121074341
Loading
A Novel Approach to the Technique of Lung Region Segmentation Based on a Deep Learning Model to Diagnose COVID-19 X-ray Images
Curr. Med. Imaging 20, e15734056271185 (2024); https://doi.org/10.2174/0115734056271185231121074341
/content/journals/cmir/10.2174/0115734056271185231121074341
/content/journals/cmir/10.2174/0115734056271185231121074341
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): COVID-19; Deep learning; FocusNet; Lung classification; Lung segmentation; X-ray

Most Cited Most Cited RSS feed

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