Skip to main content

Advertisement

Springer Nature Link
Log in

Effective Utilization of Multiple Convolutional Neural Networks for Chest X-Ray Classification

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Out of the numerous types of Medical Imaging modalities available, radiography stands out a bit more than others due to its capabilities of diagnosing diseases and conditions, including life-threatening conditions. Its affordability is another main reason for its prevalence. Chest Radiography holds even higher importance, as it focuses a critical area of the human body. However, interpreting a Chest Radiography image can be challenging and usually done by an experienced Radiologist for accurate results. There are two main issues related to this. One is that in some countries, experienced Radiologists are scarce. The other issue is that the inevitability of human errors in diagnoses. Researchers attempt to use Artificial Intelligence to address these two issues. Most of the existing work incorporates Convolutional Neural Networks for this purpose. This paper presents a novel way of parallelizing multiple architectures of Convolutional Neural Networks focusing on Chest X-ray classification. The paper further presents a comprehensive evaluation of the existing architectures with the parallelized results of them using our method. We used four large-scale datasets, including a non-medical one, for the evaluation of our models. We managed to achieve better accuracy for 9 out 13 and 11 out of 14 labels on our two main evaluation datasets. The paper concludes by presenting the limitations and future improvements possible for the system.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availability

All the material related to the developed system is available via below link; https://github.com/SuienS/parallelxnet-cxr-classifier.

Code availability

The code for the developed system is available via below link; https://github.com/SuienS/parallelxnet-cxr-classifier.

References

  1. UNICEF, ‘Pneumonia in Children’, UNICEF DATA, 2019. https://data.unicef.org/topic/child-health/pneumonia/ Accessed 9 Jan 2020

  2. Wakai A. ‘Spontaneous pneumothorax’. 2008; 11

  3. Porpodis K et al. ‘Pneumothorax and asthma’. J Thorac Dis. 2014; 6, 1, [Online]. Available: http://jtd.amegroups.com/article/view/2173

  4. Association of American Medical Colleges, ‘The Complexities of Physician Supply and Demand: Projections From 2018 to 2033’. Jun. 2020. [Online]. Available: https://www.aamc.org/media/45976/download?attachment

  5. Royal College of Radiologists, ‘Clinical Radiology UK. Workforce Census Report 2018’. 2019. [Online]. Available: https://www.rcr.ac.uk/system/files/publication/field_publication_files/clinical-radiology-uk-workforce-census-report-2018.pdf

  6. Harvard Medical School et al. Imaging in the land of 1000 hills: rwanda radiology country report. J Glob Radiol. 2015; 1, 1, https://doi.org/10.7191/jgr.2015.1004

  7. UMass Memorial Healthcare et al. Diagnostic radiology in liberia: a country report. J Glob Radiol. 2015; 1, 2, https://doi.org/10.7191/jgr.2015.1020

  8. Rosenkrantz AB, Hughes DR, Duszak R. The US radiologist workforce: an analysis of temporal and geographic variation by using large national datasets. Radiology. 2016;279(1):175–84. https://doi.org/10.1148/radiol.2015150921.

    Article  Google Scholar 

  9. Rimmer A. Radiologist shortage leaves patient care at risk, warns royal college. BMJ. 2017. https://doi.org/10.1136/bmj.j4683.

    Article  Google Scholar 

  10. Lodwick GS, Keats TE, Dorst JP. The coding of roentgen images for computer analysis as applied to lung cancer. Radiology. 1963;81(2):185–200. https://doi.org/10.1148/81.2.185.

    Article  Google Scholar 

  11. Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases, 2017, 20

  12. Irvin J et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison, ArXiv190107031 Cs Eess, 2019, Accessed: 24 Jul 2020. [Online]. Available: http://arxiv.org/abs/1901.07031

  13. Johnson AEW et al. MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs’, ArXiv190107042 Cs Eess, 2019, Accessed: 24 Jul 2020. [Online]. Available: http://arxiv.org/abs/1901.07042

  14. Silva RRS, Fernando P. An extensive survey of machine learning based approaches on automated pathology detection in chest X-rays’, 2021, 9

  15. Setio AAA, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge. Med Image Anal. 2017;42:1–13. https://doi.org/10.1016/j.media.2017.06.015.

    Article  Google Scholar 

  16. Gulshan V, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402. https://doi.org/10.1001/jama.2016.17216.

    Article  Google Scholar 

  17. Chen C, Kavuri VC, Wang X, Li R, Liu H, Huang J. Multi-frequency diffuse optical tomography for cancer detection, in 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), Brooklyn, NY, USA, 2015, pp. 67–70. https://doi.org/10.1109/ISBI.2015.7163818.

  18. Wynants L et al (2020) Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ. https://doi.org/10.1136/bmj.m1328.

    Article  Google Scholar 

  19. Jamshidi M, et al. Artificial Intelligence and COVID-19: deep learning approaches for diagnosis and treatment. IEEE Access. 2020;8:109581–95. https://doi.org/10.1109/ACCESS.2020.3001973.

    Article  Google Scholar 

  20. Kobayashi T. Effect of a computer-aided diagnosis scheme on radiologists’ performance in detection of lung nodules on radiographs, 1996, 6

  21. Wilcox JR. The written radiology report, 2006, 4

  22. Leaman R, Khare R, Lu Z. Challenges in clinical natural language processing for automated disorder normalization. J Biomed Inform. 2015;57:28–37. https://doi.org/10.1016/j.jbi.2015.07.010.

    Article  Google Scholar 

  23. Aronson AR, Lang F-M. An overview of metamap: historical perspective and recent advances. J Am Med Inform Assoc. 2010;17(3):229–36. https://doi.org/10.1136/jamia.2009.002733.

    Article  Google Scholar 

  24. Peng Y. NegBio: a high-performance tool for negation and uncertainty detection in radiology reports. 2017, 9

  25. Çallı E, Murphy K, Sogancioglu E, van Ginneken B. FRODO: free rejection of out-of-distribution samples: application to chest x-ray analysis’, ArXiv190701253 Cs Eess Stat, 2019, Accessed: 08 Aug 2020. [Online]. Available: http://arxiv.org/abs/1907.01253

  26. Cootes TF, Taylor CJ, Cooper DH, Graham J. Active shape models-their training and application. Comput Vis Image Underst. 1995;61(1):38–59. https://doi.org/10.1006/cviu.1995.1004.

    Article  Google Scholar 

  27. Wen H, Qi W, Shuang L. Medical X-ray image enhancement based on wavelet domain homomorphic filtering and CLAHE, 2016, 6

  28. Dai W et al. SCAN: structure correcting adversarial network for organ segmentation in chest X-rays, ArXiv170308770 Cs, 2017, Accessed: 02 Aug 2020. [Online]. Available: http://arxiv.org/abs/1703.08770

  29. Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks, ArXiv160806993 Cs, 2018, Accessed: 06 Aug 2020. [Online]. Available: http://arxiv.org/abs/1608.06993

  30. He K, Zhang X, Ren S, Sun J. Identity Mappings in Deep Residual Networks, ArXiv160305027 Cs, 2016, Accessed: 29 Nov 2020. [Online]. Available: http://arxiv.org/abs/1603.05027

  31. Liu H, Wang L, Nan Y, Jin F, Wang Q, Pu J. SDFN: segmentation-based deep fusion network for thoracic disease classification in chest X-ray images. Comput Med Imaging Graph. 2019;75:66–73. https://doi.org/10.1016/j.compmedimag.2019.05.005.

    Article  Google Scholar 

  32. Rubin J, Sanghavi D, Zhao C, Lee K, Qadir A, Xu-Wilson M. Large scale automated reading of frontal and lateral chest X-Rays using dual convolutional neural networks, ArXiv180407839 Cs Stat, 2018, Accessed: 03 Aug 2020. [Online]. Available: http://arxiv.org/abs/1804.07839

  33. Yan C, Yao J, Li R, Xu Z, Huang J. Weakly supervised deep learning for thoracic disease classification and localization on chest X-rays. Proc 2018 ACM Int Conf Bioinforma Comput Biol Health Inform. 2018. https://doi.org/10.1145/3233547.3233573.

    Article  Google Scholar 

  34. Hu J, Shen L, Albanie S, Sun G, Wu E. Squeeze-and-Excitation Networks, ArXiv170901507 Cs, 2019, Accessed: 08 Aug 2020. [Online]. Available: http://arxiv.org/abs/1709.01507

  35. Rajpurkar P et al. CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning, ArXiv171105225 Cs Stat, 2017, Accessed: 05 Aug 2020. [Online]. Available: http://arxiv.org/abs/1711.05225

  36. Guan Q, Huang Y, Zhong Z, Zheng Z, Zheng L, Yang Y. Diagnose like a radiologist: attention guided convolutional neural network for thorax disease classification, ArXiv180109927 Cs, 2018, Accessed: 24 Jul 2020. [Online]. Available: http://arxiv.org/abs/1801.09927

  37. Pham HH, Le TT, Tran DQ, Ngo DT, Nguyen HQ. Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels, ArXiv191106475 Cs Eess, 2020, Accessed: 03 Aug 2020. [Online]. Available: http://arxiv.org/abs/1911.06475

  38. CheXpert: a large chest x-ray dataset and competition, CheXpert: A Large Chest X-Ray Dataset And Competition. https://stanfordmlgroup.github.io/competitions/chexpert/

  39. ‘LungLifeAI’, LungLifeAI, 2019. https://www.lunglifeai.com/

  40. ‘Qure.ai’, Qure.ai—Artificial Intelligence for Radiology, 2020. https://qure.ai/

  41. ‘Oxipit’, Oxipit—The first AI chest X-Ray radiology suite for healthy patient reports, 2020. https://oxipit.ai/

  42. Putha P et al (2020) Can artificial intelligence reliably report chest X-rays?: Radiologist validation of an algorithm trained on 2.3 million X-rays, ArXiv180707455 Cs, 2019, Accessed: 18 Aug 2020. [Online]. Available: http://arxiv.org/abs/1807.07455

  43. Matthews BW. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta BBA-Protein Struct. 1975;405(2):442–51. https://doi.org/10.1016/0005-2795(75)90109-9.

    Article  Google Scholar 

Download references

Acknowledgements

We thank N F (MBBS, DFM), HB (MBBS, MD) and PDeS (MBBS, MSc), for their invaluable comments and knowledge contributions throughout this research. A special thanks should go to the Kaggle Notebooks, without which this research would not be possible. A huge appreciation should also go to the creators of the datasets, who has done immense work and released it freely on request to the research community.

Funding

This is a self-funded work by the authors.

Author information

Authors and Affiliations

  1. University of Westminster, London, UK

    Ravidu Suien Rammuni Silva

  2. Informatics Institute of Technology, Colombo, Sri Lanka

    Pumudu Fernando

Authors
  1. Ravidu Suien Rammuni Silva
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Pumudu Fernando
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Ravidu Suien Rammuni Silva.

Ethics declarations

Conflict of interest

Authors declare no conflicts of Interests.

Ethical approval

The study was carried out under the strict supervision of Informatics Institute of Technology, Sri Lanka and University of Westminster, UK. Since, no direct human involvement was observed in the study, no special Ethical approval was required.

Consent to participate

Informed consent was obtained from all individual participants included in the study including Medical Doctors and Medical Students who participated in the Survey Study relating to this research.

Consent for publication

Informed consent for publishing the results was obtained from all individual participants included in the study including Medical Doctors and Medical Students who participated in the Survey Study relating to this research.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Part of this work has been submitted as a partial requirement for the degree BSc. (Hons.) in Computer Science at the University of Westminster, UK (in collaboration with Informatics Institute of Technology, Sri Lanka).

Appendix

Appendix

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rammuni Silva, R.S., Fernando, P. Effective Utilization of Multiple Convolutional Neural Networks for Chest X-Ray Classification. SN COMPUT. SCI. 3, 492 (2022). https://doi.org/10.1007/s42979-022-01390-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01390-9

Keywords