Advertisement

Implementation of 1D-Convolution Neural Network for Pneumonia Classification Based Chest X-Ray Image

  • Muhamad FathurahmanEmail author
  • Sri Cahya Fauzi
  • Sri Chusri Haryanti
  • Ummi Azizah Rahmawati
  • Elan Suherlan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 978)

Abstract

Pneumonia is an infectious disease that attacks the lungs, causing the air sacs in the lungs to become inflamed and swollen. Pneumonia is caused by fungi, bacteria, and viruses. Pneumonia can affect anyone, including children. The most successful type of method for analyzing images to date is the Convolutional Neural Network (CNN). The Convolutional Neural Network classification is implemented based on multiple extraction features. The purpose of this study is to evaluate the performance of ID-Convolutional to classify pneumonia with various CNN architectures to produce the best performance in accuracy and compare it with the other baseline methods that have been made. Experiments are carried out based on the number of hidden layers and configuration parameters. The parameters used are the epoch, kernel, strides, and pool size. The result shows that the proposed method achieves 94% inaccuracy and 0.93 in AUC. Besides, CNN has a competitive result compare to the other baseline methods.

Keywords

Convolutional neural network Chest X-Ray Pneumonia 

References

  1. 1.
    UNICEF, Pusat Pers | UNICEF Indonesia. UNICEF Indonesia, (2015). [Online]. Available: https://www.unicef.org/indonesia/id/pusat-pers. Accessed 30 Jun 2019
  2. 2.
    WHO, Pneumonia (2016). [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/pneumonia. Accessed 30 Jun 2019
  3. 3.
    Ri KK (2010) Pneumonia Balita. Bul Jendela Epidemiol 3:43Google Scholar
  4. 4.
    Fimela, Cara Pencegahan Penyakit Mematikan Pneumonia Pada Anak-Anak—Parenting Fimela.com, (2016). [Online]. Available: https://www.fimela.com/parenting/read/3765370/cara-pencegahan-penyakit-mematikan-pneumonia-pada-anak-anak. Accessed 19 Feb 2019
  5. 5.
    Rachmad A (2008) Pengolahan Citra Digital Menggunakan Teknik Filtering Adaptive Noise Removal Pada Gambar Bernoise | Aeri Rachmad—Academia.edu. [Online]. Available: https://www.academia.edu/27291316/Pengolahan_Citra_Digital_Menggunakan_Teknik_Filtering_Adaptive_Noise_Removal_Pada_Gambar_Bernoise. Accessed 25 Feb 2019
  6. 6.
    Krizhevsky A, Sutskever I, Hinton GE, ImageNet classification with deep convolutional neural networks, pp 1–9Google Scholar
  7. 7.
    Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. 86(11)Google Scholar
  8. 8.
    Sun M, Song Z, Jiang X, Pang Y (2016) Author’s accepted manuscript learning pooling for convolutional neural network. NeurocomputingGoogle Scholar
  9. 9.
    Abiyev RH, Ma’aitah MKS (2018) Deep convolutional neural networks for chest diseases detection. J Healthc Eng, 4168538, 2018Google Scholar
  10. 10.
    Bar Y, Diamant I, Wolf L, Lieberman S, Konen E, Greenspan H (2018) Chest pathology identification using deep feature selection with non-medical training. Comput Methods Biomech Biomed Eng Imaging Vis 6(3):259–263CrossRefGoogle Scholar
  11. 11.
    Islam MT, Aowal MA, Minhaz AT, Ashraf K (2017) Abnormality detection and localization in chest X-rays using deep convolutional neural networksGoogle Scholar
  12. 12.
    Pattar S, Pavithra R (2015) Detection and classification of lung disease—pneumonia and lung cancer in chest radiology using artificial neural network. Int J Sci Res Publ, 5(1):2250–3153Google Scholar
  13. 13.
    Norris M (2018) Convolutional neural networks in radiology CS230-Fall 2018 course projectGoogle Scholar
  14. 14.
    Saraiva A et al (2019) Classification of images of childhood pneumonia using convolutional neural networksGoogle Scholar
  15. 15.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  16. 16.
    Ferreira A, Giraldi G (2017) Convolutional Neural Network approaches to granite tiles classification. Expert Syst Appl 84:1–11CrossRefGoogle Scholar
  17. 17.
    Integrated Performance Primitives 2017 Developer Reference, “Histogram of Oriented Gradients (HOG) Descriptor.”Google Scholar
  18. 18.
    Mohanaiah P, Sathyanarayana P, Gurukumar L (2013) Image texture feature extract approach. Int J Sci Res Publ 3(5):1–5Google Scholar
  19. 19.
    Zhu W, Zeng N, Wang N (2010) sensitivity_specificity_accuracy_CI.pdf, pp 1–9 2010Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Muhamad Fathurahman
    • 1
    Email author
  • Sri Cahya Fauzi
    • 1
  • Sri Chusri Haryanti
    • 1
  • Ummi Azizah Rahmawati
    • 1
  • Elan Suherlan
    • 1
  1. 1.Teknik Informatika, Fakultas Teknologi Informasi, Universitas YARSIJakartaIndonesia

Personalised recommendations