Advertisement

Improving the Model Performance of Deep Convolutional Neural Network in MURA Dataset

  • Shubhajit PandaEmail author
  • Mahesh Jangid
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 141)

Abstract

Deep convolutional neural networks have recently become one of the most powerful and expressive learning models for image pattern recognition and classification problems. And its wide use in the medical field has gathered immense success and importance in current scenarios. In this work, we made use of the Deep Convolutional Neural Network (CNN) over a large set of data called MURA (Musculoskeletal Radiographs Abnormality) and tried to improve the model performance (in terms of maximizing the accuracy and minimizing the loss) through the use of six different deep learning optimizers as well as the use of dropout regularizers (to avoid overfitting of data). The network architecture was trained using these optimizers to obtain the best possible model parameters that can easily exceed the previous level of performance in the classification tasks of abnormality detection in the human muscoskeletal system based on radiographs. Our model achieved the highest training accuracy of 95.98% and highest valid accuracy of 93.70%, which is better than the one achieved in the previous work. Similarly, in terms of train loss and valid loss also the model achieved the lowest loss of 0.11 and 0.22 respectively which is lower than the loss obtained in the previous work.

Keywords

Deep convolution neural network MURA dataset Optimizers 

References

  1. 1.
    Artificial intelligence in medicine and imaging: Available labelled medical datasets. https://aimi.stanford.edu/available-labeled-medical-datasets. Accessed 2 Dec 2017
  2. 2.
    Kuo, C.C.-J.: Understanding convolutional neural networks with a mathematical model, Ming-Hsieh Department of Electrical Engineering University of Southern California, Los Angeles, CA 90089-2564, USA, 2 November 2016. arXiv:1609.04112v2 [cs.CV]
  3. 3.
    Rajpurkar, P., Irvin, J., Bagul, A., Ding, D., Duan, T., Mehta, H., Yang, B., Zhu, K., Laird, D., Ball, R.L., Langlotz, C., Shpanskaya, K., Lungren, M.P., Ng, A.Y.: MURA: large dataset for detecting abnormalities in human muscoskeletal radiographs, Department of CSE, Medicine, Radiology, Stanford University, 22 May 2018, pp. 1–10 (2018). arXiv:1712.06957v4 [Physics.med-ph] [6]
  4. 4.
    Wu, H., Gu, X. (Fudan University): Towards, dropout training in CNN (2014)Google Scholar
  5. 5.
    McHugh, M.L.: Interrater reliability – the Kappa statistic. (BioChemia Medica, Depertment of Nursing, California) Biochem Med (Zagreb) 22(3), 276–282 (2012). Accessed 15 Oct 2012Google Scholar
  6. 6.
    Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition, CVPR 2009 (2009)Google Scholar
  7. 7.
    Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks (2016). LNCS homepage. arXiv:1608.06993, http://www.springer.com/lncs. Accessed 5 Nov 2018
  8. 8.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection, HAL, HAL Id: inria-00548512, https://hal.inria.fr/inria-00548512. Accessed 20 Dec 2010
  9. 9.
    Huang, G., (Cornell University), Liu, Z., (Tsinghua University), Weinberger, K.Q. (Cornell University): Densely connected convolutional neural network. arXiv:1608.06993v5 [cs.CV]. Accessed 28 Jan 2018
  10. 10.
    Jangid, M., Srivastava, S.: Handwritten Devanagari character recognition using layer-wise training of deep convolutional neural networks and adaptive gradient methods. J. Imaging (2018). Accessed 13 Feb 2018Google Scholar
  11. 11.
    Lee, R.S., Gimenez, F., Hoogi, A., Miyake, K.K., Gorovoy, M., Rubin, D.L.: A curated mammography dataset for use in computer-aided detection and diagnosis research. www.nature.com/scientificdata. Accessed 19 Dec 2017
  12. 12.
  13. 13.
    Goodfellow, I., Bengio, Y., Courville, A.: A Book on Deep Learning. www.deeplearningbook.org
  14. 14.
    Zhou, B., Khosla, A., Lapedriza A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)Google Scholar
  15. 15.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  16. 16.
    Wilamowski, B.M., Yu, H.: Neural network learning without backpropagation. IEEE Trans. Neural Networks 21(11), 1793–1803 (2010)CrossRefGoogle Scholar
  17. 17.
    Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)Google Scholar
  18. 18.
    Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks (2016). arXiv:1608.06993 [7]
  19. 19.
    Nelsen, M.: Neural networks and deep learning (2015). http://neuralnetworksanddeeplearning.com/chapter2.html
  20. 20.
    Emereko, K., De Ponteves, H.: A course on DEEP LEARNING A-ZTM: hands-on artificial neural networks. https://www.udemy.com/deeplearning

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringManipal University JaipurJaipurIndia

Personalised recommendations