Advertisement

Automatic Identification of Intracranial Hemorrhage on CT/MRI Image Using Meta-Architectures Improved from Region-Based CNN

  • Thi-Hoang-Yen LeEmail author
  • Anh-Cang Phan
  • Hung-Phi Cao
  • Thuong-Cang Phan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 991)

Abstract

Machine learning algorithms are suggested for detecting and classifying hemorrhage regions on head CT/MRI images with high accuracy. However, most of these algorithms are not interested in the valuable characteristic of CT/MRI images, especially Hounsfield Unit values. Besides, they also only detect and classify one of types of the intracranial hemorrhage on each image. In this paper, we propose a new approach for brain hemorrhage identification using object detection algorithms like Faster R-CNN and R-FCN. The proposed approach can detect many regions of the brain hemorrhage on a CT image. The results show that the R-FCN algorithm gives better results than the Faster R-CNN algorithm on time and accuracy of identification.

Keywords

Intracranial hemorrhage Region-based CNN Meta-architectures Hounsfield unit 

References

  1. 1.
    WHO: The top 10 causes of death. http://www.who.int/en/news-room/fact-sheets/detail/the-top-10-causes-of-death. Last accessed 19 Nov 2018
  2. 2.
    Holmes, E.J., Misra, R.R.: Interpretation of Emergency Head CT: A Practical Handbook, 2nd edn. Cambridge University Press, United Kingdom (2017)CrossRefGoogle Scholar
  3. 3.
    Pham, N.H., Le, V.P.: CT in Head Injuries, 1st edn. Medical Publishing House, Vietnam (2011)Google Scholar
  4. 4.
    Ly, N.L., Dong, V.H.: Traumatic Brain Injuries, 1st edn. Medical Publishing House, Vietnam (2013)Google Scholar
  5. 5.
    Fatima, Sridevi, M., Saba, N., Kauser, A.: Diagnosis and classification of brain hemorrhage using CAD system. In: Proceeding of NCRIET-2015 and Indian J. Sci. Res. 12(1), 121–125 (2015) (Indian)Google Scholar
  6. 6.
    Arbabshirani, M.R., Fornwalt B.K., Mongelluzzo, G.J., Suever, J.D., Geise, B.D., Patel, A.A., Moore, G.J.: Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. NPJ Digit. Med. 1(9) (2018)Google Scholar
  7. 7.
    Mahmoud, A-A., Duaa, A., Khaldun Al-D., Inad, A.: Automatic detection and classification of brain hemorrhages. WSEAS Trans. Comput. 10(12), 395–405 (2013)Google Scholar
  8. 8.
    Geenspan, H., van Ginneken, B., Summers, R.M.: Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans. Med. Imaging 35(5), 1153–1159 (2016)CrossRefGoogle Scholar
  9. 9.
    Bernal, J., Kushibar, K., Asfaw, D.S., Valverde, S., Oliver, A., Martí, R.: Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review. Artif. Intell. Med. (2018)Google Scholar
  10. 10.
    Rezaei, M., Yang, H., Meinel, C.: Brain abnormality detection by deep convolutional neural network (2016). arXiv preprint arXiv:1708.05206v1
  11. 11.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6) (2015)CrossRefGoogle Scholar
  12. 12.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379–387. Curran Associates Inc (2016)Google Scholar
  13. 13.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (2014)Google Scholar
  14. 14.
    Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision. IEEE. Santiago, Chile (2015).  https://doi.org/10.1109/ICCV.2015.169
  15. 15.
    Johnson, J., Karpathy, A.: The notes accompany the Standford CS class CS231n: convolutional neural networks for visual recognition (tranfer learning). http://cs231n.github.io/transfer-learning/. Last accessed 28 Dec 2018
  16. 16.
    Brownlee, J.: A gentle introduction to transfer learning for deep learning. https://machinelearningmastery.com/transfer-learning-for-deep-learning/. Last accessed 28 Dec 2018
  17. 17.
    NEMA’s DICOM Homepage. http://www.dicomstandard.org/. Last accessed 31 Dec 2018
  18. 18.
    Hounsfield units-scale of HU, CT numbers. http://radclass.mudr.org/content/hounsfield-units-scale-hu-ct-numbers. Last accessed 31 Dec 2018
  19. 19.
    Phan, A.-C., Phan, T.-C, Vo, V.-Q., Le, T.-H.-Y.: Automatic detection and classification of brain hemorrhage on CT/MRI images. In: 2017 National Conference. Science and Technics Publishing House, Quy Nhon, Vietnam (2017)Google Scholar
  20. 20.
    Converting CT data to Hounsfield Unit. https://www.idlcoyote.com/fileio_tips/hounsfield.html. Last accessed 31 Dec 2018
  21. 21.
    LabelImg. https://github.com/tzutalin/labelImg. Last accessed 01 Jan 2019
  22. 22.
    Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., Murphy, K.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR 2017Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Thi-Hoang-Yen Le
    • 1
    Email author
  • Anh-Cang Phan
    • 1
  • Hung-Phi Cao
    • 1
  • Thuong-Cang Phan
    • 2
  1. 1.Vinh Long University of Technology EducationVinh LongVietnam
  2. 2.Can Tho UniversityCan ThoVietnam

Personalised recommendations