Advertisement

Application of Convolutional Neural Network in Segmenting Brain Regions from MRI Data

  • Hafsa Moontari Ali
  • M. Shamim KaiserEmail author
  • Mufti MahmudEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11976)

Abstract

Extracting knowledge from digital images largely depends on how well the mining algorithms can focus on specific regions of the image. In multimodality image analysis, especially in multi-layer diagnostic images, identification of regions of interest is pivotal and this is mostly done through image segmentation. Reliable medical image analysis for error-free diagnosis requires efficient and accurate image segmentation mechanisms. With the advent of advanced machine learning methods, such as deep learning (DL), in intelligent diagnostics, the requirement of efficient and accurate image segmentation becomes crucial. Targeting the beginners, this paper starts with an overview of Convolutional Neural Network, the most widely used DL technique and its application to segment brain regions from Magnetic Resonance Imaging. It then provides a quantitative analysis of the reviewed techniques as well as a rich discussion on their performance. Towards the end, few open challenges are identified and promising future works related to medical image segmentation using DL are indicated.

Keywords

Machine learning Brain imaging Neuroimaging Segmentation Deep learning MRI 

References

  1. 1.
    Bao, S., Chung, A.C.: Multi-scale structured CNN with label consistency for brain MRI segmentation. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 6(1), 113–117 (2018) CrossRefGoogle Scholar
  2. 2.
    Birenbaum, A., Greenspan, H.: Longitudinal multiple sclerosis lesion segmentation using multi-view convolutional neural networks. In: Carneiro, G., et al. (eds.) LABELS/DLMIA - 2016. LNCS, vol. 10008, pp. 58–67. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46976-8_7CrossRefGoogle Scholar
  3. 3.
    de Brebisson, A., Montana, G.: Deep neural networks for anatomical brain segmentation. In: Proceedings of IEEE CVPR, pp. 20–28 (2015)Google Scholar
  4. 4.
    Brosch, T., et al.: Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. IEEE Trans. Med. Imaging 35(5), 1229–1239 (2016)CrossRefGoogle Scholar
  5. 5.
    Choi, H., Jin, K.H.: Fast and robust segmentation of the striatum using deep convolutional neural networks. J. Neurosci. Methods 274, 146–153 (2016)CrossRefGoogle Scholar
  6. 6.
    Dolz, J., et al.: HyperDense-Net: a hyper-densely connected CNN for multi-modal image segmentation. IEEE Trans. Med. Imaging 38(5), 1116–1126 (2019)CrossRefGoogle Scholar
  7. 7.
    Dolz, J., Ayed, I.B., Yuan, J., Desrosiers, C.: Isointense infant brain segmentation with a hyper-dense connected CNN. In: Proceedings of ISBI 2018, pp. 616–620 (2018)Google Scholar
  8. 8.
    Dolz, J., Desrosiers, C., Ayed, I.B.: 3D fully convolutional networks for subcortical segmentation in MRI: a large-scale study. NeuroImage 170, 456–470 (2017)CrossRefGoogle Scholar
  9. 9.
    Ghafoorian, M., et al.: Non-uniform patch sampling with deep CNNs for white matter hyperintensity segmentation. In: Proceedings of ISBI, pp. 1414–1417 (2016)Google Scholar
  10. 10.
    Ghafoorian, M., et al.: Location sensitive deep CNNs for segmentation of white matter hyperintensities. Sci. Rep. 7, 5110 (2017)CrossRefGoogle Scholar
  11. 11.
    Guerrero, R., et al.: White matter hyperintensity and stroke lesion segmentation and differentiation using CNNs. NeuroImage: Clin. 17, 918–934 (2018)CrossRefGoogle Scholar
  12. 12.
    Havaei, M., et al.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18–31 (2017)CrossRefGoogle Scholar
  13. 13.
    He, Z., Bao, S., Chung, A.: 3D deep affine-invariant shape learning for brain MR image segmentation. In: Stoyanov, D., et al. (eds.) DLMIA/ML-CDS - 2018. LNCS, vol. 11045, pp. 56–64. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00889-5_7CrossRefGoogle Scholar
  14. 14.
    Hoseini, F., Shahbahrami, A., Bayat, P.: An efficient implementation of deep convolutional neural networks for MRI segmentation. J. Digit. Imaging 31, 1–10 (2018)CrossRefGoogle Scholar
  15. 15.
    Hussain, S., Anwar, S.M., Majid, M.: Segmentation of glioma tumors in brain using deep convolutional neural network. Neurocomputing 282, 248–261 (2018)CrossRefGoogle Scholar
  16. 16.
    Kamnitsas, K., et al.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017)CrossRefGoogle Scholar
  17. 17.
    Kumar, S., et al.: InfiNet: fully convolutional networks for infant brain MRI segmentation. In: Proceedings of ISBI 2018, pp. 145–148 (2018)Google Scholar
  18. 18.
    Kushibar, K., et al.: Automated subcortical brain structure segmentation combining spatial and deep convolutional features. Med. Image Anal. 48, 177–186 (2018)CrossRefGoogle Scholar
  19. 19.
    Laukamp, K.R., et al.: Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI. Eur. Radiol. 29(1), 124–132 (2018)CrossRefGoogle Scholar
  20. 20.
    Le, T.H.N., Gummadi, R., Savvides, M.: Deep recurrent level set for segmenting brain tumors. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 646–653. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00931-1_74CrossRefGoogle Scholar
  21. 21.
    Li, X., et al.: 3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MRI. Med. Image Anal. 45, 41–54 (2018)CrossRefGoogle Scholar
  22. 22.
    Mahmud, M., Kaiser, M.S., Hussain, A., Vassanelli, S.: Applications of deep learning and reinforcement learning to biological data. IEEE Trans. Neural Netw. Learn Syst. 29(6), 2063–2079 (2018)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Miller, C.G., Krasnow, J., Schwartz, L.H.: Medical Imaging in Clinical Trials. Springer, London (2014).  https://doi.org/10.1007/978-1-84882-710-3CrossRefGoogle Scholar
  24. 24.
    Milletari, F., et al.: Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound. Comput. Vis. Image Underst. 164, 92–102 (2017)CrossRefGoogle Scholar
  25. 25.
    Moeskops, P., et al.: Automatic segmentation of mr brain images with a CNN. IEEE Trans. Med. Imaging 35(5), 1252–1261 (2016)CrossRefGoogle Scholar
  26. 26.
    Moeskops, P., et al.: Deep learning for multi-task medical image segmentation in multiple modalities. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 478–486. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_55CrossRefGoogle Scholar
  27. 27.
    Moeskops, P., Veta, M., Lafarge, M.W., Eppenhof, K.A.J., Pluim, J.P.W.: Adversarial training and dilated convolutions for brain MRI segmentation. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS - 2017. LNCS, vol. 10553, pp. 56–64. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67558-9_7CrossRefGoogle Scholar
  28. 28.
    Moeskops, P., et al.: Evaluation of a deep learning approach for the segmentation of brain tissues and WMH of presumed vascular origin in MRI. NeuroImage: Clin. 17, 251–262 (2018)CrossRefGoogle Scholar
  29. 29.
    Moeskops, P., Pluim, J.P.W.: Isointense infant brain MRI segmentation with a dilated convolutional neural network. CoRR abs/1708.02757 (2017)Google Scholar
  30. 30.
    Nguyen, D.M., et al.: 3D-brain segmentation using deep neural network and Gaussian mixture model. In: Proceedings of WACV 2017, pp. 815–824 (2017)Google Scholar
  31. 31.
    Nie, D., et al.: 3-D fully convolutional networks for multimodal isointense infant brain image segmentation. IEEE Trans. Cybern. 49(3), 1123–1136 (2019)CrossRefGoogle Scholar
  32. 32.
    Nie, D., Wang, L., Gao, Y., Sken, D.: FCNs for multi-modality isointense infant brain image segmentation. Proceedings of ISBI 2016, pp. 1342–1345 (2016)Google Scholar
  33. 33.
    Pereira, S., et al.: Brain tumor segmentation using CNNs in MRI images. IEEE Trans. Med. Imaging 35(5), 1240–1251 (2016)CrossRefGoogle Scholar
  34. 34.
    Rachmadi, M., et al.: Segmentation of WMHs using CNNs with global spatial information in routine clinical brain MRI with none or mild vascular pathology. Comput. Med. Imaging Graph. 66, 28–43 (2018)CrossRefGoogle Scholar
  35. 35.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  36. 36.
    Roy, S., et al.: Multiple sclerosis lesion segmentation from brain MRI via fully convolutional neural networks. arXiv preprint arXiv:1803.09172 (2018)
  37. 37.
    Shakeri, M., et al.: Sub-cortical brain structure segmentation using F-CNN’s. In: Proceedings of ISBI 2016, pp. 269–272. IEEE (2016)Google Scholar
  38. 38.
    Shen, G., et al.: Brain tumor segmentation using concurrent fully convolutional networks and conditional random fields. In: Proceedings of ICMIP 2018, pp. 24–30 (2018)Google Scholar
  39. 39.
    Valverde, S., et al.: Improving automated multiple sclerosis lesion segmentation with a cascaded 3D CNN approach. NeuroImage 155, 159–168 (2017)CrossRefGoogle Scholar
  40. 40.
    Wachinger, C., Reuter, M., Klein, T.: DeepNAT: deep CNN for segmenting neuroanatomy. NeuroImage 170, 434–445 (2018)CrossRefGoogle Scholar
  41. 41.
    Wang, Y., et al.: Automatic tumor segmentation with deep convolutional neural networks for radiotherapy applications. Neural Process. Lett. 48, 1–12 (2018)CrossRefGoogle Scholar
  42. 42.
    Xu, B., et al.: Orchestral fully convolutional networks for small lesion segmentation in brain MRI. In: Proceedings of ISBI 2018, pp. 889–892. IEEE (2018)Google Scholar
  43. 43.
    Yi, D., Zhou, M., Chen, Z., Gevaert, O.: 3-D convolutional neural networks for glioblastoma segmentation. CoRR abs/1611.04534 (2016)Google Scholar
  44. 44.
    Zeng, G., Zheng, G.: Multi-stream 3D FCN with MSDS for multi-modality isointense infant brain MRI segmentation. In: Proceedings of ISBI 2018, pp. 136–140 (2018)Google Scholar
  45. 45.
    Zhang, W., et al.: Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage 108, 214–224 (2015)CrossRefGoogle Scholar
  46. 46.
    Zhao, X., et al.: A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med. Image Anal. 43, 98–111 (2018)CrossRefGoogle Scholar
  47. 47.
    Zhou, C., Ding, C., Lu, Z., Wang, X., Tao, D.: One-pass multi-task convolutional neural networks for efficient brain tumor segmentation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 637–645. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00931-1_73CrossRefGoogle Scholar
  48. 48.
    Zhuge, Y., et al.: Brain tumor segmentation using holistically-nested neural networks in MRI images. Med. Phys. 44(10), 5234–5243 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringJahangirnagar UniversitySavarBangladesh
  2. 2.Institue of Information TechnologyJahangirnagar UniversitySavarBangladesh
  3. 3.Department of Computing and TechnologyNottingham Trent University, CliftonNottinghamUK

Personalised recommendations