Journal of Digital Imaging

, Volume 31, Issue 5, pp 738–747 | Cite as

An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation

  • Farnaz Hoseini
  • Asadollah ShahbahramiEmail author
  • Peyman Bayat


Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.


Deep convolutional neural networks Image segmentation Deep learning MRI Medical image MRI segmentation 


  1. 1.
    Russ JC, Matey JR, Mallinckrodt AJ, McKay S: The image processing handbook. Computers in Physics 8(2):177–178, 1994CrossRefGoogle Scholar
  2. 2.
    Prakash RM, Kumari RSS: Spatial fuzzy C means and expectation maximization algorithms with bias correction for segmentation of MR brain images. Journal of medical systems 41(1):15, 2017CrossRefGoogle Scholar
  3. 3.
    Raghupathi W, Raghupathi V: Big data analytics in healthcare: promise and potential. Health information science and systems 2(1):3–13, 2014CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Steele JR, Jones AK, Clarke RK, Giordano SH, Shoemaker S: Oncology patient perceptions of the use of ionizing radiation in diagnostic imaging. Journal of the American College of Radiology 13(7):768–774, 2016CrossRefPubMedGoogle Scholar
  5. 5.
    Greenspan H, van Ginneken B, Summers RM: Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Transactions on Medical Imaging 35(5):1153–1159, 2016CrossRefGoogle Scholar
  6. 6.
    Camaiti M, Bortolotti V, Fantazzini P: Stone porosity, wettability changes and other features detected by MRI and NMR relaxometry: a more than 15year study. Magnetic Resonance in Chemistry 53(1):34–47, 2015CrossRefPubMedGoogle Scholar
  7. 7.
    Deliolanis NC, Ale A, Morscher S, Burton NC, Schaefer K, Radrich K, … Ntziachristos V: Deep-tissue reporter-gene imaging with fluorescence and optoacoustic tomography: a performance overview. Mol Imaging Biol 16(5): 652–660, 2014CrossRefPubMedGoogle Scholar
  8. 8.
    Fan X, Khaki L, Zhu TS, Soules ME, Talsma CE, Gul N, … Nikkhah G: NOTCH pathway blockade depletes CD133-positive glioblastoma cells and inhibits growth of tumor neurospheres and xenografts. Stem Cells 28(1): 5–16, 2010Google Scholar
  9. 9.
    Sotiras A, Davatzikos C, Paragios N: Deformable medical image registration: a survey. IEEE transactions on medical imaging 32(7):1153–1190, 2013CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    Prajapati SJ, Jadhav KR: Brain tumor detection by various image segmentation techniques with introduction to non negative matrix factorization. Brain 4(3):600–603, 2015Google Scholar
  11. 11.
    Zhang J, Jiang W, Wang R, Wang L: Brain MR image segmentation with spatial constrained k-mean algorithm and dual-tree complex wavelet transform. Journal of medical systems 39(9):93, 2014CrossRefGoogle Scholar
  12. 12.
    Kalchbrenner N, Grefenstette E, Blunsom P: A convolutional neural network for modelling sentences. 52nd Annual Meeting of the Association for Computational Linguistics, 2014, pp 655–665.Google Scholar
  13. 13.
    Jin J, Gokhale V, Dundar A, Krishnamurthy B, Martini B, Culurciello E: An efficient implementation of deep convolutional neural networks on a mobile coprocessor. IEEE 57th International Symposium on Circuits and Systems, 2014, pp 133–136Google Scholar
  14. 14.
    Jin J, Dundar A, Bates J, Farabet C, Culurciello E: Tracking with deep neural networks. IEEE 47th Annual Conference on Information Sciences and Systems, 2013, pp 1–5Google Scholar
  15. 15.
    Wells WM, Grimson WEL, Kikinis R, Jolesz FA: Adaptive segmentation of MRI data. IEEE transactions on medical imaging 15(4):429–442, 1996CrossRefPubMedGoogle Scholar
  16. 16.
    Gondara L: Medical image denoising using convolutional denoising autoencoders. 16th International Conference on Data Mining Workshops (ICDMW), 2016, pp. 241–246.Google Scholar
  17. 17.
    Rekeczky C, Tahy Á, Végh Z, Roska T: CNNbased spatiotemporal nonlinear filtering and endocardial boundary detection in echocardiography. International Journal of Circuit Theory and Applications 27(1):171–207, 1999CrossRefGoogle Scholar
  18. 18.
    Zikic D, Ioannou Y, Brown M, Criminisi A: Segmentation of brain tumor tissues with convolutional neural networks. MICCAI workshop on Multimodal Brain Tumor Segmentation Challenge (BRATS) , 2014, pp 36–39Google Scholar
  19. 19.
    Wachinger C, Reuter M, Klein T: DeepNAT: deep convolutional neural network for segmenting neuroanatomy. NeuroImage, preprint arXiv:1702–08192, 2017Google Scholar
  20. 20.
    Pinheiro P, Collobert R: Recurrent convolutional neural networks for scene labeling. In: International Conference on Machine Learning, 2014, pp 82–90.Google Scholar
  21. 21.
    Shelhamer E, Long J, Darrell T: Fully convolutional networks for semantic segmentation. IEEE transactions on pattern analysis and machine intelligence 39(4):640–651, 2017CrossRefPubMedGoogle Scholar
  22. 22.
    Zhao X, Wu Y, Song G, Li Z, Zhang Y, Fan Y: A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Medical image analysis 43:98–111, 2018CrossRefPubMedGoogle Scholar
  23. 23.
    Milletari F, Ahmadi SA, Kroll C, Plate A, Rozanski V, Maiostre J, … Navab N: Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound. Comput Vis Image Underst, 2017Google Scholar
  24. 24.
    Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, … Larochelle H:Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31, 2017CrossRefPubMedGoogle Scholar
  25. 25.
    Havaei M, Guizard N, Larochelle H, Jodoin PM: Deep learning trends for focal brain pathology segmentation in MRI. Machine Learning for Health Informatics Springer International Publishing, 2016, pp 125–148Google Scholar
  26. 26.
    Pereira S, Pinto A, Alves V, Silva CA: Brain tumor segmentation using convolutional neural networks in MRI images. IEEE transactions on medical imaging 35(5):1240–1251, 2016CrossRefPubMedGoogle Scholar
  27. 27.
    Dvorák P, Menze BH: Local Structure Prediction with Convolutional Neural Networks for Multimodal Brain Tumor Segmentation International MICCAI Workshop on Medical Computer Vision, 2015, pp 59–71Google Scholar
  28. 28.
    Hoseini F, Shahbahrami A: An efficient implementation of fuzzy edge detection using GPU in MATLAB. In: High Performance Computing & Simulation (HPCS), 2015 International Conference on, 2015, pp 605–610). IEEEGoogle Scholar
  29. 29.
    Hoseini F, Shahbahrami A: An efficient implementation of fuzzy c-means and watershed algorithms for MRI segmentation. In: Telecommunications (IST), 2016 8th International Symposium on, 2016, pp 178–184. IEEEGoogle Scholar
  30. 30.
    Hoseini F, Shahbahrami A, Yaghoobi Notash A, Bayat P: A parallel implementation of modified fuzzy logic for breast cancer detection. Journal of Advances in Computer Research 7(2):139–148, 2016Google Scholar
  31. 31.
    Sutskever I, Martens J, Dahl G, Hinton G: On the importance of initialization and momentum in deep learning. In International conference on machine learning, 2013, pp 1139–1147Google Scholar
  32. 32.
    Nesterov Y: Introductory lectures on convex optimization: a basic course. Springer Science & Business Media (Book), Vol. 87, 2013Google Scholar
  33. 33.
    Kingma D, Ba J: Adam: a method for stochastic optimization. 3rd International Conference for Learning Representations, preprint arXiv:1412–6980, 2015Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  1. 1.Department of Computer Engineering, Rasht BranchIslamic Azad UniversityRashtIran
  2. 2.Department of Computer Engineering, Faculty of EngineeringUniversity of GuilanRashtIran

Personalised recommendations