Vessels semantic segmentation with gradient descent optimization

  • Authors

    • wahyudi setiawan University of Trunojoyo Madura
    • Moh. Imam Utoyo University of Airlangga
    • Riries Rulaningtyas University of Airlangga
    2018-12-17
    https://doi.org/10.14419/ijet.v7i4.18104
  • Convolutional Neural Network, Deep Learning, Gradient Descent, Retinal Vessels, Semantic Segmentation.

  • Semantic segmentation is a segmentation based on the accuracy of the pixel. Segmentation of retinal vessels aims to differentiate between vessels and non-vessels. There are many conventional methods of retinal vessels segmentation. Conventional methods should perform feature extraction manually. Currently, there has been widely researching on deep learning. Deep learning performs feature extraction automatically during the training phase. One of the methods of deep learning is the Convolutional Neural Network (CNN). The research used three steps i.e creating network layers, training the network, and evaluation of accuracy. We use ten layers of CNN. The CNN architecture consists of Convolution layers, Rectified Linear Unit layers, MaxPooling Layers, Transpose Convolution Layers and Softmax Layer. Furthermore, training the network include the optimization of the training phase. There are three optimization algorithms used for the training phase. The optimization algorithms are Stochastic Gradient Descent with Momentum (SGDM), Root Means Square Propagation (RMSProp) and Adaptive Moment Optimization (Adam). The dataset used for the experiment is Digital Retinal Image for Vessel Extraction (DRIVE). Computation process using the Graphical Processing Unit. Variation scenarios are performed to get the optimal accuracy. The vessels semantic segmentation average accuracy achieved 91.11% - 98.08%.

     

     

  • References

    1. [1] Thoma M. A Survey of Semantic Segmentation. 2016; 1–16. Available from: http://arxiv.org/abs/1602.06541

      [2] Hong S, Noh H, Han B. Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation. 2015 1–9. Available from: http://arxiv.org/abs/1506.04924

      [3] Shelhamer E, Long J, Darrell T. Fully Convolutional Networks for Semantic Segmentation.2016; 1–12. Available from: http://arxiv.org/abs/1605.06211

      [4] Lempitsky V, Vedaldi A, Zisserman A. A Pylon Model for Semantic Segmentation.2011 (228180):1–9. Available from: http://eprints.pascal-network.org/archive/00008426/

      [5] Chen C, Seff A, Kornhauser A, Xiao J. DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving. Princet Vison&Robotics [Internet].2018 ;( Figure 1):1. Available from: http://deepdriving.cs.princeton.edu/

      [6] Lenz I, Lee H, Saxena A. Deep learning for detecting robotic grasps. Int J Rob Res. 2015; 34(4–5):705–24. https://doi.org/10.1177/0278364914549607.

      [7] Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42(December 2012):60–88.

      [8] Fraz MM, Barman SA, Remagnino P, Hoppe A, Basit A, Uyyanonvara B, et al. An approach to localize the retinal blood vessels using bit planes and centerline detection. Comput Methods Programs Biomed [Internet].2012; 108(2):600–16. Available from: https://doi.org/10.1016/j.cmpb.2011.08.009.

      [9] Welikala RA. Automated Detection of Proliferative Diabetic Retinopathy from Retinal Images. 2014 ;( September).

      [10] Li Q, You J, Zhang D. Vessel segmentation and width estimation in retinal images using multiscale production of matched filter responses. Expert Syst Appl [Internet]. 2012; 39(9):7600–10. Available from: https://doi.org/10.1016/j.eswa.2011.12.046.

      [11] Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Owen CG, Rudnicka AR, et al. Retinal vessel extraction using first-order derivative of gaussian and morphological processing. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics). 2011; 6938 LNCS (PART 1):410–20. https://doi.org/10.1007/978-3-642-24028-7_38.

      [12] Morales S, Naranjo V, Fernando L, Alca M, Paristech M. Determination Of Retinal Network Skeleton Through Mathematical Morphology. In: Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European. 2014. p. 1–5.

      [13] Hameed IS, Ocbagabir H, Barkana BD, Yildirim B. Blood vessel segmentation in retinal images by morphological operations and by a novel pixel-tracking algorithm. Int J Innov Comput Inf Control. 2015; 11(1):189–201.

      [14] Melinscak M, Prentasic P, Loncaric S. Retinal Vessel Segmentation Using Deep Neural Networks. 2012; 1–6.

      [15] Maji D, Santara A, Mitra P, Sheet D. Ensemble of Deep Convolutional Neural Networks for Learning to Detect Retinal Vessels in Fundus Images.

      [16] Maninis K, Pont-tuset J, Arbel P, Gool L Van. Deep Retinal Image Understanding.

      [17] Liskowski P, Krawiec K. Segmenting Retinal Blood Vessels with Deep Neural Networks. IEEE Trans Med Imaging. 2016; 0062(c):1–12. https://doi.org/10.1109/TMI.2016.2546227.

      [18] Pratt H, Williams BM, Ku JY, Vas C, Mccann E, Al-bander B, et al. Automatic Detection and Distinction of Retinal Vessel Bifurcations and Crossings in Colour Fundus Photography †. 2018;1–14.

      [19] Staal J, Member A, Abrà moff MD, Niemeijer M, Viergever MA, Ginneken B Van, et al. Ridge-Based Vessel Segmentation in Color Images of the Retina. 2004; 23(4):501–9.

      [20] Deng L, Yu D. Deep L Earning : 2014. 1-134 p.

      [21] Krizhevsky A, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. : 1–9.

      [22] Lechun. Gradient-based learning applied to document recognition. proc.of IEEE. 1998 ;( november):1–46.

      [23] Zeiler MD, Fergus R. Visualizing and Understanding Convolutional Networks arXiv: 1311.2901v3 [cs.CV] 28 Nov 2013. Comput Vision–ECCV 2014 [Internet]. 2014; 8689:818–33. Available from: http://link.springer.com/10.1007/978-3-319-10590-1_53%5Cnhttp://arxiv.org/abs/1311.2901%5Cnpapers3://publication/uuid/44feb4b1-873a-4443-8baa-1730ecd16291

      [24] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2015; 07–12–June: 1–9.

      [25] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition.2014; 1–14. Available from: http://arxiv.org/abs/1409.1556

      [26] He K, ZHang X, Ren S, Sun J. Deep residual learning for image steganalysis. Multimed Tools Appl. 2015; 1–17.

      [27] Dumoulin V, Visin F. A guide to convolution arithmetic for deep learning.2018; 1–31.

      [28] Nagi J, Ducatelle F. Max-pooling convolutional neural networks for vision-based hand gesture recognition. 2011 IEEE Int Conf Signal Image Process Appl [Internet]. 2011; 342–7. Available from: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6144164

      [29] Wang C, Xi Y. Convolutional Neural Network for Image Classification. 1997 ;( 1969). Available from: http://www.cs.jhu.edu/~cwang107/files/cnn.pdf

      [30] Sainath T, Vinyals O, Senior A, Sak H. Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks. ICASSP, IEEE Int Conf Acoust Speech Signal Process - Proc. 2015; 2015–Augus: 4580–4.

      [31] Ruder S. An overview of gradient descent optimization. 2016; 1–14.

      [32] Hinton GE, Srivastava N, Swersky K. Lecture 6a- overview of mini-batch gradient descent. COURSERA Neural Networks Mach Learn [Internet]. 2012; 31. Available from: http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf

      [33] Kingma DP, Ba J. Adam: A Method for Stochastic Optimization. 2014; 1–15. Available from: http://arxiv.org/abs/1412.6980

      [34] Janocha K, Czarnecki WM. On Loss Functions for Deep Neural Networks in Classification. 2017 1–10. Available from: http://arxiv.org/abs/1702.05659.

  • Downloads

  • How to Cite

    setiawan, wahyudi, Imam Utoyo, M., & Rulaningtyas, R. (2018). Vessels semantic segmentation with gradient descent optimization. International Journal of Engineering & Technology, 7(4), 4062-4067. https://doi.org/10.14419/ijet.v7i4.18104