Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Lightweight cascade framework for optic disc segmentation

  • Author(s): Xu Zhang 1, 2, 3 ; Jie Liu 2, 3 ; Shuyan Wang 2, 3 ; Zhewei Chen 2, 3 ; Bin Huang 2, 3 ; Jilun Ye 1, 2, 3
    • View affiliations
  • Source: Volume 13, Issue 10, 22 August 2019, p. 1805 – 1810
    DOI:  10.1049/iet-ipr.2019.0244 , Print ISSN 1751-9659, Online ISSN 1751-9667
© The Institution of Engineering and Technology
Received 26/02/2019, Accepted 11/06/2019, Revised 04/06/2019, Published 16/06/2019

The accurate segmentation of the optic disc (OD) is important in diagnosing and evaluating many retinal diseases. However, the OD boundary is unclear, making the task of automatic OD segmentation very challenging. Recently,many researchers have applied convolutional neural network (CNN) technology to the automatic segmentation of OD ,and the network has been widened and deepened. It can effectively improves the accuracy of segmentation but also requires high computational complexity and large memory consumption. To overcome the above defects, we propose a segmentation framework of a lightweight cascade CNN. It consists of a designed-to-be-lightweight segmentation network and a shape-refinement network cascade, cascading a shape-refined network behind a segmentation network to compensate for the degraded performance of the segmentation network after lightweight design. We tested our framework on three databases, DRIVE, DIARETDB1, and DRIONS-DB, and found that its segmentation performance is slightly better than that of u-net, and the trainable parameters are approximately 1/35 that of u-net. After verified by the DRIVE dataset, the memory used for training and testing is only about 1/3 of u-net. The method proposed in this paper can greatly reduce trainable parameters and computational resource consumption while guaranteeing satisfactory segmentation performance of the model.

Inspec keywords: diseases; neural nets; medical image processing; image resolution; learning (artificial intelligence); feature extraction; convolution; image segmentation; eye

Other keywords: automatic segmentation; shape-refined network; lightweight design; segmentation framework; designed-to-be-lightweight segmentation network; OD boundary; accurate segmentation; shape-refinement network cascade; lightweight cascade CNN; lightweight cascade network framework; automatic OD segmentation; convolutional neural network; lightweight cascade framework; optic disc segmentation; satisfactory segmentation performance

Subjects: Knowledge engineering techniques; Biology and medical computing; Computer vision and image processing techniques; Patient diagnostic methods and instrumentation; Neural computing techniques; Optical, image and video signal processing

References

    1. 1)
      • 5. Ashraf, M.N., Habib, Z., Hussain, M.: ‘Computer Aided Diagnosis of Diabetic Retinopathy’, 2015.
    2. 2)
      • 19. Staal, J., Abràmoff, M.D., Niemeijer, M., et al: ‘Ridge-based vessel segmentation in color images of the retina’, IEEE Trans. Med. Imaging, 2004, 23, (4), pp. 501–509.
    3. 3)
      • 20. Kauppi, T., Kalesnykiene, V., Kamarainen, J.K., et al: ‘DIARETDB1 diabetic retinopathy database and evaluation protocol’. British Machine Vision Conf. 2007, Warwick, UK, September 2007.
    4. 4)
      • 10. Alam, F.I., Zhou, J., Liew, W.C., et al: ‘Conditional random field and deep feature learning for hyperspectral image segmentation’. 2018.
    5. 5)
      • 4. Kumar, J.R.H., Pediredla, A.K., Seelamantula, C.S.: ‘Active discs for automated optic disc segmentation’. Signal and Information Processing, Orlando, USA, 2016, pp. 225–229.
    6. 6)
      • 2. Al-Bander, B., Al-Nuaimy, W., Williams, B.M., et al: ‘Multiscale sequential convolutional neural networks for simultaneous detection of fovea and optic disc’, Biomed. Signal Process. Control, 2018, 40, pp. 91–101.
    7. 7)
      • 3. Mckeague, C., Margrain, T.H., Bailey, C., et al: ‘Low-level night-time light therapy for age-related macular degeneration (ALight): study protocol for a randomized controlled trial’, Trials, 2014, 15, (1), pp. 1–9.
    8. 8)
      • 16. Iandola, F.N., Han, S., Moskewicz, M.W., et al: ‘Squeezenet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size’, 2016.
    9. 9)
      • 9. Cheng, J., Liu, J., Xu, Y., et al: ‘Superpixel classification for initialization in model based optic disc segmentation’. Engineering in Medicine and Biology Society.San Diego, USA, 2012, pp. 1450–1453.
    10. 10)
      • 7. Sedai, S., Roy, P.K., Mahapatra, D., et al: ‘Segmentation of optic disc and optic cup in retinal fundus images using shape regression’. Engineering in Medicine and Biology Society.Orlando, USA, 2016, pp. 3260–3264.
    11. 11)
      • 13. Maninis, K.K., Ponttuset, J., Arbeláez, P., et al: ‘Deep retinal image understanding’, 2016.
    12. 12)
      • 14. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, Comput. Sci., 2014.
    13. 13)
      • 15. Shankaranarayana, S.M., Ram, K., Mitra, K., et al: ‘Joint optic disc and cup segmentation using fully convolutional and adversarial networks’, 2017.
    14. 14)
      • 12. Sevastopolsky, A.: ‘Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network’, Pattern Recogn. Image Anal., 2017, 27, (3), pp. 618–624.
    15. 15)
      • 17. Zhang, X., Zhou, X., Lin, M., et al: ‘Shufflenet: an extremely efficient convolutional neural network for Mobile devices’, 2017.
    16. 16)
      • 25. Tan, J.H., Acharya, U.R., Bhandary, S.V., et al: ‘Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network’, J. Comput. Sci., 2017, 20, pp. 70–79.
    17. 17)
      • 24. Bharkad, S.: ‘Automatic segmentation of optic disk in retinal images’, Biomed. Signal Process. Control, 2017, 31, pp. 483–498.
    18. 18)
      • 21. Walter, S.D.: ‘The partial area under the summary ROC curve’, Stat. Med., 2005, 24, (13), p. 2025.
    19. 19)
      • 22. Ronneberger, O., Fischer, P., Brox, T.: ‘U-Net: convolutional networks for biomedical image segmentation’. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015, pp. 234–241.
    20. 20)
      • 1. Carmona, E.J., Rincón, M., García-Feijoó, J., et al: ‘Identification of the optic nerve head with genetic algorithms’, Artif. Intell. Med., 2008, 43, (3), pp. 243–259.
    21. 21)
      • 27. Basit, A., Fraz, M.M.: ‘Optic disc detection and boundary extraction in retinal images’, Appl. Opt., 2015, 54, (11), pp. 3440–3447.
    22. 22)
      • 18. Zhang, T., Qi, G.J., Xiao, B., et al: ‘Interleaved group convolutions for deep neural networks’, 2017.
    23. 23)
      • 26. Zahoor, M.N., Fraz, M.M.: ‘Fast optic disc segmentation in retinal images using polar transform’, 2017.
    24. 24)
      • 11. Zilly, J., Buhmann, J.M., Mahapatra, D.: ‘Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation’, Comput. Med. Imaging Graph., 2017, 55, pp. 28–41.
    25. 25)
      • 23. He, K., Zhang, X., Ren, S., et al: ‘Delving deep into rectifiers: surpassing human-level performance on ImageNet classification’, 2015, pp. 1026–1034.
    26. 26)
      • 8. Singh, A., Dutta, M.K., Parthasarathi, M., et al: ‘Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image’, Comput. Methods Programs Biomed., 2016, 124, (C), pp. 108–120.
    27. 27)
      • 6. Salih, N.D., Saleh, M.D., Eswaran, C., et al: ‘Fast optic disc segmentation using FFT-based template-matching and region-growing techniques’, Computer Methods in Biomech. Biomed. Eng. Imaging & Visualization, 2017, 6, (1), pp. 1–12.
    28. 28)
      • 28. Abdullah, M.A., Fraz, M.M., Barman, S.: ‘Localization and segmentation of optic disc in retinal images using circular Hough transform and grow-cut algorithm’, PeerJ, 2016, 4.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.0244
Loading

Related content

content/journals/10.1049/iet-ipr.2019.0244
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address