access icon free Automatic production of synthetic labelled OCT images using an active shape model

Limited labelled data is a challenge in the field of medical imaging and the need for a large number of them is paramount for the training of machine learning algorithms, as well as measuring the performance of image processing algorithms. The purpose of this study is to construct synthetic and labelled optical coherence tomography (OCT) data to solve the problems of having access to accurately labelled data and evaluating the processing algorithms. In this study, a modified active shape model is used which considers the anatomical features of available images such as the number and thickness of the layers as well as their associated brightness, the location of retinal blood vessels and shadow information with respect to speckle noise. The algorithm is also able to provide different data sets with the varying noise level. The validity of the proposed method for the synthesis of retinal images is measured by two methods (qualitative assessment and quantitative analysis).

Inspec keywords: image segmentation; biomedical optical imaging; eye; learning (artificial intelligence); optical tomography; speckle; blood vessels; image processing; medical image processing

Other keywords: labelled optical coherence tomography; retinal blood vessels; accurately labelled data; modified active shape model; automatic production; synthetic coherence tomography; medical imaging; machine learning algorithms; retinal images; synthetic labelled OCT images; image processing algorithms; available images

Subjects: Patient diagnostic methods and instrumentation; Optical and laser radiation (biomedical imaging/measurement); Knowledge engineering techniques; Other topics in statistics; Biology and medical computing; Computer vision and image processing techniques; Optical, image and video signal processing; Optical and laser radiation (medical uses)

References

    1. 1)
      • 24. Kulkarni, P., Lozano, D., Zouridakis, G., et al: ‘A statistical model of retinal optical coherence tomography image data’. 2011 Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, Boston, MA USA, 2011, pp. 61276130.
    2. 2)
      • 4. Danesh, H., Kafieh, R., Rabbani, H., et al: ‘Segmentation of choroidal boundary in enhanced depth imaging OCTs using a multiresolution texture based modeling in graph cuts’, Comput. Math. Methods Med., 2014, 2014, pp. 19.
    3. 3)
      • 5. Kafieh, R., Rabbani, H., Kermani, S.: ‘A review of algorithms for segmentation of optical coherence tomography from retina’, J. Med. Signals. Sens., 2013, 3, (1), p. 45.
    4. 4)
      • 31. Hamarneh, G., Abu-Gharbieh, R., Gustavsson, T., et al: ‘Active shape models-part I: modeling shape and gray level variations’, 1998.
    5. 5)
      • 7. Rabbani, H., Kafieh, R., Kazemian, , et al: ‘Obtaining thickness maps of corneal layers using the optimal algorithm for intracorneal layer segmentation’, Int. J. Biomed. Imaging., 2016, 2016, pp. 111.
    6. 6)
      • 15. Fiorini, S., Ballerini, L., Trucco, E., et al: ‘Automatic generation of synthetic retinal Fundus images’. Eurographics Italian Chapter Conf., Cagliari, Italy, 2014, pp. 4144.
    7. 7)
      • 8. Rabbani, H., Kafieh, R., Amini, Z.: ‘Optical coherence tomography image analysis’, In: ‘Wiley encyclopedia of electrical and electronics engineering’ (John Wiley & Sons, USA, 2016), pp. 116.
    8. 8)
      • 36. Li, M., Idoughi, R., Choudhury, B., et al: ‘Statistical model for OCT image denoising’, Biomed. Opt. Express, 2017, 8, (9), pp. 39033917.
    9. 9)
      • 1. Kardon, R.: ‘The role of the macula OCT scan in neuro-ophthalmology’, J. Neuroophthalmol., 2011, 31, (4), p. 353.
    10. 10)
      • 21. Serranho, P., Maduro, C., Santos, T., et al: ‘Synthetic oct data for image processing performance testing’. 2011 18th IEEE Int. Conf. on Image Processing, Brussels, Belgium, 2011, pp. 401404.
    11. 11)
      • 14. Fang, L., Cunefare, D., Wang, C., et al: ‘Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search’, Biomed. Opt. Express, 2017, 8, (5), pp. 27322744.
    12. 12)
      • 9. Kafieh, R., Amini, Z., Rabbani, H., et al: ‘Automatic multifaceted matlab package for analysis of ocular images (AMPAO)’, SoftwareX, 2019, 10, p. 100339.
    13. 13)
      • 12. Amini, Z., Kafieh, R., Rabbani, H.: ‘Speckle noise reduction and enhancement for OCT images’. Retinal Optical Coherence Tomography Image Analysis: Springer, Singapore, 2019, pp. 3972.
    14. 14)
      • 18. Costa, P., Galdran, A., Meyer, M.I., et al: ‘End-to-end adversarial retinal image synthesis’, IEEE Trans. Med. Imaging, 2017, 37, (3), pp. 781791.
    15. 15)
      • 26. Montuoro, A., Wu, J., Waldstein, S., et al: ‘Motion artefact correction in retinal optical coherence tomography using local symmetry’. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Boston, MA, USA, 2014, pp. 130137.
    16. 16)
      • 22. Varnousfaderani, E.S., Vogl, W.D., Wu, J., et al: ‘Improve synthetic retinal OCT images with present of pathologies and textural information’. Medical Imaging 2016: Image Processing, San Diego, CA, United States, 2016, vol. 9784, p. 97843V: International Society for Optics and Photonics.
    17. 17)
      • 35. Dabov, K., Foi, A., Katkovnik, V., et al: ‘Image denoising by sparse 3-D transform-domain collaborative filtering’, IEEE Trans. Image Process., 2007, 16, (8), pp. 20802095.
    18. 18)
      • 10. Trucco, E., Ruggeri, A., Karnowski, T., et al: ‘Validating retinal fundus image analysis algorithms: issues and a proposal’, Invest. Ophthalmol. Visual Sci., 2013, 54, (5), pp. 35463559.
    19. 19)
      • 19. Chen, S., Quan, H., Qin, A., et al: ‘MR image-based synthetic CT for IMRT prostate treatment planning and CBCT image-guided localization’, J. Appl. Clin. Med. Phys., 2016, 17, (3), pp. 236245.
    20. 20)
      • 23. Montuoro, A., Waldstein, S.M., Gerendas, B., et al: ‘Statistical retinal OCT appearance models’, Invest. Ophthalmol. Visual Sci., 2014, 55, (13), pp. 48084808.
    21. 21)
      • 3. Kafieh, R., Rabbani, H.: ‘Optical coherence tomography noise reduction over learned dictionaries with introduction of complex wavelet for noise reduction’. SPIE Proc. on Wavelets and Sparsity XV, San Diego, California, United States, 2013, vol. 8858.
    22. 22)
      • 25. Duan, J., Tench, C., Gottlob, I., et al: ‘New variational image decomposition model for simultaneously denoising and segmenting optical coherence tomography images’, Phys. Med. Biol., 2015, 60, (22), p. 8901.
    23. 23)
      • 11. Kafieh, R., Rabbani, H., Unal, G.: ‘Bandlets on oriented graphs: application to medical image enhancement’, IEEE Access, 2019, 7, pp. 3258932601.
    24. 24)
      • 29. Cootes, T.F., Taylor, C.J., Cooper, D.H., et al: ‘Active shape models-their training and application’, Comput. Vis. Image Underst., 1995, 61, (1), pp. 3859.
    25. 25)
      • 16. Collins, D.L., Zijdenbos, A.P., Kollokian, V., et al: ‘Design and construction of a realistic digital brain phantom’, IEEE Trans. Med. Imaging, 1998, 17, (3), pp. 463468.
    26. 26)
      • 28. Kafieh, R., Rabbani, H., Abramoff, M. D., et al: ‘Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map’, Med. Image Anal., 2013, 17, (8), pp. 907928.
    27. 27)
      • 30. Gower, J.C.: ‘Generalized procrustes analysis’, Psychometrika, 1975, 40, (1), pp. 3351.
    28. 28)
      • 34. Montazerin, M., Sajjadifar, Z., Kafieh, R.: ‘Livelayer: A semi-automatic software for segmentation of layers and objects in optical coherence tomography images’, arXiv preprint arXiv:2003.05916, 2020.
    29. 29)
      • 13. Venhuizen, F.G., van Ginneken, B., Liefers, B., et al: ‘Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks’, Biomed. Opt. Express, 2017, 8, (7), pp. 32923316.
    30. 30)
      • 33. Kafieh, R., Danesh, H., Rabbani, H., et al: ‘Vessel segmentation in images of optical coherence tomography using shadow information and thickening of retinal nerve fiber layer’. 2013 IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 2013, pp. 10751079.
    31. 31)
      • 17. Costa, P., Galdran, A., Meyer, M.I., et al: ‘Towards adversarial retinal image synthesis’, arXiv preprint arXiv:1701.08974, 2017.
    32. 32)
      • 27. Klotz, A.C.: ‘2d and 3D multiphase active contours without edges based algorithms for simultaneous segmentation of retinal layers from OCT images’, 2013.
    33. 33)
      • 20. Hsu, S.-H., Cao, Y., Huang, K., et al: ‘Investigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapy’, Phys. Med. Biol., 2013, 58, (23), p. 8419.
    34. 34)
      • 2. Chen, T.C., Cense, B., Pierce, M.C., et al: ‘Spectral domain optical coherence tomography: ultra-high speed, ultra-high resolution ophthalmic imaging’, Arch. Ophthalmol., 2005, 123, (12), pp. 17151720.
    35. 35)
      • 6. Ben-Cohen, A., Mark, D., Kovler, I., et al: ‘Retinal layers segmentation using fully convolutional network in OCT images’. RSIP Vision, Venice, Italy, 2017.
    36. 36)
      • 32. Roberts, M., Cootes, T., Adams, J.: ‘Automatic segmentation of lumbar vertebrae on digitised radiographs using linked active appearance models’, Proc. Med. Image Understanding Anal., 2006, 2, pp. 120124.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2020.0075
Loading

Related content

content/journals/10.1049/iet-ipr.2020.0075
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading