Advertisement

The Next Frontier of Imaging in Ophthalmology: Machine Learning and Tissue Biomechanics

  • Jenna Tauber
  • Larry KagemannEmail author
Chapter
Part of the Modeling and Simulation in Science, Engineering and Technology book series (MSSET)

Abstract

Medical imaging has revolutionized the diagnosis and management of disease in healthcare. Early integration of computers into medical imaging brought control of devices and data acquisition to new heights of precision. As computing power and sophistication of software evolve, we have reached an era of computer-based image interpretation. Machine learning approaches have been developed to automate certain quantitative measures derived from these modalities. Prospects for machine learning in ophthalmology address its potential role in approaching some of the most common causes of blindness worldwide: diabetic retinopathy, glaucoma, and age-related macular degeneration. As these analysis techniques evolve, concurrent advancements are seen in ophthalmology imaging technologies themselves, and today, the aqueous outflow tract and the optic nerve head can be visualized in more detail than ever before. The optimization and assimilation of these tools may hold clinically significant answers to screening, diagnosing, and managing disease.

References

  1. 1.
    Gladwell, M., Blink: The power of thinking without thinking. 2005, New York: Little, Brown and Co.Google Scholar
  2. 2.
    Kononenko, I., Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med, 2001. 23(1): p. 89-109.Google Scholar
  3. 3.
    Sajda, P., Machine learning for detection and diagnosis of disease. Annu Rev Biomed Eng, 2006. 8: p. 537-65.CrossRefGoogle Scholar
  4. 4.
    Torok, Z., et al., Combined Methods for Diabetic Retinopathy Screening, Using Retina Photographs and Tear Fluid Proteomics Biomarkers. J Diabetes Res, 2015. 2015: p. 623619.Google Scholar
  5. 5.
    Gargeya, R. and T. Leng, Automated Identification of Diabetic Retinopathy Using Deep Learning. Ophthalmology, 2017. 124(7): p. 962-969.CrossRefGoogle Scholar
  6. 6.
    Balaratnasingam, C., et al., Visual Acuity Is Correlated with the Area of the Foveal Avascular Zone in Diabetic Retinopathy and Retinal Vein Occlusion. Ophthalmology, 2016. 123(11): p. 2352-2367.CrossRefGoogle Scholar
  7. 7.
    Hwang, T.S., et al., Automated Quantification of Capillary Nonperfusion Using Optical Coherence Tomography Angiography in Diabetic Retinopathy. JAMA Ophthalmol, 2016. 134(4): p. 367-73.Google Scholar
  8. 8.
    Linderman, R., et al., Assessing the Accuracy of Foveal Avascular Zone Measurements Using Optical Coherence Tomography Angiography: Segmentation and Scaling. Transl Vis Sci Technol, 2017. 6(3): p. 16.Google Scholar
  9. 9.
    Tan, C.S., et al., Optical Coherence Tomography Angiography Evaluation of the Parafoveal Vasculature and Its Relationship With Ocular Factors. Invest Ophthalmol Vis Sci, 2016. 57(9): p. Oct224-34.CrossRefGoogle Scholar
  10. 10.
    Tang, F.Y., et al., Determinants of Quantitative Optical Coherence Tomography Angiography Metrics in Patients with Diabetes. Sci Rep, 2017. 7(1): p. 2575.Google Scholar
  11. 11.
    Khansari, M.M., et al., Automated fine structure image analysis method for discrimination of diabetic retinopathy stage using conjunctival microvasculature images. Biomed Opt Express, 2016. 7(7): p. 2597-606.CrossRefGoogle Scholar
  12. 12.
    Bowd, C. and M.H. Goldbaum, Machine learning classifiers in glaucoma. Optom Vis Sci, 2008. 85(6): p. 396-405.CrossRefGoogle Scholar
  13. 13.
    Bowd, C., et al., Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes. Invest Ophthalmol Vis Sci, 2008. 49(3): p. 945-53.Google Scholar
  14. 14.
    Asaoka, R., et al., Detecting Preperimetric Glaucoma with Standard Automated Perimetry Using a Deep Learning Classifier. Ophthalmology, 2016. 123(9): p. 1974-80.Google Scholar
  15. 15.
    Chen, X., Yanwu, X., Yan, S., Wong, D.W.K., Wong, T.Y., Liu, J., Automatic feature learning for glaucoma detection based on deep learning, in International Conference on Medical Image Computing and Computer Assisted Intervention --- MICCAI 2015, N. Navab, Hornegger, J., Wells, W. M., and A.F. Frangi, Editors. 2015, Springer International Publishing: Munich, Germany. p. 669–677.Google Scholar
  16. 16.
    Goldbaum, M.H., et al., Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. Invest Ophthalmol Vis Sci, 2002. 43(1): p. 162-9.Google Scholar
  17. 17.
    Bizios, D., et al., Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT. Acta Ophthalmol, 2010. 88(1): p. 44-52.Google Scholar
  18. 18.
    Barella, K.A., et al., Glaucoma Diagnostic Accuracy of Machine Learning Classifiers Using Retinal Nerve Fiber Layer and Optic Nerve Data from SD-OCT. J Ophthalmol, 2013. 2013: p. 789129.Google Scholar
  19. 19.
    Kim, S.J., K.J. Cho, and S. Oh, Development of machine learning models for diagnosis of glaucoma. PLoS One, 2017. 12(5): p. e0177726.CrossRefGoogle Scholar
  20. 20.
    Zilly, J., J.M. Buhmann, and D. Mahapatra, Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Comput Med Imaging Graph, 2017. 55: p. 28-41.CrossRefGoogle Scholar
  21. 21.
    Miri, M.S., et al., A machine-learning graph-based approach for 3D segmentation of Bruch’s membrane opening from glaucomatous SD-OCT volumes. Med Image Anal, 2017. 39: p. 206-217.Google Scholar
  22. 22.
    Chauhan, B.C., et al., Enhanced detection of open-angle glaucoma with an anatomically accurate optical coherence tomography-derived neuroretinal rim parameter. Ophthalmology, 2013. 120(3): p. 535-43.Google Scholar
  23. 23.
    Mookiah, M.R., et al., Decision support system for age-related macular degeneration using discrete wavelet transform. Med Biol Eng Comput, 2014. 52(9): p. 781-96.CrossRefGoogle Scholar
  24. 24.
    Fraccaro, P., et al., Combining macula clinical signs and patient characteristics for age--related macular degeneration diagnosis: a machine learning approach. BMC Ophthalmol, 2015. 15: p. 10.Google Scholar
  25. 25.
    Bogunovic, H., et al., Machine Learning of the Progression of Intermediate Age-Related Macular Degeneration Based on OCT Imaging. Invest Ophthalmol Vis Sci, 2017. 58(6): p. Bio141-bio150.CrossRefGoogle Scholar
  26. 26.
    Bogunovic, H., et al., Prediction of Anti-VEGF Treatment Requirements in Neovascular AMD Using a Machine Learning Approach. Invest Ophthalmol Vis Sci, 2017. 58(7): p. 3240-3248.Google Scholar
  27. 27.
    Caixinha, M. and S. Nunes, Machine Learning Techniques in Clinical Vision Sciences. Curr Eye Res, 2017. 42(1): p. 1-15.CrossRefGoogle Scholar
  28. 28.
    Rosner, B., R.J. Glynn, and M.L. Lee, A nonparametric test for observational non-normally distributed ophthalmic data with eye-specific exposures and outcomes. Ophthalmic Epidemiol, 2007. 14(4): p. 243-50.CrossRefGoogle Scholar
  29. 29.
    Grant, W.M., Clinical measurements of aqueous outflow. AMA Arch Ophthalmol, 1951. 46(2): p. 113-31.Google Scholar
  30. 30.
    Stamer, W.D., et al., Biomechanics of Schlemm’s canal endothelium and intraocular pressure reduction. Prog Retin Eye Res, 2015. 44: p. 86-98.Google Scholar
  31. 31.
    Carreon, T., et al., Aqueous outflow --- A continuum from trabecular meshwork to episcleral veins. Prog Retin Eye Res, 2017. 57: p. 108-133.Google Scholar
  32. 32.
    Zeng, D., et al., Young’s modulus of elasticity of Schlemm’s canal endothelial cells. Biomech Model Mechanobiol, 2010. 9(1): p. 19-33.Google Scholar
  33. 33.
    Kagemann, L., et al., Identification and assessment of Schlemm’s canal by spectral-domain optical coherence tomography. Invest Ophthalmol Vis Sci, 2010. 51(8): p. 4054-9.Google Scholar
  34. 34.
    Kagemann, L., et al., IOP elevation reduces Schlemm’s canal cross-sectional area. Invest Ophthalmol Vis Sci, 2014. 55(3): p. 1805-9.Google Scholar
  35. 35.
    Wang, F., et al., Comparison of Schlemm’s canal’s biological parameters in primary open-angle glaucoma and normal human eyes with swept source optical. J Biomed Opt, 2012. 17(11): p. 116008.Google Scholar
  36. 36.
    Pant, A.D., Kagemann, L., Schuman, J.S., Sigal, I.A., Amini, R., An imaged-based inverse finite element method to determine in-vivo mechanical properties of the human trabecular meshwork. Journal for Modeling in Ophthalmology, 2017. 3: p. 100-111.Google Scholar
  37. 37.
    Xin, C., et al., Aqueous outflow regulation: Optical coherence tomography implicates pressure-dependent tissue motion. Exp Eye Res, 2017. 158: p. 171-186.Google Scholar
  38. 38.
    Hariri, S., et al., Platform to investigate aqueous outflow system structure and pressure-dependent motion using high-resolution spectral domain optical coherence tomography. J Biomed Opt, 2014. 19(10): p. 106013.CrossRefGoogle Scholar
  39. 39.
    Francis, A.W., et al., Morphometric analysis of aqueous humor outflow structures with spectral-domain optical coherence tomography. Invest Ophthalmol Vis Sci, 2012. 53(9): p. 5198-207.Google Scholar
  40. 40.
    Li, P., et al., Pulsatile motion of the trabecular meshwork in healthy human subjects quantified by phase-sensitive optical coherence tomography. Biomed Opt Express, 2013. 4(10): p. 2051-65.Google Scholar
  41. 41.
    Sun, Y.C., et al., Pulsatile motion of trabecular meshwork in a patient with iris cyst by phase-sensitive optical coherence tomography: a case report. Quant Imaging Med Surg, 2015. 5(1): p. 171-3.Google Scholar
  42. 42.
    Burgoyne, C.F., et al., The optic nerve head as a biomechanical structure: a new paradigm for understanding the role of IOP-related stress and strain in the pathophysiology of glaucomatous optic nerve head damage. Prog Retin Eye Res, 2005. 24(1): p. 39-73.Google Scholar
  43. 43.
    Girard, M.J., et al., Translating ocular biomechanics into clinical practice: current state and future prospects. Curr Eye Res, 2015. 40(1): p. 1-18.Google Scholar
  44. 44.
    Spaide, R.F., H. Koizumi, and M.C. Pozzoni, Enhanced depth imaging spectral-domain optical coherence tomography. Am J Ophthalmol, 2008. 146(4): p. 496-500.Google Scholar
  45. 45.
    Lee, E.J., et al., Visualization of the lamina cribrosa using enhanced depth imaging spectral-domain optical coherence tomography. Am J Ophthalmol, 2011. 152(1): p. 87-95.e1.Google Scholar
  46. 46.
    Park, S.C., et al., Enhanced depth imaging optical coherence tomography of deep optic nerve complex structures in glaucoma. Ophthalmology, 2012. 119(1): p. 3-9.Google Scholar
  47. 47.
    Nadler, Z., et al., Automated lamina cribrosa microstructural segmentation in optical coherence tomography scans of healthy and glaucomatous eyes. Biomed Opt Express, 2013. 4(11): p. 2596-608.Google Scholar
  48. 48.
    Omodaka, K., et al., 3D evaluation of the lamina cribrosa with swept-source optical coherence tomography in normal tension glaucoma. PLoS One, 2015. 10(4): p. e0122347.CrossRefGoogle Scholar
  49. 49.
    Wang, B., et al., In vivo lamina cribrosa micro-architecture in healthy and glaucomatous eyes as assessed by optical coherence tomography. Invest Ophthalmol Vis Sci, 2013. 54(13): p. 8270-4.Google Scholar
  50. 50.
    Sigal, I.A., et al., Recent advances in OCT imaging of the lamina cribrosa. Br J Ophthalmol, 2014. 98 Suppl 2: p. ii34-9.Google Scholar
  51. 51.
    Hermann, B., et al., Adaptive-optics ultrahigh-resolution optical coherence tomography. Opt Lett, 2004. 29(18): p. 2142-4.Google Scholar
  52. 52.
    Girard, M.J., et al., Shadow removal and contrast enhancement in optical coherence tomography images of the human optic nerve head. Invest Ophthalmol Vis Sci, 2011. 52(10): p. 7738-48.Google Scholar
  53. 53.
    Mari, J.M., et al., Enhancement of lamina cribrosa visibility in optical coherence tomography images using adaptive compensation. Invest Ophthalmol Vis Sci, 2013. 54(3): p. 2238-47.Google Scholar
  54. 54.
    Kim, T.W., et al., Imaging of the lamina cribrosa in glaucoma: perspectives of pathogenesis and clinical applications. Curr Eye Res, 2013. 38(9): p. 903-9.Google Scholar
  55. 55.
    Sigal, I.A., et al., Eye-specific IOP-induced displacements and deformations of human lamina cribrosa. Invest Ophthalmol Vis Sci, 2014. 55(1): p. 1-15.Google Scholar
  56. 56.
    Girard, M.J., et al., In vivo optic nerve head biomechanics: performance testing of a three-dimensional tracking algorithm. J R Soc Interface, 2013. 10(87): p. 20130459.Google Scholar
  57. 57.
    Midgett, D.E., et al., The pressure-induced deformation response of the human lamina cribrosa: Analysis of regional variations. Acta Biomater, 2017. 53: p. 123-139.Google Scholar
  58. 58.
    Strouthidis, N.G. and M.J. Girard, Altering the way the optic nerve head responds to intraocular pressure-a potential approach to glaucoma therapy. Curr Opin Pharmacol, 2013. 13(1): p. 83-9.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of OphthalmologyNYU Langone Medical Center, NYU School of MedicineNew YorkUSA

Personalised recommendations