Page 268 - Computational Retinal Image Analysis

266 CHAPTER 13 Drusen and macular degeneration

6 Conclusions

The world’s aging population continues to increase at an unprecedented rate, and
AMD is a key global challenge posed to patients, their families, healthcare provid-
ers and society as a whole. For a long time, there have been limited options for the
management of AMD. However, with advances in the understanding of the patho-
physiology, new treatment options, and new imaging modalities, it seems there is a
new changing point.
First, the automated diagnosis of AMD at an early stage may be useful for the
prediction of the development of AMD. Deep learning techniques seem be the key
enabler to transform the research in automated analysis of AMD, as with other areas
in medical imaging. The availability of well-defined, large datasets is crucial for
making significant improvements the field. While there has been recent effort in
making data available, ethics and other regulatory requirements have to be addressed.
The engagement of ophthalmologists will be key for the development, valida-
tion and introduction of any kind of automated decisions. Clinicians are expected to
perform an important role in the deep learning era. In particular, multiple experts are
important in producing reference standards in order to avoid individual bias.
The challenges introduced by the invention of new imaging modalities such as
OCTA need to be addressed. To use images for the classification of AMD is the cur-
rent focus, but predictions of the onset and outcomes of AMD, as well as the effects
of treatment will be important in the next wave. Continuing investment in research
and the involvement of industry will also lead to the rapid development in terms of
automated image analysis for AMD. It is our expectation that patients with AMD will
soon feel the huge benefit offered by AI and automated image analysis.

References
[1] A. Bird, N. Bressler, S. Bressler, I. Chisholm, G. Coscas, M. Davis, P. De Jong,
C. Klaver, B. Klein, R. Klein, An international classification and grading system for
age-related maculopathy and age-related macular degeneration, Surv. Ophthalmol. 39
(1995) 367–374.
[2] W.L. Wong, X. Su, X. Li, C.M.G. Cheung, R. Klein, C.-Y. Cheng, T.Y. Wong, Global prev-
alence of age-related macular degeneration and disease burden projection for 2020 and
2040: a systematic review and meta-analysis, Lancet Glob. Health 2 (2014) e106–e116.
[3] K.J. Cruickshanks, R.F. Hamman, R. Klein, D.M. Nondahl, S.M. Shetterly, The preva-
lence of age-related maculopathy by geographic region and ethnicity: the Colorado-
Wisconsin Study of Age-Related Maculopathy, Arch. Ophthalmol. 115 (1997) 242–250.
[4] R. Varma, S. Fraser-Bell, S. Tan, R. Klein, S.P. Azen, Los Angeles Latino Eye Study
Group, Prevalence of age-related macular degeneration in Latinos: the Los Angeles
Latino eye study, Ophthalmology 111 (2004) 1288–1297.
[5] R. Kawasaki, M. Yasuda, S.J. Song, S.-J. Chen, J.B. Jonas, J.J. Wang, P. Mitchell,
T.Y. Wong, The prevalence of age-related macular degeneration in Asians: a systematic
review and meta-analysis, Ophthalmology 117 (2010) 921–927.