Deep Learning Approach for Automated Detection of Myopic Maculopathy and Pathologic Myopia in Fundus Images

Published:February 18, 2021DOI:


      To determine whether eyes with pathologic myopia can be identified and whether each type of myopic maculopathy lesion on fundus photographs can be diagnosed by deep learning (DL) algorithms.


      A DL algorithm was developed to recognize myopic maculopathy features and to categorize the myopic maculopathy automatically.


      We examined 7020 fundus images from 4432 highly myopic eyes obtained from the Advanced Clinical Center for Myopia.


      Deep learning (DL) algorithms were developed to recognize the key features of myopic maculopathy with 5176 fundus images. These algorithms were also used to develop a Meta-analysis for Pathologic Myopia (META-PM) study categorizing system (CS) by adding a specific processing layer. Models and the system were evaluated by 1844 fundus image. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to determine the performance of each DL algorithm. The rate of correct predictions was used to determine the performance of the META-PM study CS.

      Main Outcome Measures

      Four trained DL models were able to recognize the lesions of myopic maculopathy accurately with high sensitivity and specificity. The META-PM study CS also showed a high accuracy and was qualified to be used in a semiautomated way during screening for myopic maculopathy in highly myopic eyes.


      The sensitivity of the DL models was 84.44% for diffuse atrophy, 87.22% for patchy atrophy, 85.10% for macular atrophy, and 37.07% for choroidal neovascularization, and the AUC values were 0.970, 0.978, 0.982, and 0.881, respectively. The rate of total correct predictions from the META-PM study CS was 87.53%, with rates of 90.18%, 95.28%, 97.50%, and 91.14%, respectively, for each type of lesion. The META-PM study CS showed an overall rate of 92.08% in detecting pathologic myopia correctly, which was defined as having myopic maculopathy equal to or more serious than diffuse atrophy.


      The novel DL models and system can achieve high sensitivity and specificity in identifying the different types of lesions of myopic maculopathy. These results will assist in the screening for pathologic myopia and subsequent protection of patients against low vision and blindness caused by myopic maculopathy.


      Abbreviations and Acronyms:

      AUC (area under the receiver operating characteristic curve), CNN (convolutional neural network), CNV (choroidal neovascularization), CS (categorizing system), DL (deep learning), META-PM (Meta-analysis for Pathologic Myopia), SEED (Singapore Epidemiology of Eye Diseases)
      To read this article in full you will need to make a payment
      Subscribe to Ophthalmology Retina
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Morgan I.G.
        • Ohno-Matsui K.
        • Saw S.M.
        Lancet. 2012; 379: 1739-1748
        • Dong L.
        • Kang Y.K.
        • Li Y.
        • et al.
        Prevalence and time trends of myopia in children and adolescents in China: a systemic review and meta-analysis.
        Retina. 2020; 40: 399-411
        • Lin L.L.
        • Shih Y.F.
        • Hsiao C.K.
        • Chen C.J.
        Prevalence of myopia in Taiwanese schoolchildren: 1983 to 2000.
        Ann Acad Med Singapore. 2004; 33: 27-33
        • Edwards M.H.
        • Lam C.S.
        The epidemiology of myopia in Hong Kong.
        Ann Acad Med Singapore. 2004; 33: 34-38
        • Ueda E.
        • Yasuda M.
        • Fujiwara K.
        • et al.
        Trends in the prevalence of myopia and myopic maculopathy in a Japanese population: the Hisayama Study.
        Invest Ophthalmol Vis Sci. 2019; 60: 2781-2786
        • Sensaki S.
        • Sabanayagam C.
        • Verkicharla P.K.
        • et al.
        An ecologic study of trends in the prevalence of myopia in Chinese adults in Singapore born from the 1920s to 1980s.
        Ann Acad Med Singapore. 2017; 46: 229-236
        • Han S.B.
        • Jang J.
        • Yang H.K.
        • et al.
        Prevalence and risk factors of myopia in adult Korean population: Korea National Health and Nutrition Examination Survey 2013–2014 (KNHANES VI).
        PLoS One. 2019; 14e0211204
        • Morgan I.G.
        • French A.N.
        • Ashby R.S.
        • et al.
        The epidemics of myopia: aetiology and prevention.
        Prog Retin Eye Res. 2018; 62: 134-149
        • Reed D.S.
        • Ferris L.M.
        • Santamaria J.
        • et al.
        Prevalence of myopia in newly enlisted airmen at Joint Base San Antonio.
        Clin Ophthalmol. 2020; 14: 133-137
        • Hopf S.
        • Korb C.
        • Nickels S.
        • et al.
        Prevalence of myopic maculopathy in the German population: results from the Gutenberg Health Study.
        Br J Ophthalmol. 2019; (;104:1254–1259)
        • Alvarez-Peregrina C.C.
        • Sanchez-Tena M.
        • Martinez-Perez C.C.
        • Villa-Collar C.C.
        Prevalence and risk factors of myopia in Spain.
        J Ophthalmol. 2019; 2019: 3419576
        • Bikbov M.M.
        • Gilmanshin T.R.
        • Kazakbaeva G.M.
        • et al.
        Prevalence of myopic maculopathy among adults in a Russian population.
        JAMA Netw Open. 2020; 3e200567
        • Holden B.A.
        • Fricke T.R.
        • Wilson D.A.
        • et al.
        Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050.
        Ophthalmology. 2016; 123: 1036-1042
        • Ohno-Matsui K.
        • Lai T.Y.
        • Lai C.C.
        • Cheung C.M.
        Updates of pathologic myopia.
        Prog Retin Eye Res. 2016; 52: 156-187
        • Flitcroft D.I.
        • He M.
        • Jonas J.B.
        • et al.
        IMI—Defining and classifying myopia: a proposed set of standards for clinical and epidemiologic studies.
        Invest Ophthalmol Vis Sci. 2019; 60: M20-M30
        • Ohno-Matsui K.
        Atlas of Pathologic Myopia.
        Springer Singapore, Singapore2020: 3-6
        • Wang N.K.
        • Wu Y.M.
        • Wang J.P.
        • et al.
        Clinical characteristics of posterior staphylomas in myopic eyes with axial length shorter than 26.5 millimeters.
        Am J Ophthalmol. 2016; 162: 180-190 e1
        • Ohno-Matsui K.
        Proposed classification of posterior staphylomas based on analyses of eye shape by three-dimensional magnetic resonance imaging and wide-field fundus imaging.
        Ophthalmology. 2014; 121: 1798-1809
        • Tang Y.
        • Wang X.
        • Wang J.
        • et al.
        Prevalence and causes of visual impairment in a Chinese adult population: the Taizhou Eye Study.
        Ophthalmology. 2015; 122: 1480-1488
        • Iwase A.
        • Araie M.
        • Tomidokoro A.
        • et al.
        Prevalence and causes of low vision and blindness in a Japanese adult population: the Tajimi Study.
        Ophthalmology. 2006; 113: 1354-1362
        • Xu L.
        • Wang Y.
        • Li Y.
        • et al.
        Causes of blindness and visual impairment in urban and rural areas in Beijing: the Beijing Eye Study.
        Ophthalmology. 2006; 113 (1134 e1–11)
        • Avisar R.
        • Friling R.
        • Snir M.
        • et al.
        Estimation of prevalence and incidence rates and causes of blindness in Israel, 1998–2003.
        Isr Med Assoc J. 2006; 8: 880-881
        • Kuang T.M.
        • Tsai S.Y.
        • Hsu W.M.
        • et al.
        Correctable visual impairment in an elderly Chinese population in Taiwan: the Shihpai Eye Study.
        Invest Ophthalmol Vis Sci. 2007; 48: 1032-1037
        • Dandona L.
        • Dandona R.
        • Srinivas M.
        • et al.
        Blindness in the Indian state of Andhra Pradesh.
        Invest Ophthalmol Vis Sci. 2001; 42: 908-916
        • van Newkirk M.R.
        The Hong Kong Vision Study: a pilot assessment of visual impairment in adults.
        Trans Am Ophthalmol Soc. 1997; 95: 715-749
        • Varma R.
        • Kim J.S.
        • Burkemper B.S.
        • et al.
        Prevalence and causes of visual impairment and blindness in Chinese American adults: the Chinese American Eye Study.
        JAMA Ophthalmol. 2016; 134: 785-793
        • Cotter S.A.
        • Varma R.
        • Ying-Lai M.
        • et al.
        Causes of low vision and blindness in adult Latinos: the Los Angeles Latino Eye Study.
        Ophthalmology. 2006; 113: 1574-1582
        • Sainz-Gomez C.
        • Fernandez-Robredo P.
        • Salinas-Alaman A.
        • et al.
        Prevalence and causes of bilateral blindness and visual impairment among institutionalized elderly people in Pamplona, Spain.
        Eur J Ophthalmol. 2010; 20: 442-450
        • Cedrone C.
        • Culasso F.
        • Cesareo M.
        • et al.
        Incidence of blindness and low vision in a sample population: the Priverno Eye Study, Italy.
        Ophthalmology. 2003; 110: 584-588
        • Buch H.
        • Vinding T.
        • La Cour M.
        • et al.
        Prevalence and causes of visual impairment and blindness among 9980 Scandinavian adults: the Copenhagen City Eye Study.
        Ophthalmology. 2004; 111: 53-61
        • Bamashmus M.A.
        • Matlhaga B.
        • Dutton G.N.
        Causes of blindness and visual impairment in the West of Scotland.
        Eye (Lond). 2004; 18: 257-261
        • Krumpaszky H.G.
        • Ludtke R.
        • Mickler A.
        • et al.
        Blindness incidence in Germany. A population-based study from Wurttemberg-Hohenzollern.
        Ophthalmologica. 1999; 213: 176-182
        • Klaver C.C.
        • Wolfs R.C.
        • Vingerling J.R.
        • et al.
        Age-specific prevalence and causes of blindness and visual impairment in an older population: the Rotterdam Study.
        Arch Ophthalmol. 1998; 116: 653-658
        • Xu L.
        • Wang Y.
        • Li Y.
        • et al.
        Causes of blindness and visual impairment in urban and rural areas in Beijing: the Beijing Eye Study.
        Ophthalmology. 2006; 113 (1134 e1–11)
        • Gao L.Q.
        • Liu W.
        • Liang Y.B.
        • et al.
        Prevalence and characteristics of myopic retinopathy in a rural Chinese adult population: the Handan Eye Study.
        Arch Ophthalmol. 2011; 129: 1199-1204
        • Vongphanit J.
        • Mitchell P.
        • Wang J.J.
        Prevalence and progression of myopic retinopathy in an older population.
        Ophthalmology. 2002; 109: 704-711
        • Tan M.
        • Le Q.V.
        EfficientNet: rethinking model scaling for convolutional neural networks.
        arXiv e-prints. 2019; (Available at: Accessed July 2018.)
        • Ravì D.
        • Wong C.
        • Deligianni F.
        • et al.
        Deep learning for health informatics.
        IEEE J Biomed Health Inform. 2017; 21: 4-21
        • Ting D.S.W.
        • Cheung C.Y.
        • Lim G.
        • et al.
        Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes.
        JAMA. 2017; 318: 2211-2223
        • Peng Y.
        • Dharssi S.
        • Chen Q.
        • et al.
        DeepSeeNet: a deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs.
        Ophthalmology. 2019; 126: 565-575
        • Ohno-Matsui K.
        • Kawasaki R.
        • Jonas J.B.
        • et al.
        International photographic classification and grading system for myopic maculopathy.
        Am J Ophthalmol. 2015; 159: 877-883 e7
        • Ohno-Matsui K.
        Myopic chorioretinal atrophy.
        in: Spaide R.F. K O.-M. Yannuzzi L.A. Pathologic Myopia. Springer, New York2014: 189-204
        • Choudhury F.
        • Meuer S.M.
        • Klein R.
        • et al.
        Prevalence and characteristics of myopic degeneration in an adult Chinese American population: the Chinese American Eye Study.
        Am J Ophthalmol. 2018; 187: 34-42
        • Wong Y.L.
        • Sabanayagam C.
        • Ding Y.
        • et al.
        Prevalence, risk factors, and impact of myopic macular degeneration on visual impairment and functioning among adults in Singapore.
        Invest Ophthalmol Vis Sci. 2018; 59: 4603-4613
        • Majithia S.
        • Tham Y.C.
        • Chee M.L.
        • et al.
        Cohort profile: the Singapore Epidemiology of Eye Diseases (SEED) study.
        Int J Epidemiol. 2021; (;50:41–42)
        • Xu X.
        • Fang Y.
        • Uramoto K.
        • et al.
        Clinical features of lacquer cracks in eyes with pathologic myopia.
        Retina. 2019; 39: 1265-1277
        • Selvaraju R.R.
        • Cogswell M.
        • Das A.
        • et al.
        Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.
        Int J Comput Vis. 2016; (;128:36–359)
        • Fang Y.
        • Yokoi T.
        • Nagaoka N.
        • et al.
        Progression of myopic maculopathy during 18-year follow-up.
        Ophthalmology. 2018; 125: 863-877
        • Du R.
        • Fang Y.
        • Jonas J.B.
        • et al.
        Clinical features of patchy chorioretinal atrophy in pathologic myopia.
        Retina. 2020; 40: 951-959
        • Wong T.Y.
        • Ferreira A.
        • Hughes R.
        • et al.
        Epidemiology and disease burden of pathologic myopia and myopic choroidal neovascularization: an evidence-based systematic review.
        Am J Ophthalmol. 2014; 157: 9-25 e12
        • Farinha C.L.
        • Baltar A.S.
        • Nunes S.G.
        • et al.
        Progression of myopic maculopathy after treatment of choroidal neovascularization.
        Ophthalmologica. 2014; 231: 211-220
        • Zheng Y.F.
        • Pan C.W.
        • Chay J.
        • et al.
        The economic cost of myopia in adults aged over 40 years in Singapore.
        Invest Ophthalmol Vis Sci. 2013; 54: 7532-7537