Top

Graefe's Archive for Clinical and Experimental Ophthalmology

Published in:

01-07-2021 | Artificial Intelligence | Retinal Disorders

Classification of pachychoroid on optical coherence tomography using deep learning

Authors: Nam Yeo Kang, Ho Ra, Kook Lee, Jun Hyuk Lee, Won Ki Lee, Jiwon Baek

Published in: Graefe's Archive for Clinical and Experimental Ophthalmology | Issue 7/2021

Abstract

Purpose

Pachychoroid is characterized by dilated Haller vessels and choriocapillaris attenuation that are seen on optical coherence tomography (OCT) B-scans. This study investigated the feasibility of using deep learning (DL) models to classify pachychoroid and non-pachychoroid eyes from OCT B-scan images.

Methods

In total, 1898 OCT B-scan images were collected from eyes with macular diseases. Images were labeled as pachychoroid or non-pachychoroid based on strict quantitative and qualitative criteria for multimodal imaging analysis by two retina specialists. DL models were trained (80%) and validated (20%) using pretrained convolutional neural networks (CNNs). Model performance was assessed using an independent test set of 50 non-pachychoroid and 50 pachychoroid images.

Results

The final accuracy of AlexNet and VGG-16 was 57.52% for both models. ResNet50, Inception-v3, Inception-ResNet-v2, and Xception showed a final accuracy of 96.31%, 95.25%, 93.40%, and 92.61%, respectively, for the validation set. These models demonstrated accuracy on an independent test set of 78.00%, 86.00%, 90.00%, and 92.00%, and an F1 score of 0.718, 0.841, 0.894, and 0.920, respectively.

Conclusion

DL models classified pachychoroid and non-pachychoroid images with good performance. Accurate classification can be achieved using CNN models with deep rather than shallow neural networks.

Guyer DR, Yannuzzi LA, Slakter JS, Sorenson JA, Ho A, Orlock D (1994) Digital indocyanine green videoangiography of central serous chorioretinopathy. Arch Ophthalmol 112:1057–1062CrossRef

Warrow DJ, Hoang QV, Freund KB (2013) Pachychoroid pigment epitheliopathy. Retina 33:1659–1672. https://doi.org/10.1097/IAE.0b013e3182953df4CrossRefPubMed

Pang CE, Freund KB (2015) Pachychoroid neovasculopathy. Retina 35:1–9. https://doi.org/10.1097/IAE.0000000000000331CrossRefPubMed

Fung AT, Yannuzzi LA, Freund KB (2012) Type 1 (sub-retinal pigment epithelial) neovascularization in central serous chorioretinopathy masquerading as neovascular age-related macular degeneration. Retina 32:1829–1837. https://doi.org/10.1097/IAE.0b013e3182680a66CrossRefPubMed

Lee WK, Baek J, Dansingani KK, Lee JH, Freund KB (2016) Choroidal morphology in eyes with polypoidal choroidal vasculopathy and normal or subnormal subfoveal choroidal thickness. Retina 36(Suppl 1):S73–s82. https://doi.org/10.1097/iae.0000000000001346CrossRefPubMed

Dansingani KK, Balaratnasingam C, Naysan J, Freund KB (2016) En face imaging of pachychoroid spectrum disorders with swept-source optical coherence tomography. Retina 36:499–516. https://doi.org/10.1097/IAE.0000000000000742CrossRefPubMed

Spaide RF, Koizumi H, Pozzoni MC (2008) Enhanced depth imaging spectral-domain optical coherence tomography. Am J Ophthalmol 146:496–500. https://doi.org/10.1016/j.ajo.2008.05.032CrossRefPubMed

Zhao J, Wang YX, Zhang Q, Wei WB, Xu L, Jonas JB (2018) Macular choroidal small-vessel layer, Sattler's layer and Haller's layer thicknesses: the Beijing Eye Study. Sci Rep 8:4411. https://doi.org/10.1038/s41598-018-22745-4CrossRefPubMedPubMedCentral

Chung YR, Kim JW, Choi SY, Park SW, Kim JH, Lee K (2018) Subfoveal choroidal thickness and vascular diameter in active and resolved central serous chorioretinopathy. Retina 38:102–107. https://doi.org/10.1097/iae.0000000000001502CrossRefPubMed

10.

Chung SE, Kang SW, Lee JH, Kim YT (2011) Choroidal thickness in polypoidal choroidal vasculopathy and exudative age-related macular degeneration. Ophthalmology 118:840–845. https://doi.org/10.1016/j.ophtha.2010.09.012CrossRefPubMed

11.

Lai K, Zhou L, Zhong X, Huang C, Gong Y, Xu F, Ma L, Chen G, Cheng L, Lu L, Jin C (2018) Morphological difference of choroidal vasculature between polypoidal choroidal vasculopathy and neovascular AMD on OCT: from the perspective of pachychoroid. Ophthalmic Surg Lasers Imaging Retina 49:e114–e121. https://doi.org/10.3928/23258160-20181002-13CrossRefPubMed

12.

Flores-Moreno I, Arcos-Villegas G, Sastre M, Ruiz-Medrano J, Arias-Barquet L, Duker JS, Ruiz-Moreno JM (2020) Changes in choriocapillaris, Sattler, and Haller layer thicknesses in central serous chorioretinopathy after half-fluence photodynamic therapy. Retina. https://doi.org/10.1097/iae.0000000000002764

13.

Burlina PM, Joshi N, Pekala M, Pacheco KD, Freund DE, Bressler NM (2017) Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol 135:1170–1176. https://doi.org/10.1001/jamaophthalmol.2017.3782CrossRefPubMedPubMedCentral

14.

Gargeya R, Leng T (2017) Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124:962–969. https://doi.org/10.1016/j.ophtha.2017.02.008CrossRefPubMed

15.

Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, Hamzah H, Garcia-Franco R, San Yeo IY, Lee SY, Wong EYM, Sabanayagam C, Baskaran M, Ibrahim F, Tan NC, Finkelstein EA, Lamoureux EL, Wong IY, Bressler NM, Sivaprasad S, Varma R, Jonas JB, He MG, Cheng CY, Cheung GCM, Aung T, Hsu W, Lee ML, Wong TY (2017) Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318:2211–2223. https://doi.org/10.1001/jama.2017.18152CrossRefPubMedPubMedCentral

16.

Yanagi Y (2020) Pachychoroid disease: a new perspective on exudative maculopathy. Jpn J Ophthalmol. https://doi.org/10.1007/s10384-020-00740-5

17.

Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY (2019) Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol 103:167–175. https://doi.org/10.1136/bjophthalmol-2018-313173CrossRefPubMed

18.

Véstias MP (2019) A survey of convolutional neural networks on edge with reconfigurable computing. Algorithms 12:154. https://doi.org/10.3390/a12080154CrossRef

19.

Baek J, Lee JH, Lee K, Chung BJ, Lee WK (2019) Clinical outcome of polypoidal choroidal vasculopathy/aneurysmal type 1 neovascularization according to choroidal vascular morphology. Retina. https://doi.org/10.1097/IAE.0000000000002723

20.

Chang YC, Cheng CK (2019) Difference between pachychoroid and nonpachychoroid polypoidal choroidal vasculopathy and their response to anti-vascular endothelial growth factor therapy. Retina. https://doi.org/10.1097/IAE.0000000000002583

21.

Forte R, Coscas F, Serra R, Cabral D, Colantuono D, Souied EH (2019) Long-term follow-up of quiescent choroidal neovascularisation associated with age-related macular degeneration or pachychoroid disease. Br J Ophthalmol. https://doi.org/10.1136/bjophthalmol-2019-315189

22.

Miyake M, Ooto S, Yamashiro K, Takahashi A, Yoshikawa M, Akagi-Kurashige Y, Ueda-Arakawa N, Oishi A, Nakanishi H, Tamura H, Tsujikawa A, Yoshimura N (2015) Pachychoroid neovasculopathy and age-related macular degeneration. Sci Rep 5:16204. https://doi.org/10.1038/srep16204CrossRefPubMedPubMedCentral

23.

Morimoto M, Matsumoto H, Mimura K, Akiyama H (2017) Two-year results of a treat-and-extend regimen with aflibercept for polypoidal choroidal vasculopathy. Graefes Arch Clin Exp Ophthalmol 255:1891–1897. https://doi.org/10.1007/s00417-017-3718-6

24.

Matsumoto H, Hiroe T, Morimoto M, Mimura K, Ito A, Akiyama H (2018) Efficacy of treat-and-extend regimen with aflibercept for pachychoroid neovasculopathy and type 1 neovascular age-related macular degeneration. Jpn J Ophthalmol 62:144–150. https://doi.org/10.1007/s10384-018-0562-0CrossRefPubMed

25.

Bressem KK, Adams LC, Erxleben C, Hamm B, Niehues SM, Vahldiek JL (2020) Comparing different deep learning architectures for classification of chest radiographs. Sci Rep 10:13590. https://doi.org/10.1038/s41598-020-70479-zCrossRefPubMedPubMedCentral

26.

Feng D, Chen X, Zhou Z, Liu H, Wang Y, Bai L, Zhang S, Mou X (2020) A preliminary study of predicting effectiveness of anti-VEGF injection using OCT images based on deep learning. Annu Int Conf IEEE Eng Med Biol Soc 2020:5428–5431. https://doi.org/10.1109/embc44109.2020.9176743CrossRefPubMed

27.

Yu C, Xie S, Niu S, Ji Z, Fan W, Yuan S, Liu Q, Chen Q (2019) Hyper-reflective foci segmentation in SD-OCT retinal images with diabetic retinopathy using deep convolutional neural networks. Med Phys 46:4502–4519. https://doi.org/10.1002/mp.13728CrossRefPubMed

28.

Park K, Kim J, Kim S, Shin J (2020) Prediction of visual field from swept-source optical coherence tomography using deep learning algorithms. Graefes Arch Clin Exp Ophthalmol. https://doi.org/10.1007/s00417-020-04909-z

29.

Kim IK, Lee K, Park JH, Baek J, Lee WK (2020) Classification of pachychoroid disease on ultrawide-field indocyanine green angiography using auto-machine learning platform. Br J Ophthalmol. https://doi.org/10.1136/bjophthalmol-2020-316108

30.

Pang CE, Shah VP, Sarraf D, Freund KB (2014) Ultra-widefield imaging with autofluorescence and indocyanine green angiography in central serous chorioretinopathy. Am J Ophthalmol 158:362–371.e362. https://doi.org/10.1016/j.ajo.2014.04.021CrossRefPubMed

31.

Lee A, Ra H, Baek J (2020) Choroidal vascular densities of macular disease on ultra-widefield indocyanine green angiography. Graefes Arch Clin Exp Ophthalmol 258:1921–1929. https://doi.org/10.1007/s00417-020-04772-yCrossRefPubMed

32.

Chirco KR, Sohn EH, Stone EM, Tucker BA, Mullins RF (2017) Structural and molecular changes in the aging choroid: implications for age-related macular degeneration. Eye (Lond) 31:10–25. https://doi.org/10.1038/eye.2016.216CrossRef

Title: Classification of pachychoroid on optical coherence tomography using deep learning
Authors: Nam Yeo Kang
Ho Ra
Kook Lee
Jun Hyuk Lee
Won Ki Lee
Jiwon Baek
Publication date: 01-07-2021
Publisher: Springer Berlin Heidelberg
Keyword: Artificial Intelligence
Published in: Graefe's Archive for Clinical and Experimental Ophthalmology / Issue 7/2021
Print ISSN: 0721-832X
Electronic ISSN: 1435-702X
DOI: https://doi.org/10.1007/s00417-021-05104-4

Keynote webinar | Spotlight on sleep in brain health

Springer Medicine

Classification of pachychoroid on optical coherence tomography using deep learning

Abstract

Purpose

Methods

Results

Conclusion

Keynote webinar | Spotlight on sleep in brain health

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 7/2021

Reliability and clinical applicability of a novel tear film imaging tool

Outcomes after Descemet membrane endothelial keratoplasty over a period of 7 years at a tertiary referral center: endothelial cell density, central corneal thickness, and visual acuity

Regression of drusen or vitelliform material heralding geographic atrophy: correlation between clinical observations and basic science

Comparative profile of ocular surface microbiome in vernal keratoconjunctivitis patients and healthy subjects

Delayed follow-up of medical retina patients due to COVID-19: impact on disease activity and visual acuity

May ganglion cell complex analysis be a marker for glaucoma susceptibility in unilateral Fuchs’ uveitis syndrome?