Utility of a public-available artificial intelligence in diagnosis of polypoidal choroidal vasculopathy
- 46 Downloads
To investigate the feasibility of training an artificial intelligence (AI) on a public-available AI platform to diagnose polypoidal choroidal vasculopathy (PCV) using indocyanine green angiography (ICGA).
Two methods using AI models were trained by a data set including 430 ICGA images of normal, neovascular age-related macular degeneration (nvAMD), and PCV eyes on a public-available AI platform. The one-step method distinguished normal, nvAMD, and PCV images simultaneously. The two-step method identifies normal and abnormal ICGA images at the first step and diagnoses PCV from the abnormal ICGA images at the second step. The method with higher performance was used to compare with retinal specialists and ophthalmologic residents on the performance of diagnosing PCV.
The two-step method had better performance, in which the precision was 0.911 and the recall was 0.911 at the first step, and the precision was 0.783, and the recall was 0.783 at the second step. For the test data set, the two-step method distinguished normal and abnormal images with an accuracy of 1 and diagnosed PCV with an accuracy of 0.83, which was comparable to retinal specialists and superior to ophthalmologic residents.
In this evaluation of ICGA images from normal, nvAMD, and PCV eyes, the models trained on a public-available AI platform had comparable performance to retinal specialists for diagnosing PCV. The utility of public-available AI platform might help everyone including ophthalmologists who had no AI-related resources, especially those in less developed areas, for future studies.
KeywordsArtificial intelligence Deep learning Diagnosis Indocyanine green angiography Machine learning Polypoidal choroidal vasculopathy
Thanks are due to Xiao Zhang, Huan Chen, Ruoan Han, Bilei Zhang, Yuelin Wang, and Shan Wu for making diagnosis on data set and supporting this study.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All applicable international, national, and/or institutional guidelines for the care and use of animals were followed. All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. For this type of study formal consent is not required.
- 3.Koh AH, Chen LJ, Chen SJ, Chen Y, Giridhar A, Iida T, Kim H, Yuk Yau Lai T, Lee WK, Li X, Han Lim T, Ruamviboonsuk P, Sharma T, Tang S, Yuzawa M (2013) Polypoidal choroidal vasculopathy: evidence-based guidelines for clinical diagnosis and treatment. Retina 33:686–716. https://doi.org/10.1097/IAE.0b013e3182852446 CrossRefGoogle Scholar
- 4.Ozkaya A, Alagoz C, Garip R, Alkin Z, Perente I, Yazici AT, Taskapili M (2016) The role of indocyanine green angiography imaging in further differential diagnosis of patients with nAMD who are morphologically poor responders to ranibizumab in a real-life setting. Eye (Lond) 30:958–965. https://doi.org/10.1038/eye.2016.71 CrossRefGoogle Scholar
- 6.Tan CS, Ngo WK, Lim LW, Tan NW, Lim TH (2016) EVEREST study report 3: diagnostic challenges of polypoidal choroidal vasculopathy. Lessons learnt from screening failures in the EVEREST study. Graefes Arch Clin Exp ophthalmol 254:1923–1930. https://doi.org/10.1007/s00417-016-3333-y CrossRefPubMedPubMedCentralGoogle Scholar
- 11.Zoph B, Le QV (2016) Neural architecture search with reinforcement learning. https://arxiv.org/abs/1611.01578
- 12.Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710Google Scholar
- 13.Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J, Kim R, Raman R, Nelson PC, Mega JL, Webster DR (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316:2402–2410. https://doi.org/10.1001/jama.2016.17216 CrossRefPubMedGoogle Scholar
- 14.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 ophthalmology 135:1170–1176. https://doi.org/10.1001/jamaophthalmol.2017.3782 CrossRefPubMedPubMedCentralGoogle Scholar
- 19.Bogunovic H, Waldstein SM, Schlegl T, Langs G, Sadeghipour A, Liu X, Gerendas BS, Osborne A, Schmidt-Erfurth U (2017) Prediction of anti-VEGF treatment requirements in neovascular AMD using a machine learning approach. Invest Ophthalmol Vis Sci 58:3240–3248. https://doi.org/10.1167/iovs.16-21053 CrossRefPubMedGoogle Scholar
- 20.Rohm M, Tresp V, Muller M, Kern C, Manakov I, Weiss M, Sim DA, Priglinger S, Keane PA, Kortuem K (2018) Predicting visual acuity by using machine learning in patients treated for neovascular age-related macular degeneration. Ophthalmology 125:1028–1036. https://doi.org/10.1016/j.ophtha.2017.12.034 CrossRefPubMedGoogle Scholar