Clinical explainable differential diagnosis of polypoidal choroidal vasculopathy and age-related macular degeneration using deep learning

Ting, 2017, Choroidal remodeling in age-related macular degeneration and polypoidal choroidal vasculopathy: a 12-month prospective study, Sci. Rep., 7, 10.1038/s41598-017-08276-4 Lau, 2015, En-face optical coherence tomography in the diagnosis and management of age-related macular degeneration and polypoidal choroidal vasculopathy, Indian J. Ophthalmol., 63, 378, 10.4103/0301-4738.159860 Chung, 2011, Choroidal thickness in polypoidal choroidal vasculopathy and exudative age-related macular degeneration, Ophthalmology., 118, 840, 10.1016/j.ophtha.2010.09.012 Laude, 2010, Polypoidal choroidal vasculopathy and neovascular age-related macular degeneration: same or different disease?, Prog. Retin. Eye Res., 29, 19, 10.1016/j.preteyeres.2009.10.001 Yannuzzi, 1999, Polypoidal choroidal vasculopathy and neovascularized age-related macular degeneration, Arch. Ophthalmol., 117, 1503, 10.1001/archopht.117.11.1503 Spaide, 2010 Klaver, 1998, Age-specific prevalence and causes of blindness and visual impairment in an older population: the Rotterdam Study, Arch. Ophthalmol., 116, 653, 10.1001/archopht.116.5.653 Wong, 2007, Clinical update: new treatments for age-related macular degeneration, Lancet, 370, 204, 10.1016/S0140-6736(07)61104-0 Kumar, 2020, Prevalence of polypoidal choroidal vasculopathy in Indian population: risk factors, clinical and imaging characteristics, PLoS One, 15, 1, 10.1371/journal.pone.0231901 Wong, 2015, Polypoidal choroidal vasculopathy in asians, J. Clin. Med., 4, 10.3390/jcm4050782 Yadav, 2017, Polypoidal choroidal vasculopathy: a common type of neovascular age-related macular degeneration in Caucasians, Br. J. Ophthalmol., 101, 1377, 10.1136/bjophthalmol-2016-310074 2005, Criteria for diagnosis of polypoidal choroidal vasculopathy, Japanese Study. Gr Polypoidal. Choroidal. Vasc., 109, 417 Puliafito, 1995, Imaging of macular diseases with optical coherence tomography, Ophthalmology., 102, 217, 10.1016/S0161-6420(95)31032-9 Iijima, 2000, Optical coherence tomography of orange-red subretinal lesions in eyes with idiopathic polypoidal choroidal vasculopathy, Am. J. Ophthalmol., 129, 21, 10.1016/S0002-9394(99)00253-6 Iijima, 1999, Optical coherence tomography of idiopathic polypoidal choroidal vasculopathy, Am. J. Ophthalmol., 127, 301, 10.1016/S0002-9394(98)00411-5 Sa, 2005, Optical coherence tomography of idiopathic polypoidal choroidal vasculopathy, Kor. J. Ophthalmol., 19, 275, 10.3341/kjo.2005.19.4.275 Fenner, 2021, Prevalence of polypoidal choroidal vasculopathy using non-ICGA based criteria, Ophthalmol Retin, 24 Heisler M, Karst S, Lo J, et al. Ensemble deep learning for diabetic retinopathy detection using optical coherence tomography angiography. Published online 2020:1-11. Zang, 2021, vol. 68, 1859 Tomographic, 2018 Lee, 2016, Deep learning is effective for classifying normal versus age-related macular degeneration OCT images, Ophthalmol Retin, 1, 322, 10.1016/j.oret.2016.12.009 Kermany, 2018, Identifying medical diagnoses and treatable diseases by image-based deep learning, Cell, 172, 1122, 10.1016/j.cell.2018.02.010 Ma, 2021, LF-UNet – a novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images, Comput. Med. Imag. Graph., 94, 10.1016/j.compmedimag.2021.101988 Yim, 2020, Predicting conversion to wet age-related macular degeneration using deep learning, Nat Med., 1 De Fauw, 2018, Clinically applicable deep learning for diagnosis and referral in retinal disease, Nat. Med., 24, 1342, 10.1038/s41591-018-0107-6 Hwang, 2021, Distinguishing retinal angiomatous proliferation from polypoidal choroidal vasculopathy with a deep neural network based on optical coherence tomography, Scientific Report, 11, 9275, 10.1038/s41598-021-88543-7 He, 2016, Deep residual learning for image recognition, 770 Deng, 2009, Imagenet: a large-scale hierarchical image database, 248 He, 2015, Delving deep into rectifiers: surpassing human-level performance on imagenet classification, vol. 2015, 1026 Kouw Kingma, 2014, 1 Singh, 2016, Layer-specific adaptive learning rates for deep networks, vol. 2, 364 Howard, 2018, Universal language model fine-tuning for text classification, vol. 1, 328 Caruana, 2001, Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping, Adv Neural Inf Process Syst., 402 Karlsruhe, 1998, Early stopping-but when?, 55 Ma, 2020, Differential diagnosis between polypoidal choroidal vasculopathy (PCV) and Age-related macular degeneration (AMD) using Deep Neural Network, Investigative Ophthalmology & Visual Science, 61 Singh, 2013, Analysis of repeated measurement data in the clinical trials, J. Ayurveda Integr. Med., 4, 77, 10.4103/0975-9476.113872 Benjamini, 1995, Controlling the false discovery rate: a practical and powerful approach to multiple testing, J. R Stat. Soc. Ser. B, 57, 289 Selvaraju, 2017, Grad-CAM: visual explanations from deep networks via gradient-based localization, 618 Ma, 2020, Differential diagnosis of frontotemporal dementia, Alzheimer's disease and normal aging using a multi-scale multi-type feature generative adversarial deep neural network on structural magnetic resonance images, Front. Neurosci., 14, 853, 10.3389/fnins.2020.00853 Singh, 2021, COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays, Neural Comput. Appl., 33, 8871, 10.1007/s00521-020-05636-6 Xia, 2021, Deep learning for automatic differential diagnosis of primary central nervous system lymphoma and glioblastoma: multi-parametric magnetic resonance imaging based convolutional neural network model, J. Magn. Reson. Imag., 54, 880, 10.1002/jmri.27592 Irie, 2020, A novel deep learning approach with a 3D convolutional ladder network for differential diagnosis of idiopathic normal pressure hydrocephalus and Alzheimer's disease, Magn. Reson. Med. Sci., 19, 351, 10.2463/mrms.mp.2019-0106 Heo, 2020, Development of a deep-learning-based artificial intelligence tool for differential diagnosis between dry and neovascular age-related macular degeneration, Diagnostics, 10, 10.3390/diagnostics10050261 Friedman, 2004, Prevalence of age-related macular degeneration in the United States, Arch. Ophthalmol., 122, 564, 10.1001/archopht.1941.00870100042005 Lee, 2008, The therapeutic effects of bevacizumab in patients with polypoidal choroidal vasculopathy, Korean. J. Ophthalmol., 22, 92, 10.3341/kjo.2008.22.2.92 Gomi, 2008, Polypoidal choroidal vasculopathy and treatments, Curr. Opin. Ophthalmol., 19, 208, 10.1097/ICU.0b013e3282fb7c33 Yuzawa, 2003, A study of laser photocoagulation for polypoidal choroidal vasculopathy, Jpn. J. Ophthalmol., 47, 379, 10.1016/S0021-5155(03)00042-X Chan, 2004, Photodynamic therapy with verteporfin for symptomatic polypoidal choroidal vasculopathy: one-year results of a prospective case series, Ophthalmology., 111, 1576, 10.1016/j.ophtha.2003.12.056 Tsai, 2022, Diagnosis of Polypoidal Choroidal Vasculopathy From Fluorescein Angiography Using Deep Learning, Diagnosis of Polypoidal Choroidal Vasculopathy From Fluorescein Angiography Using Deep Learning, 11, 6 Lin, 2021, Assessing the clinical utility of expanded macular OCTs using machine learning, Transl. Vis. Sci. Technol., 10, 32, 10.1167/tvst.10.6.32 Tomita, 2018, Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans, Comput. Biol. Med., 98, 8, 10.1016/j.compbiomed.2018.05.011 Qiu, 2020, Development and validation of an interpretable deep learning framework for Alzheimer's disease classification, Brain, 143, 1920, 10.1093/brain/awaa137 Yoo, 2019, The possibility of the combination of OCT and fundus images for improving the diagnostic accuracy of deep learning for age-related macular degeneration: a preliminary experiment, Med. Biol. Eng. Comput., 57, 677, 10.1007/s11517-018-1915-z Yoo, 2021, Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification, Med. Biol. Eng. Comput., 59, 401, 10.1007/s11517-021-02321-1