Accurate prediction of glaucoma from colour fundus images with a convolutional neural network that relies on active and transfer learning

Ruben Hemelings, Bart Elen, João Barbosa-Breda, Sophie Lemmens, Maarten Meire, Sayeh Pourjavan, Evelien Vandewalle, Sara Van de Veire, Matthew B Blaschko, Patrick De Boever, Ingeborg Stalmans, Ruben Hemelings, Bart Elen, João Barbosa-Breda, Sophie Lemmens, Maarten Meire, Sayeh Pourjavan, Evelien Vandewalle, Sara Van de Veire, Matthew B Blaschko, Patrick De Boever, Ingeborg Stalmans

Abstract

Purpose: To assess the use of deep learning (DL) for computer-assisted glaucoma identification, and the impact of training using images selected by an active learning strategy, which minimizes labelling cost. Additionally, this study focuses on the explainability of the glaucoma classifier.

Methods: This original investigation pooled 8433 retrospectively collected and anonymized colour optic disc-centred fundus images, in order to develop a deep learning-based classifier for glaucoma diagnosis. The labels of the various deep learning models were compared with the clinical assessment by glaucoma experts. Data were analysed between March and October 2018. Sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and amount of data used for discriminating between glaucomatous and non-glaucomatous fundus images, on both image and patient level.

Results: Trained using 2072 colour fundus images, representing 42% of the original training data, the trained DL model achieved an AUC of 0.995, sensitivity and specificity of, respectively, 98.0% (CI 95.5%-99.4%) and 91% (CI 84.0%-96.0%), for glaucoma versus non-glaucoma patient referral.

Conclusions: These results demonstrate the benefits of deep learning for automated glaucoma detection based on optic disc-centred fundus images. The combined use of transfer and active learning in the medical community can optimize performance of DL models, while minimizing the labelling cost of domain-specific mavens. Glaucoma experts are able to make use of heat maps generated by the deep learning classifier to assess its decision, which seems to be related to inferior and superior neuroretinal rim (within ONH), and RNFL in superotemporal and inferotemporal zones (outside ONH).

Keywords: artificial intelligence; deep learning; fundus image; glaucoma detection.

© 2019 Acta Ophthalmologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.

References

    1. Ahn JM, Kim S, Ahn KS, Cho SH, Lee KB & Kim US (2018): A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PLoS ONE 13(11): e0207982.
    1. Asaoka R, Murata H, Iwase A & Araie M (2016): Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier. Ophthalmology 123(9): 1974-1980.
    1. Burlina PM, Joshi N, Pacheco KD, Freund DE, Kong J & Bressler NM (2018): Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration. JAMA Ophthalmol 136(12): 1359-1366.
    1. Burr J, Hernández R, Ramsay C et al. (2014): Is it worthwhile to conduct a randomized controlled trial of glaucoma screening in the United Kingdom? J Health Serv Res Policy 19(1): 42-51.
    1. Chen X, Xu Y, Kee Wong DW, Wong TY & Liu J (2015): Glaucoma detection based on deep convolutional neural network. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan 715-718.
    1. Christopher M, Belghith A, Bowd C et al. (2018): Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci Rep 8(1): 16685.
    1. Deng J, Dong W, Socher R, Li L-J, Li K & Fei-Fei L (2009): ImageNet: A Large-Scale Hierarchical Image Database. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL 248-255.
    1. Ervin AM, Boland MV, Myrowitz EH et al. (2012): Screening for Glaucoma: Comparative Effectiveness. Rockville (MD): Agency for Healthcare Research and Quality (US). (Comparative Effectiveness Reviews, No. 59.)
    1. Fu H, Cheng J, Xu Y, Wong DWK, Liu J & Cao X (2018): Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans Med Imaging 37(7): 1597-1605.
    1. Grassmann F, Mengelkamp J, Brandl C et al. (2018): A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography. Ophthalmology 125(9): 1410-1420.
    1. Gulshan V, Peng L, Coram M et al. (2016): Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22): 2402-2410.
    1. He K, Zhang X, Ren S & Sun J (2016): Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Piscataway, NJ 771-778.
    1. van der Heijden AA, Abramoff MD, Verbraak F, Hecke MV, Liem A & Nijpels G (2018): Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System. Acta Ophthalmol 96: 63-68.
    1. Jones E, Oliphant E & Peterson P (2001): SciPy: Open Source Scientific Tools for Python.
    1. Joshi AJ, Porikli F & Papanikolopoulos N (2009): Multi-class active learning for image classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, 2372-2379.
    1. Kapetanakis VV, Chan MPY, Foster PJ et al. (2006): Global variations and time trends in the prevalence of primary open angle glaucoma (POAG): a systematic review and meta-analysis. Br J Ophthalmol 100: 86-93.
    1. Kingma DP & Ba J. (2015): Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR).
    1. Kotikalapudi R (2017): keras-vis. .
    1. Li Z, He Y, Keel S, Meng W, Chang R & He M (2018a): Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125(8): 1199-1206.
    1. Li Z, Keel S, Liu C & He M. (2018b): Can artificial intelligence make screening faster, more accurate, and more accessible? Asia Pac J Ophthalmol (Phila) 7: 436-441.
    1. Maheshwari S, Pachori RB & Acharya UR (2017): Automated diagnosis of glaucoma using empirical wavelet transform and correntropy features extracted from fundus images. IEEE J Biomed Health Inform 21(3): 803-813.
    1. Matsopoulos GK, Asvestas PA, Delibasis KK, Mouravliansky NA & Zeyen TG (2008): Detection of glaucomatous change based on vessel shape analysis. Comput Med Imaging Graph 32(3): 183-192.
    1. Muhammad H, Fuchs TJ, De Cuir N et al. (2017): Hybrid deep learning on single wide-field optical coherence tomography scans accurately classifies glaucoma suspects. J Glaucoma 26(12): 1086-1094.
    1. Settles B (2009): Active Learning Literature Survey. Computer Sciences Technical Report 1648, University of Wisconsin-Madison.
    1. Shibata N, Tanito M, Mitsuhashi K et al. (2018): Development of a deep residual learning algorithm to screen for glaucoma from fundus photography. Sci Rep 8(1): 14665.
    1. Simonyan K, Vedaldi A & Zisserman A (2014): Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. Proceedings of the 2014 International Conference on Learning Representations (ICLR).
    1. Tham Y, Li X, Wong T, Quigley H, Aung T & Cheng C (2014): Global Prevalence of Glaucoma and Projections of Glaucoma Burden through 2040. Ophthalmology 121(11): 2081-2090.
    1. Ting DSW, Pasquale LR, Peng L et al. (2019): Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol 103 167-175.
    1. Tuulonen A. (2011): Cost-effectiveness of screening for open angle glaucoma in developed countries. Indian J Ophthalmol 59(Suppl1): S24-S30.
    1. Wen JC, Lee CS, Keane PA et al. (2018): Forecasting Future Humphrey Visual Fields Using Deep Learning. arXiv e-prints.

Source: PubMed

Спонсоры и соавторы

Заболевания

Медикаментозные вмешательства

Подписаться