Clinically applicable deep learning for diagnosis and referral in retinal disease

The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.A novel deep learning architecture performs device-independent tissue segmentation of clinical 3D retinal images followed by separate diagnostic classification that meets or exceeds human expert clinical diagnoses of retinal disease.

[1]  Yue Wu,et al.  Deep-learning based, automated segmentation of macular edema in optical coherence tomography. , 2017, Biomedical optics express.

[2]  Sascha Fauser,et al.  Delay between medical indication to anti-VEGF treatment in age-related macular degeneration can result in a loss of visual acuity , 2011, Graefe's Archive for Clinical and Experimental Ophthalmology.

[3]  ALICJA R. RUDNICKA,et al.  Incidence of Late-Stage Age-Related Macular Degeneration in American Whites: Systematic Review and Meta-analysis. , 2015, American journal of ophthalmology.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2015, ICLR.

[5]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[6]  U. Schmidt-Erfurth,et al.  Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning. , 2017, Ophthalmology.

[7]  Adnan Tufail,et al.  Evaluation of age-related macular degeneration with optical coherence tomography. , 2012, Survey of ophthalmology.

[8]  Nassir Navab,et al.  ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network , 2017, Biomedical optics express.

[9]  Olaf Ronneberger Invited Talk: U-Net Convolutional Networks for Biomedical Image Segmentation , 2017, Bildverarbeitung für die Medizin.

[10]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[11]  J. Kempen,et al.  Magnitude, temporal trends, and projections of the global prevalence of blindness and distance and near vision impairment: a systematic review and meta-analysis. , 2017, The Lancet. Global health.

[12]  B Foot,et al.  Surveillance of sight loss due to delay in ophthalmic treatment or review: frequency, cause and outcome , 2017, Eye.

[13]  Roger S. Anderson,et al.  Human Factor and Usability Testing of a Binocular Optical Coherence Tomography System , 2017, Translational vision science & technology.

[14]  U. Schmidt-Erfurth,et al.  A paradigm shift in imaging biomarkers in neovascular age-related macular degeneration , 2016, Progress in Retinal and Eye Research.

[15]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[16]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[17]  Debjani Chakraborty,et al.  Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration. , 2017, Biomedical optics express.

[18]  Mirza Faisal Beg,et al.  Retinal Fluid Segmentation and Detection in Optical Coherence Tomography Images using Fully Convolutional Neural Network , 2017, ArXiv.

[19]  Mark B Horton,et al.  A modeled economic analysis of a digital tele-ophthalmology system as used by three federal health care agencies for detecting proliferative diabetic retinopathy. , 2005, Telemedicine journal and e-health : the official journal of the American Telemedicine Association.

[20]  William J Feuer,et al.  Anatomic Clinical Trial Endpoints for Nonexudative Age-Related Macular Degeneration. , 2016, Ophthalmology.

[21]  J. Fujimoto,et al.  Optical Coherence Tomography , 1991 .

[22]  S A Vernon,et al.  How to defuse a demographic time bomb: the way forward? , 2017, Eye.

[23]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Davide Castelvecchi,et al.  Can we open the black box of AI? , 2016, Nature.

[25]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[26]  Geraint Rees,et al.  Automated analysis of retinal imaging using machine learning techniques for computer vision , 2016, F1000Research.

[27]  Glenn J Jaffe,et al.  Comparison of optical coherence tomography assessments in the comparison of age-related macular degeneration treatments trials. , 2014, Ophthalmology.

[28]  U. Schmidt-Erfurth,et al.  A view of the current and future role of optical coherence tomography in the management of age-related macular degeneration , 2017, Eye.

[29]  Richard Wormald,et al.  The estimated prevalence and incidence of late stage age related macular degeneration in the UK , 2012, British Journal of Ophthalmology.

[30]  U. Schmidt-Erfurth,et al.  Machine Learning to Analyze the Prognostic Value of Current Imaging Biomarkers in Neovascular Age-Related Macular Degeneration. , 2018, Ophthalmology. Retina.

[31]  Chong Wang,et al.  Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search. , 2017, Biomedical optics express.

[32]  Pedram Hamrah,et al.  Decade-Long Profile of Imaging Biomarker Use in Ophthalmic Clinical Trials. , 2017, Investigative ophthalmology & visual science.

[33]  Raphael Sznitman,et al.  RetiNet: Automatic AMD identification in OCT volumetric data , 2016, ArXiv.

[34]  Sina Farsiu,et al.  Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. , 2014, Biomedical optics express.

[35]  Srinivas R Sadda,et al.  Predicting visual outcomes for macular disease using optical coherence tomography. , 2011, Saudi journal of ophthalmology : official journal of the Saudi Ophthalmological Society.

[36]  M. Delgado-Rodríguez,et al.  Systematic review and meta-analysis. , 2017, Medicina intensiva.

[37]  Aaron Y. Lee,et al.  Deep Learning Is Effective for Classifying Normal versus Age-Related Macular Degeneration Optical Coherence Tomography Images , 2017 .

[38]  Geraint Rees,et al.  Automated analysis of retinal imaging using machine learning techniques for computer vision. , 2016, F1000Research.

[39]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Eric L Yuan,et al.  Quantitative classification of eyes with and without intermediate age-related macular degeneration using optical coherence tomography. , 2014, Ophthalmology.

[41]  L Arias,et al.  Delay in treating age-related macular degeneration in Spain is associated with progressive vision loss , 2009, Eye.