Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation

Optical coherence tomography (OCT) images of the retina provide a structural representation and give an insight into the pathological changes present in age-related macular degeneration (AMD). Due to the three-dimensionality and complexity of the images, manual analysis of pathological features is difficult, time-consuming, and prone to subjectivity. Computer analysis of 3D OCT images is necessary to enable automated quantitative measuring of the features, objectively and repeatedly. As supervised and semi-supervised learning-based automatic segmentation depends on the training data and quality of annotations, we have created a new database of annotated retinal OCT images – the AROI database. It consists of 1136 images with annotations for pathological changes (fluid accumulation and related findings) and basic structures (layers) in patients with AMD. Inter- and intra-observer errors have been calculated in order to enable the validation of developed algorithms in relation to human variability. Also, we have performed the automatic segmentation with standard U-net architecture and two state-of-the-art architectures for medical image segmentation to set a baseline for further algorithm development and to get insight into challenges for automatic segmentation. To facilitate and encourage further research in the field, we have made the AROI database openly available.

[1]  S. Hariprasad,et al.  Geographic atrophy: clinical impact and emerging treatments. , 2015, Ophthalmic surgery, lasers & imaging retina.

[2]  D. Hassabis,et al.  Predicting conversion to wet age-related macular degeneration using deep learning , 2020, Nature Medicine.

[3]  Judy E. Kim,et al.  Current Best Clinical Practices—Management of Neovascular AMD , 2017 .

[4]  Xu Sun,et al.  Adaptive Gradient Methods with Dynamic Bound of Learning Rate , 2019, ICLR.

[5]  Christian Simader,et al.  Quantitative comparison of macular segmentation performance using identical retinal regions across multiple spectral-domain optical coherence tomography instruments , 2015, British Journal of Ophthalmology.

[6]  Bianca S. Gerendas,et al.  Prediction of Anti-VEGF Treatment Requirements in Neovascular AMD Using a Machine Learning Approach. , 2017, Investigative ophthalmology & visual science.

[7]  Bianca S. Gerendas,et al.  Joint retinal layer and fluid segmentation in OCT scans of eyes with severe macular edema using unsupervised representation and auto-context. , 2017, Biomedical optics express.

[8]  Geraint Rees,et al.  Clinically applicable deep learning for diagnosis and referral in retinal disease , 2018, Nature Medicine.

[9]  A. Adamis,et al.  Building on the success of anti-vascular endothelial growth factor therapy: a vision for the next decade , 2020, Eye.

[10]  R. T. Smith,et al.  Geographic Atrophy and Choroidal Neovascularization in the Same Eye: A Review , 2016, Ophthalmic Research.

[11]  Hyung Chan Kim,et al.  Three-Dimensional Analysis of Morphologic Changes and Visual Outcomes in Neovascular Age-Related Macular Degeneration. , 2017, Investigative ophthalmology & visual science.

[12]  Zubin Mishra,et al.  Automated Retinal Layer Segmentation Using Graph-based Algorithm Incorporating Deep-learning-derived Information , 2020, Scientific Reports.

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Christian Simader,et al.  Intraretinal cysts are the most relevant prognostic biomarker in neovascular age-related macular degeneration independent of the therapeutic strategy , 2014, British Journal of Ophthalmology.

[15]  Keshab K. Parhi,et al.  RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge , 2019, IEEE Transactions on Medical Imaging.

[16]  J. F. Cullen Retinal Vascular Disease , 1968, Scottish medical journal.

[17]  Suhwan Lee,et al.  Long-Term Visual/Anatomic Outcome in Patients with Fovea-Involving Fibrovascular Pigment Epithelium Detachment Presenting Choroidal Neovascularization on Optical Coherence Tomography Angiography , 2020, Journal of clinical medicine.

[18]  S. Sadda,et al.  Proposed lexicon for anatomic landmarks in normal posterior segment spectral-domain optical coherence tomography: the IN•OCT consensus. , 2014, Ophthalmology.

[19]  Shenghua Gao,et al.  CE-Net: Context Encoder Network for 2D Medical Image Segmentation , 2019, IEEE Transactions on Medical Imaging.

[20]  U. Schmidt-Erfurth,et al.  Application of Automated Quantification of Fluid Volumes to Anti-VEGF Therapy of Neovascular Age-Related Macular Degeneration. , 2020, Ophthalmology.

[21]  Pearse A. Keane,et al.  A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability. , 2020, The Lancet. Digital health.

[22]  Sina Farsiu,et al.  Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema. , 2015, Biomedical optics express.

[23]  José Ignacio Orlando,et al.  U2-Net: A Bayesian U-Net Model With Epistemic Uncertainty Feedback For Photoreceptor Layer Segmentation In Pathological OCT Scans , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[24]  David J. Wilson,et al.  Consensus Nomenclature for Reporting Neovascular Age-Related Macular Degeneration Data: Consensus on Neovascular Age-Related Macular Degeneration Nomenclature Study Group. , 2019, Ophthalmology.

[25]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[26]  A. Ramé [Age-related macular degeneration]. , 2006, Revue de l'infirmiere.

[27]  Hao Wei,et al.  The Segmentation of Retinal Layer and Fluid in SD-OCT Images Using Mutex Dice Loss Based Fully Convolutional Networks , 2020, IEEE Access.

[28]  Klaus H. Maier-Hein,et al.  Automated Design of Deep Learning Methods for Biomedical Image Segmentation , 2019 .

[29]  Bianca S. Gerendas,et al.  Correlation of 3-Dimensionally Quantified Intraretinal and Subretinal Fluid With Visual Acuity in Neovascular Age-Related Macular Degeneration. , 2016, JAMA ophthalmology.

[30]  S. Priglinger,et al.  Impact of Sub-Retinal Fluid on the Long-Term Incidence of Macular Atrophy in Neovascular Age-related Macular Degeneration under Treat & Extend Anti-Vascular Endothelial Growth Factor Inhibitors , 2020, Scientific Reports.

[31]  E. Souied,et al.  Retinal Vascular Disease , 2020 .

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

[33]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

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

[35]  Jens Petersen,et al.  nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation , 2020, Nature Methods.

[36]  P. Keane,et al.  Relationship between Visual Acuity and Spectral Domain Optical Coherence Tomography Retinal Parameters in Neovascular Age-Related Macular Degeneration , 2013, Ophthalmologica.

[37]  R. Klein,et al.  Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis. , 2014, The Lancet. Global health.

[38]  Yu Qiao,et al.  S-D Net: Joint Segmentation and Diagnosis Revealing the Diagnostic Significance of Using Entire RNFL Thickness in Glaucoma , 2018 .

[39]  R. Klein,et al.  Prevalence of age-related maculopathy. The Beaver Dam Eye Study. , 1992, Ophthalmology.

[40]  Glenn J Jaffe,et al.  Subretinal Hyperreflective Material in the Comparison of Age-Related Macular Degeneration Treatments Trials. , 2015, Ophthalmology.

[41]  L. Labree,et al.  Errors in retinal thickness measurements obtained by optical coherence tomography. , 2006, Ophthalmology.

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

[43]  Qingge Ji,et al.  MDAN-UNet: Multi-Scale and Dual Attention Enhanced Nested U-Net Architecture for Segmentation of Optical Coherence Tomography Images , 2020, Algorithms.

[44]  Qingyu Chen,et al.  Predicting risk of late age-related macular degeneration using deep learning , 2020, npj Digital Medicine.

[45]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.