Effect of Altered OCT Image Quality on Deep Learning Boundary Segmentation

Deep learning methods provide a platform to segment boundaries within the retina and choroid in OCT images of the posterior eye, with the ultimate goal of having a robust model that works well across a wide range of different datasets. However, since most studies of deep learning methods use datasets exhibiting similar image quality for both training and evaluation, the effect of varied image quality on such methods is not normally explored in the context of OCT image segmentation. An understanding of the effects of image quality factors is vital to determine the robustness of the methods and their ability to be applied in clinical practice where images exhibiting a range of different qualities are encountered. This study examined a range of factors that can affect standard OCT image quality and determined how and why the performance of an existing neural network based segmentation method can subsequently degrade as a result. Three image quality factors (noise, contrast reduction, and gamma correction) all had a negative impact upon performance, while more robust performance was maintained in the presence of both JPEG and JPEG2000 image compression. Improving the method’s robustness to each of these degradations is also demonstrated with marked performance improvements identified by applying a fine-tuning approach to the network. This study improves our understanding of the effect of OCT image degradation on neural network performance, the effect that fine-tuning with poor-image quality data has on the network and highlights the benefit and importance of training resilient models using data augmentation.

[1]  J. Schmitt,et al.  Speckle in optical coherence tomography. , 1999, Journal of biomedical optics.

[2]  Kim L. Boyer,et al.  Retinal thickness measurements from optical coherence tomography using a Markov boundary model , 2001, IEEE Transactions on Medical Imaging.

[3]  M. V. D. van der Linden,et al.  Influence of cataract on optical coherence tomography image quality and retinal thickness , 2006, British Journal of Ophthalmology.

[4]  Xiaodong Wu,et al.  Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Gábor Márk Somfai,et al.  Evaluation of potential image acquisition pitfalls during optical coherence tomography and their influence on retinal image segmentation. , 2007, Journal of biomedical optics.

[6]  H. M. Salinas,et al.  Comparison of PDE-Based Nonlinear Diffusion Approaches for Image Enhancement and Denoising in Optical Coherence Tomography , 2007, IEEE Transactions on Medical Imaging.

[7]  R. Spaide,et al.  A pilot study of enhanced depth imaging optical coherence tomography of the choroid in normal eyes. , 2009, American journal of ophthalmology.

[8]  Robert N Weinreb,et al.  Effect of image quality on tissue thickness measurements obtained with spectral domain-optical coherence tomography. , 2009, Optics express.

[9]  Vikram S Brar,et al.  Normative data for macular thickness by high-definition spectral-domain optical coherence tomography (spectralis). , 2009, American journal of ophthalmology.

[10]  Masanori Hangai,et al.  Three-dimensional imaging of the macular retinal nerve fiber layer in glaucoma with spectral-domain optical coherence tomography. , 2010, Investigative ophthalmology & visual science.

[11]  Joseph A. Izatt,et al.  Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation , 2010, Optics express.

[12]  J. Hornegger,et al.  Retinal Nerve Fiber Layer Segmentation on FD-OCT Scans of Normal Subjects and Glaucoma Patients , 2010, Biomedical optics express.

[13]  Ghassan Hamarneh,et al.  Segmentation of Intra-Retinal Layers From Optical Coherence Tomography Images Using an Active Contour Approach , 2011, IEEE Transactions on Medical Imaging.

[14]  Wolfgang Drexler,et al.  Retinal and choroidal thickness in early age-related macular degeneration. , 2011, American journal of ophthalmology.

[15]  David Alonso-Caneiro,et al.  Speckle reduction in optical coherence tomography imaging by affine-motion image registration. , 2011, Journal of biomedical optics.

[16]  Scott A Read,et al.  Diurnal variations in axial length, choroidal thickness, intraocular pressure, and ocular biometrics. , 2011, Investigative ophthalmology & visual science.

[17]  Elise Harb,et al.  Factors Associated with Macular Thickness in the COMET Myopic Cohort , 2012, Optometry and vision science : official publication of the American Academy of Optometry.

[18]  David Alonso-Caneiro,et al.  Diurnal Variation of Retinal Thickness with Spectral Domain OCT , 2012, Optometry and vision science : official publication of the American Academy of Optometry.

[19]  Gadi Wollstein,et al.  OCT for glaucoma diagnosis, screening and detection of glaucoma progression , 2013, British Journal of Ophthalmology.

[20]  Milan Sonka,et al.  Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map , 2012, Medical Image Anal..

[21]  David Alonso-Caneiro,et al.  Choroidal thickness in myopic and nonmyopic children assessed with enhanced depth imaging optical coherence tomography. , 2013, Investigative ophthalmology & visual science.

[22]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[23]  Erika Tátrai,et al.  The effect of incorrect scanning distance on boundary detection errors and macular thickness measurements by spectral domain optical coherence tomography: a cross sectional study , 2014, BMC Ophthalmology.

[24]  Sina Farsiu,et al.  Automatic segmentation of up to ten layer boundaries in SD-OCT images of the mouse retina with and without missing layers due to pathology. , 2014, Biomedical optics express.

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

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

[27]  David Alonso-Caneiro,et al.  Longitudinal changes in choroidal thickness and eye growth in childhood. , 2015, Investigative ophthalmology & visual science.

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

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

[31]  Lina J. Karam,et al.  Understanding how image quality affects deep neural networks , 2016, 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX).

[32]  João Batista Neto,et al.  An empirical study on the effects of different types of noise in image classification tasks , 2016, ArXiv.

[33]  Qiang Chen,et al.  Automated geographic atrophy segmentation for SD-OCT images using region-based C-V model via local similarity factor. , 2016, Biomedical optics express.

[34]  Jyotirmoy Chatterjee,et al.  Learning layer-specific edges for segmenting retinal layers with large deformations. , 2016, Biomedical optics express.

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

[36]  Xinjian Chen,et al.  An automated framework for 3D serous pigment epithelium detachment segmentation in SD-OCT images , 2016, Scientific Reports.

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

[38]  Thomas Theelen,et al.  Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks. , 2017, Biomedical optics express.

[39]  Yupeng Xu,et al.  Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy. , 2017, Biomedical optics express.

[40]  Min Chen,et al.  Automated Segmentation of the Choroid in EDI-OCT Images with Retinal Pathology Using Convolution Neural Networks , 2017, FIFI/OMIA@MICCAI.

[41]  David Alonso-Caneiro,et al.  Longitudinal changes in macular retinal layer thickness in pediatric populations: Myopic vs non-myopic eyes , 2017, PloS one.

[42]  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.

[43]  Omar Fawzi,et al.  Robustness of classifiers to uniform $\ell_p$ and Gaussian noise , 2018, AISTATS.

[44]  Sina Farsiu,et al.  Deep longitudinal transfer learning-based automatic segmentation of photoreceptor ellipsoid zone defects on optical coherence tomography images of macular telangiectasia type 2 , 2018, Biomedical optics express.

[45]  Yuta Wakayama,et al.  Comparison of medical image classification accuracy among three machine learning methods. , 2018, Journal of X-ray science and technology.

[46]  David Alonso-Caneiro,et al.  Automatic Retinal and Choroidal Boundary Segmentation in OCT Images Using Patch-Based Supervised Machine Learning Methods , 2018, ACCV Workshops.

[47]  Leixin Zhou,et al.  Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images , 2018, Biomedical optics express.

[48]  Xinjian Chen,et al.  Automatic Segmentation of Retinal Layer in OCT Images With Choroidal Neovascularization , 2018, IEEE Transactions on Image Processing.

[49]  David Alonso-Caneiro,et al.  Effect of patch size and network architecture on a convolutional neural network approach for automatic segmentation of OCT retinal layers. , 2018, Biomedical optics express.

[50]  Saumik Bhattacharya,et al.  Effects of Degradations on Deep Neural Network Architectures , 2018, ArXiv.

[51]  Daniel S. Weller,et al.  Image quality affects deep learning reconstruction of MRI , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[52]  David Alonso-Caneiro,et al.  Automatic segmentation of OCT retinal boundaries using recurrent neural networks and graph search. , 2018, Biomedical optics express.

[53]  Xiaoming Liu,et al.  Semi-Supervised Automatic Segmentation of Layer and Fluid Region in Retinal Optical Coherence Tomography Images Using Adversarial Learning , 2019, IEEE Access.

[54]  Dong Liu,et al.  Automated Layer Segmentation of Retinal Optical Coherence Tomography Images Using a Deep Feature Enhanced Structured Random Forests Classifier , 2019, IEEE Journal of Biomedical and Health Informatics.

[55]  Sohini Roy Chowdhury,et al.  Segmentation of Intra-Retinal Cysts From Optical Coherence Tomography Images Using a Fully Convolutional Neural Network Model , 2019, IEEE Journal of Biomedical and Health Informatics.

[56]  Karl R. Gegenfurtner,et al.  Manifestation of Image Contrast in Deep Networks , 2019, ArXiv.

[57]  David Alonso-Caneiro,et al.  Automatic choroidal segmentation in OCT images using supervised deep learning methods , 2019, Scientific Reports.