The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation

We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of large-scale patches at multiple image-scales during training. Experiments on three fundus image datasets demonstrate that this approach achieves state-of-the-art results and can be implemented using a simple and efficient fully-convolutional network with a parameter count of less than 0.8M. Furthermore, we show that this framework - called VLight - avoids overfitting to specific training images and generalizes well across different datasets, which makes it highly suitable for real-world applications where robustness, accuracy as well as low inference time on high-resolution fundus images is required.

[1]  Xin Yang,et al.  Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation , 2018, IEEE Transactions on Biomedical Engineering.

[2]  Tianfu Wang,et al.  A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images , 2016, IEEE Transactions on Medical Imaging.

[3]  Md Zahangir Alom,et al.  Recurrent residual U-Net for medical image segmentation , 2019, Journal of medical imaging.

[4]  Martin Kraus,et al.  Automatic no-reference quality assessment for retinal fundus images using vessel segmentation , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

[5]  Yichen Wei,et al.  Simple Baselines for Human Pose Estimation and Tracking , 2018, ECCV.

[6]  Elisa Ricci,et al.  Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification , 2007, IEEE Transactions on Medical Imaging.

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

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

[9]  Xin Cai,et al.  Flattenet: A Simple and Versatile Framework for Dense Pixelwise Prediction , 2019, IEEE Access.

[10]  Anton van den Hengel,et al.  Wider or Deeper: Revisiting the ResNet Model for Visual Recognition , 2016, Pattern Recognit..

[11]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[13]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  R. Klein,et al.  Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the Atherosclerosis Risk in Communities Study. , 1999, Ophthalmology.

[15]  C. Paterson,et al.  Measuring retinal vessel tortuosity in 10-year-old children: validation of the Computer-Assisted Image Analysis of the Retina (CAIAR) program. , 2009, Investigative ophthalmology & visual science.

[16]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[17]  Américo Oliveira,et al.  Retinal vessel segmentation based on Fully Convolutional Neural Networks , 2018, Expert Syst. Appl..

[18]  Zhaoquan Cai,et al.  Domain adaptation for retinal vessel segmentation using asymmetrical maximum classifier discrepancy , 2019, ACM TUR-C.

[19]  Tuan D. Pham,et al.  DUNet: A deformable network for retinal vessel segmentation , 2018, Knowl. Based Syst..

[20]  Krzysztof Krawiec,et al.  Segmenting Retinal Blood Vessels With Deep Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[21]  Tillman Weyde,et al.  M2U-Net: Effective and Efficient Retinal Vessel Segmentation for Resource-Constrained Environments , 2018, ArXiv.

[22]  Qinmu Peng,et al.  Segmentation of retinal blood vessels using the radial projection and semi-supervised approach , 2011, Pattern Recognit..

[23]  R. Klein,et al.  Retinal vascular tortuosity, blood pressure, and cardiovascular risk factors. , 2011, Ophthalmology.

[24]  Tillman Weyde,et al.  M2U-Net: Effective and Efficient Retinal Vessel Segmentation for Real-World Applications , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[25]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[26]  Manuel G. Penedo,et al.  Personal authentication using digital retinal images , 2006, Pattern Analysis and Applications.

[27]  Marcos Ortega,et al.  Multimodal Registration of Retinal Images Using Domain-Specific Landmarks and Vessel Enhancement , 2018, KES.

[28]  Bunyarit Uyyanonvara,et al.  An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation , 2012, IEEE Transactions on Biomedical Engineering.

[29]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  M. Sonka,et al.  Retinal Imaging and Image Analysis. , 2010, IEEE transactions on medical imaging.

[31]  Matthew B. Blaschko,et al.  A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images , 2017, IEEE Transactions on Biomedical Engineering.

[32]  Roberto Marcondes Cesar Junior,et al.  Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification , 2005, ArXiv.

[33]  Nima Tajbakhsh,et al.  ErrorNet: Learning Error Representations from Limited Data to Improve Vascular Segmentation , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[34]  Sabalan Daneshvar,et al.  Retinal Image Registration Using Geometrical Features , 2013, Journal of Digital Imaging.

[35]  José Manuel Bravo,et al.  A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features , 2011, IEEE Transactions on Medical Imaging.

[36]  Juntang Zhuang,et al.  LadderNet: Multi-path networks based on U-Net for medical image segmentation , 2018, ArXiv.

[37]  Sang Jun Park,et al.  Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks , 2017, ArXiv.

[38]  Xing Zhang,et al.  Retinal Fundus Image Registration via Vascular Structure Graph Matching , 2010, Int. J. Biomed. Imaging.

[39]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

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

[41]  Luc Van Gool,et al.  Deep Retinal Image Understanding , 2016, MICCAI.

[42]  Stephen Lin,et al.  DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field , 2016, MICCAI.