Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation

Retinal blood vessel segmentation influences a lot of blood vessel-related disorders such as diabetic retinopathy, hypertension, cardiovascular and cerebrovascular disorders, etc. It is found that vessel segmentation using a convolutional neural network (CNN) showed increased accuracy in feature extraction and vessel segmentation compared to the classical segmentation algorithms. CNN does not need any artificial handcrafted features to train the network. In the proposed deep neural network (DNN), a better pre-processing technique and multilevel/multiscale deep supervision (DS) layers are being incorporated for proper segmentation of retinal blood vessels. From the first four layers of the VGG-16 model, multilevel/multiscale deep supervision layers are formed by convolving vessel-specific Gaussian convolutions with two different scale initializations. These layers output the activation maps that are capable to learn vessel-specific features at multiple scales, levels, and depth. Furthermore, the receptive field of these maps is increased to obtain the symmetric feature maps that provide the refined blood vessel probability map. This map is completely free from the optic disc, boundaries, and non-vessel background. The segmented results are tested on Digital Retinal Images for Vessel Extraction (DRIVE), STructured Analysis of the Retina (STARE), High-Resolution Fundus (HRF), and real-world retinal datasets to evaluate its performance. This proposed model achieves better sensitivity values of 0.8282, 0.8979 and 0.8655 in DRIVE, STARE and HRF datasets with acceptable specificity and accuracy performance metrics.

[1]  Yong Yang,et al.  An Automatic Hybrid Method for Retinal Blood Vessel Extraction , 2008, Int. J. Appl. Math. Comput. Sci..

[2]  Sidan Du,et al.  Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation , 2019, Multimedia Tools and Applications.

[3]  Giri Babu Kande,et al.  Unsupervised Fuzzy Based Vessel Segmentation In Pathological Digital Fundus Images , 2010, Journal of Medical Systems.

[4]  Majid A. Al-Taee,et al.  Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis , 2018, Symmetry.

[5]  Matthew B. Blaschko,et al.  Learning Fully-Connected CRFs for Blood Vessel Segmentation in Retinal Images , 2014, MICCAI.

[6]  Charles V. Stewart,et al.  Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures , 2006, IEEE Transactions on Medical Imaging.

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

[8]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[9]  J. Reinhardt,et al.  Automated Method for Identification and Artery-Venous Classification of Vessel Trees in Retinal Vessel Networks , 2014, PloS one.

[10]  Heather E Moss,et al.  Retinal Vascular Changes are a Marker for Cerebral Vascular Diseases , 2015, Current Neurology and Neuroscience Reports.

[11]  Mohammed Al-Rawi,et al.  An improved matched filter for blood vessel detection of digital retinal images , 2007, Comput. Biol. Medicine.

[12]  Yongliang Chen,et al.  A Labeling-Free Approach to Supervising Deep Neural Networks for Retinal Blood Vessel Segmentation , 2017, ArXiv.

[13]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[14]  Karel J. Zuiderveld,et al.  Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[15]  Huazhu Fu,et al.  Retinal vessel segmentation via deep learning network and fully-connected conditional random fields , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[16]  Lei Zhang,et al.  Multi-level deep supervised networks for retinal vessel segmentation , 2017, International Journal of Computer Assisted Radiology and Surgery.

[17]  Keshab K. Parhi,et al.  Iterative Vessel Segmentation of Fundus Images , 2015, IEEE Transactions on Biomedical Engineering.

[18]  Khaled Elleithy,et al.  Retinal Vessels Segmentation Techniques and Algorithms: A Survey , 2018 .

[19]  Mingchen Gao,et al.  Deep vessel tracking: A generalized probabilistic approach via deep learning , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[20]  Susanto Rahardja,et al.  A Modified Dolph-Chebyshev Type II Function Matched Filter for Retinal Vessels Segmentation , 2018, Symmetry.

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

[22]  András Hajdu,et al.  Segmentation of retinal vessels by means of directional response vector similarity and region growing , 2015, Comput. Biol. Medicine.

[23]  Elli Angelopoulou,et al.  Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database , 2013, IET Image Process..

[24]  Xun Xu,et al.  Improving dense conditional random field for retinal vessel segmentation by discriminative feature learning and thin-vessel enhancement , 2017, Comput. Methods Programs Biomed..

[25]  Erik J. Bekkers,et al.  Retinal vessel delineation using a brain-inspired wavelet transform and random forest , 2017, Pattern Recognit..

[26]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[27]  Xiaoyi Jiang,et al.  A self-adaptive matched filter for retinal blood vessel detection , 2014, Machine Vision and Applications.

[28]  Xin Yang,et al.  A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.

[29]  Hai-Chao Han.  Twisted Blood Vessels: Symptoms, Etiology and Biomechanical Mechanisms , 2012, Journal of Vascular Research.

[30]  R. Klein,et al.  Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease, and mortality. , 2001, Survey of ophthalmology.

[31]  Halil Murat Ünver,et al.  Statistical Edge Detection and Circular Hough Transform for Optic Disk Localization , 2019, Applied Sciences.

[32]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[33]  Junhao Wen,et al.  Fundus Image Classification Using VGG-19 Architecture with PCA and SVD , 2018, Symmetry.

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

[35]  Bram van Ginneken,et al.  Comparative study of retinal vessel segmentation methods on a new publicly available database , 2004, SPIE Medical Imaging.

[36]  J. Alison Noble,et al.  Tramline and NP windows estimation for enhanced unsupervised retinal vessel segmentation , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[37]  Ke Chen,et al.  Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal Images , 2015, IEEE Transactions on Medical Imaging.

[38]  A. Osareh,et al.  Vessel Segmentation in Retinal Images Using Multi-scale Line Operator and K-Means Clustering , 2014, Journal of medical signals and sensors.

[39]  Bram van Ginneken,et al.  Automated Measurement of the Arteriolar-to-Venular Width Ratio in Digital Color Fundus Photographs , 2011, IEEE Transactions on Medical Imaging.

[40]  Shahab Aslani,et al.  A new supervised retinal vessel segmentation method based on robust hybrid features , 2016, Biomed. Signal Process. Control..

[41]  Yanhui Guo,et al.  A Retinal Vessel Detection Approach Based on Shearlet Transform and Indeterminacy Filtering on Fundus Images , 2017, Symmetry.

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

[43]  S. Nowilaty,et al.  Idiopathic Juxtafoveolar Retinal Telangiectasis: A Current Review , 2010, Middle East African journal of ophthalmology.

[44]  Anushikha Singh,et al.  Blood vessel inpainting based technique for efficient localization and segmentation of optic disc in digital fundus images , 2016, Biomed. Signal Process. Control..

[45]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[46]  Loretta Ichim,et al.  Intelligent Image Processing System for Detection and Segmentation of Regions of Interest in Retinal Images , 2018, Symmetry.

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

[48]  H. Taylor,et al.  World blindness: a 21st century perspective , 2001, The British journal of ophthalmology.

[49]  Mark Fisher,et al.  Retinal vessel segmentation using multi-scale textons derived from keypoints , 2015, Comput. Medical Imaging Graph..

[50]  Andrew Hunter,et al.  An Active Contour Model for Segmenting and Measuring Retinal Vessels , 2009, IEEE Transactions on Medical Imaging.

[51]  Rajeev Srivastava,et al.  Retinal blood vessels segmentation by using Gumbel probability distribution function based matched filter , 2016, Comput. Methods Programs Biomed..

[52]  Yudong Zhang,et al.  Cerebral micro‐bleeding identification based on a nine‐layer convolutional neural network with stochastic pooling , 2019, Concurr. Comput. Pract. Exp..

[53]  Yongtian Wang,et al.  Saliency driven vasculature segmentation with infinite perimeter active contour model , 2017, Neurocomputing.

[54]  Javad Rahebi,et al.  Retinal Blood Vessel Segmentation with Neural Network by Using Gray-Level Co-Occurrence Matrix-Based Features , 2014, Journal of Medical Systems.

[55]  David B. L. Bong,et al.  Detection of Neovascularization in Diabetic Retinopathy , 2012, Journal of Digital Imaging.