CcNet: A cross-connected convolutional network for segmenting retinal vessels using multi-scale features

Abstract Retinal vessel segmentation (RVS) helps the diagnosis of diabetic retinopathy, which can cause visual impairment and even blindness. Some problems are hindering the application of automatic RVS, including accuracy, robustness and segmentation speed. In this paper, we propose a cross-connected convolutional neural network (CcNet) for the automatic segmentation of retinal vessel trees. In the CcNet, convolutional layers extract the features and predict the pixel classes according to those learned features. The CcNet is trained and tested with full green channel images directly. The cross connections between primary path and secondary path fuse the multi-level features. The experimental results on two publicly available datasets (DRIVE: Sn = 0.7625, Acc = 0.9528; STARE: Sn = 0.7709, Acc = 0.9633) are higher than those of most state-of-the-art methods. In the cross-training phase, CcNte’s accuracy fluctuations (△Accs) on DRIVE and STARE are 0.0042 and 0.007, respectively, which are relatively small compared with those of published methods. In addition, our algorithm has faster computing speed (0.063 s) than those listed algorithms using a GPU (graphics processing unit). These results reveal that our algorithm has potential in practical applications due to promising segmentation performances including advanced specificity, accuracy, robustness and fast processing speed.

[1]  Jie Yang,et al.  Patch-based fully convolutional neural network with skip connections for retinal blood vessel segmentation , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[2]  Xiaoyi Jiang,et al.  Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Ana Maria Mendonça,et al.  Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction , 2006, IEEE Transactions on Medical Imaging.

[4]  Le Zhang,et al.  A survey of randomized algorithms for training neural networks , 2016, Inf. Sci..

[5]  Lu Yang,et al.  Size-Invariant Fully Convolutional Neural Network for vessel segmentation of digital retinal images , 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

[6]  Bunyarit Uyyanonvara,et al.  An approach to localize the retinal blood vessels using bit planes and centerline detection , 2012, Comput. Methods Programs Biomed..

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

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

[9]  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.

[10]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[11]  Huisheng Zhang,et al.  A supervised method using convolutional neural networks for retinal vessel delineation , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[12]  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).

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

[14]  U. Rajendra Acharya,et al.  Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach , 2013, Knowl. Based Syst..

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

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

[17]  Zhuowen Tu,et al.  Deeply Supervised Salient Object Detection with Short Connections , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Christopher Joseph Pal,et al.  The Importance of Skip Connections in Biomedical Image Segmentation , 2016, LABELS/DLMIA@MICCAI.

[19]  Alan Wee-Chung Liew,et al.  General Retinal Vessel Segmentation Using Regularization-Based Multiconcavity Modeling , 2010, IEEE Transactions on Medical Imaging.

[20]  Robert W. Miller,et al.  Brain Tumor Segmentation in MRI Scans Using Deeply-Supervised Neural Networks , 2017, BrainLes@MICCAI.

[21]  George Azzopardi,et al.  Trainable COSFIRE filters for vessel delineation with application to retinal images , 2015, Medical Image Anal..

[22]  Boreom Lee,et al.  Development of automatic retinal vessel segmentation method in fundus images via convolutional neural networks , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[23]  Sonam Singh,et al.  A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation , 2016, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

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

[25]  Lu Yang,et al.  Efficient CNN-CRF Network for Retinal Image Segmentation , 2016, ICCSIP.

[26]  Bo Du,et al.  Deeply-supervised CNN for prostate segmentation , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

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

[28]  V. Shanmugam,et al.  Retinal blood vessel segmentation using an Extreme Learning Machine approach , 2013, 2013 IEEE Point-of-Care Healthcare Technologies (PHT).

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

[30]  Gongping Yang,et al.  Hierarchical retinal blood vessel segmentation based on feature and ensemble learning , 2015, Neurocomputing.

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

[32]  Bunyarit Uyyanonvara,et al.  Blood vessel segmentation methodologies in retinal images - A survey , 2012, Comput. Methods Programs Biomed..

[33]  Sven Loncaric,et al.  Retinal Vessel Segmentation using Deep Neural Networks , 2015, VISAPP.

[34]  Vasileios Megalooikonomou,et al.  Discriminative vessel segmentation in retinal images by fusing context-aware hybrid features , 2014, Machine Vision and Applications.

[35]  Yuan Zhang,et al.  Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function , 2018, Neurocomputing.

[36]  Li-Qun Xu,et al.  Convolutional Neural Network for Retinal Blood Vessel Segmentation , 2016, 2016 9th International Symposium on Computational Intelligence and Design (ISCID).

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

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

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

[40]  U. Rajendra Acharya,et al.  Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network , 2017, J. Comput. Sci..

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

[42]  Zhuowen Tu,et al.  Deeply-Supervised Nets , 2014, AISTATS.

[43]  Hao Chen,et al.  3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes , 2016, MICCAI.

[44]  Buket D. Barkana,et al.  Performance analysis of descriptive statistical features in retinal vessel segmentation via fuzzy logic, ANN, SVM, and classifier fusion , 2017, Knowl. Based Syst..