Blood Vessels Segmentation by Using CDNet

Blood vessel segmentation is one of the important premises for the analysis in Medical Imaging. In this paper, a new operation block called segmentation block is designed for learning the finer feature maps and keeping the resolution invariant. Based on segmentation block, a new U-net-like model called CDNet is proposed for blood vessel segmentation task and achieves precise segmentation results. The novel model has been trained and tested in the retinal dataset called DRIVE and achieved the highest scores in accuracy (0.9633), sensitivity (0.8158) and AUC (0.9841) comparing with other methods. Our experimental results indicate that the segmentation block performs better in feature learning and CDNet can achieve a good performance in blood vessels segmentation task.

[1]  Yann LeCun,et al.  Multi-Digit Recognition Using a Space Displacement Neural Network , 1991, NIPS.

[2]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[6]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[8]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

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

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

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

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

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

[14]  Hamid Reza Pourreza,et al.  A novel method for retinal exudate segmentation using signal separation algorithm , 2016, Comput. Methods Programs Biomed..

[15]  A. Hofman,et al.  Retinal vessel diameters and risk of stroke , 2006, Neurology.

[16]  John C. Platt,et al.  Postal Address Block Location Using a Convolutional Locator Network , 1993, NIPS.

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

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

[19]  Keshab K. Parhi,et al.  Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification , 2015, IEEE Journal of Biomedical and Health Informatics.

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

[21]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[22]  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).

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

[24]  Edgardo Manuel Felipe Riverón,et al.  Regular paper , 2005, 2005 IEEE/PES Transmission & Distribution Conference & Exposition: Asia and Pacific.