MAU-Net: A Retinal Vessels Segmentation Method

Detailed extraction of retinal vessel morphology is of great significance in many clinical applications. In this paper, we propose a retinal image segmentation method, called MAU-Net, which is based on the U-net structure and takes advantages of both modulated deformable convolution and dual attention modules to realize vessels segmentation. Specifically, based on the classic U-shaped architecture, our network introduces the Modulated Deformable Convolutional (MDC) block as encoding and decoding unit to model vessels with various shapes and deformations. In addition, in order to obtain better feature presentations, we aggregate the outputs of dual attention modules: the position attention module (PAM) and channel attention module (CAM). On three publicly available datasets: DRIVE, STARE and CHASEDB1, we have achieved superior performance to other algorithms. Quantitative and qualitative experimental results show that our MAU-Net can effectively and accurately accomplish the retinal vessels segmentation task.

[1]  Vincent Lepetit,et al.  Supervised Feature Learning for Curvilinear Structure Segmentation , 2013, MICCAI.

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

[3]  Jeny Rajan,et al.  Automated Method for Retinal Artery/Vein Separation via Graph Search Metaheuristic Approach , 2019, IEEE Transactions on Image Processing.

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

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

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

[7]  Nashwa El-Bendary,et al.  Retinal Blood Vessel Segmentation Approach Based on Mathematical Morphology , 2015 .

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

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

[10]  Patrick van der Smagt,et al.  CNN-based Segmentation of Medical Imaging Data , 2017, ArXiv.

[11]  Stephen Lin,et al.  Deformable ConvNets V2: More Deformable, Better Results , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[13]  Li Cheng,et al.  Learning to Boost Filamentary Structure Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Jun Fu,et al.  Dual Attention Network for Scene Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).