Automated segmentaiton and classification of arterioles and venules using Cascading Dilated Convolutional Neural Networks

The change of retinal vasculature is an early sign of many vascular and systematic diseases, such as diabetes and hypertension. Different behaviors of retinal arterioles and venules form an important metric to measure the disease severity. Therefore, an accurate classification of arterioles and venules is of great necessity. In this work, we propose a novel architecture of deep convolutional neural network for segmenting and classifying arterioles and venules on retinal fundus images. This network takes the original color fundus image as inputs and multi-class labels as outputs. We adopt the encoding-decoding structure (Unet) as the backbone network of our proposed model. To improve the classification accuracy, we develop a special encoding path that couples InceptionV4 modules and Cascading Dilated Convolutions (CDCs) on top of the backbone network. The model is thus able to extract and fuse high-level semantic features from multi-scale receptive fields. The proposed method has outperformed the previous state-of-the-art method on DRIVE dataset with an accuracy of 0.955 $\pm$ 0.002.

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

[2]  Feng Xu,et al.  Smartphone-Based Accurate Analysis of Retinal Vasculature towards Point-of-Care Diagnostics , 2016, Scientific Reports.

[3]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Daniel Kondermann,et al.  Blood vessel classification into arteries and veins in retinal images , 2007, SPIE Medical Imaging.

[5]  Wei Liu,et al.  ParseNet: Looking Wider to See Better , 2015, ArXiv.

[6]  Tao Tan,et al.  Simultaneous arteriole and venule segmentation with domain-specific loss function on a new public database. , 2018, Biomedical optics express.

[7]  Michael D. Abràmoff,et al.  An improved arteriovenous classification method for the early diagnostics of various diseases in retinal image , 2017, Comput. Methods Programs Biomed..

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

[9]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[10]  Alicja R. Rudnicka,et al.  Automated arteriole and venule classification using deep learning for retinal images from the UK Biobank cohort , 2017, Comput. Biol. Medicine.

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

[12]  Josien P. W. Pluim,et al.  Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores , 2016, IEEE Transactions on Medical Imaging.

[13]  Muhammad Moazam Fraz,et al.  Arterioles and Venules Classification in Retinal Images Using Fully Convolutional Deep Neural Network , 2018, ICIAR.