Deep Vessel Segmentation By Learning Graphical Connectivity

6 Jun 2018  ·  Seung Yeon Shin, Soochahn Lee, Il Dong Yun, Kyoung Mu Lee ·

We propose a novel deep-learning-based system for vessel segmentation. Existing methods using CNNs have mostly relied on local appearances learned on the regular image grid, without considering the graphical structure of vessel shape. To address this, we incorporate a graph convolutional network into a unified CNN architecture, where the final segmentation is inferred by combining the different types of features. The proposed method can be applied to expand any type of CNN-based vessel segmentation method to enhance the performance. Experiments show that the proposed method outperforms the current state-of-the-art methods on two retinal image datasets as well as a coronary artery X-ray angiography dataset.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Retinal Vessel Segmentation CHASE_DB1 VGN F1 score 0.8034 # 8
AUC 0.9830 # 7
Retinal Vessel Segmentation DRIVE VGN F1 score 0.8263 # 4
AUC 0.9802 # 6
Retinal Vessel Segmentation HRF VGN AUC 0.9838 # 1
F1 score 0.8151 # 1
Retinal Vessel Segmentation STARE VGN F1 score 0.8429 # 2
AUC 0.9877 # 3

Methods


No methods listed for this paper. Add relevant methods here