Deep Vessel Segmentation By Learning Graphical Connectivity

Abstract

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.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Semi-Supervised Classification with Graph Convolutional Networks
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Inductive Representation Learning on Large Graphs
• Geometric deep learning: going beyond Euclidean data
• Conditional Random Fields as Recurrent Neural Networks
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification
• Deep Convolutional Networks on Graph-Structured Data
• Learning Convolutional Neural Networks for Graphs
• Retinal vessel segmentation based on Fully Convolutional Neural Networks
• Situation Recognition with Graph Neural Networks
• Extraction of Coronary Vessels in Fluoroscopic X-Ray Sequences Using Vessel Correspondence Optimization
• Person Re-identification with Deep Similarity-Guided Graph Neural Network
• Extraction of Airways using Graph Neural Networks
• Iterative Deep Learning for Road Topology Extraction

Cited by in corpus (17)

• Medical Image Segmentation Using Deep Learning: A Survey
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• ELEMENT: Multi-Modal Retinal Vessel Segmentation Based on a Coupled Region Growing and Machine Learning Approach
• A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography
• CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging
• DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences
• Zoom in to where it matters: a hierarchical graph based model for mammogram analysis
• Deep Learning Methods for Retinal Blood Vessel Segmentation: Evaluation on Images with Retinopathy of Prematurity
• OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation
• Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images
• The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models
• Semi-overcomplete convolutional auto-encoder embedding as shape priors for deep vessel segmentation
• Local-sensitive connectivity filter (ls-cf): A post-processing unsupervised improvement of the frangi, hessian and vesselness filters for multimodal vessel segmentation
• Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images
• VC-Net: Deep Volume-Composition Networks for Segmentation and Visualization of Highly Sparse and Noisy Image Data
• Learning-Based Algorithms for Vessel Tracking: A Review
• Automated airway segmentation by learning graphical structure