BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation

by   Yanda Meng, et al.

Segmentation is an essential operation of image processing. The convolution operation suffers from a limited receptive field, while global modelling is fundamental to segmentation tasks. In this paper, we apply graph convolution into the segmentation task and propose an improved Laplacian. Different from existing methods, our Laplacian is data-dependent, and we introduce two attention diagonal matrices to learn a better vertex relationship. In addition, it takes advantage of both region and boundary information when performing graph-based information propagation. Specifically, we model and reason about the boundary-aware region-wise correlations of different classes through learning graph representations, which is capable of manipulating long range semantic reasoning across various regions with the spatial enhancement along the object's boundary. Our model is well-suited to obtain global semantic region information while also accommodates local spatial boundary characteristics simultaneously. Experiments on two types of challenging datasets demonstrate that our method outperforms the state-of-the-art approaches on the segmentation of polyps in colonoscopy images and of the optic disc and optic cup in colour fundus images.


page 1

page 3

page 8


Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

The convolution operation suffers from a limited receptive filed, while ...

Boundary-aware Graph Reasoning for Semantic Segmentation

In this paper, we propose a Boundary-aware Graph Reasoning (BGR) module ...

DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation

Transformer-based models have been widely demonstrated to be successful ...

Boundary-Aware Feature Propagation for Scene Segmentation

In this work, we address the challenging issue of scene segmentation. To...

Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation

The transformer-based semantic segmentation approaches, which divide the...

FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images

Computed Tomography (CT) based precise prostate segmentation for treatme...

TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation

Regular pavement inspection plays a significant role in road maintenance...

Please sign up or login with your details

Forgot password? Click here to reset