Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2019

Abstract

Curvilinear structures are frequently observed in various images in different forms, such as blood vessels or neuronal boundaries in biomedical images. In this paper, we propose a novel curvilinear structure segmentation approach using context-aware spatio-recurrent networks. Instead of directly segmenting the whole image or densely segmenting fixed-sized local patches, our method recurrently samples patches with varied scales from the target image with learned policy and processes them locally, which is similar to the behavior of changing retinal fixations in the human visual system and it is beneficial for capturing the multi-scale or hierarchical modality of the complex curvilinear structures. In specific, the policy of choosing local patches is attentively learned based on the contextual information of the image and the historical sampling experience. In this way, with more patches sampled and refined, the segmentation of the whole image can be progressively improved. To validate our approach, comparison experiments on different types of image data are conducted and the sampling procedures for exemplar images are illustrated. We demonstrate that our method achieves the state-of-the-art performance in public datasets.

Keywords

Contextual information, Curvilinear structures, Grouping and Shape, Human Visual System, Medical, Recurrent networks, Sampling procedures, State-of-the-art performance

Discipline

Databases and Information Systems

Research Areas

Information Systems and Management

Publication

Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019 June 16-20

First Page

12640

Last Page

12649

ISBN

9781728132938

Identifier

10.1109/CVPR.2019.01293

Publisher

IEEE

City or Country

New Jersey

Additional URL

https://doi.org/10.1109/CVPR.2019.01293

Share

COinS