CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging

TL;DR

CS2-Net is a novel deep learning model that effectively segments curvilinear structures in various medical images by employing self-attention mechanisms and specialized convolutional kernels, improving accuracy in clinical diagnostics.

Contribution

The paper introduces CS2-Net, a unified CNN with self-attention modules and boundary-focused convolutions for enhanced curvilinear structure segmentation across multiple medical imaging modalities.

Findings

Outperforms existing methods in accuracy across several datasets

Effectively captures complex curvilinear structures in 2D and 3D images

Demonstrates robustness in diverse medical imaging applications

Abstract

Automated detection of curvilinear structures, e.g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases. Precise measurement of the morphological changes of these curvilinear organ structures informs clinicians for understanding the mechanism, diagnosis, and treatment of e.g. cardiovascular, kidney, eye, lung, and neurological conditions. In this work, we propose a generic and unified convolution neural network for the segmentation of curvilinear structures and illustrate in several 2D/3D medical imaging modalities. We introduce a new curvilinear structure segmentation network (CS2-Net), which includes a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures. Two types of attention modules - spatial attention and channel attention - are utilized to enhance the inter-class discrimination and intra-class responsiveness, to further integrate local features with their global dependencies and normalization, adaptively. Furthermore, to facilitate the segmentation of curvilinear structures in medical images, we employ a 1x3 and a 3x1 convolutional kernel to capture boundary features. ...