Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images

TL;DR

This paper introduces a deep CNN with global guidance and boundary detection modules to improve breast lesion segmentation in ultrasound images, effectively capturing long-range dependencies and enhancing boundary accuracy.

Contribution

The proposed network incorporates a global guidance block and boundary detection modules, advancing ultrasound lesion segmentation by leveraging multi-layer features and boundary information.

Findings

Outperforms existing segmentation methods on public and collected datasets.

Effectively captures long-range dependencies in ultrasound images.

Improves boundary quality of segmentation results.

Abstract

Automatic breast lesion segmentation in ultrasound helps to diagnose breast cancer, which is one of the dreadful diseases that affect women globally. Segmenting breast regions accurately from ultrasound image is a challenging task due to the inherent speckle artifacts, blurry breast lesion boundaries, and inhomogeneous intensity distributions inside the breast lesion regions. Recently, convolutional neural networks (CNNs) have demonstrated remarkable results in medical image segmentation tasks. However, the convolutional operations in a CNN often focus on local regions, which suffer from limited capabilities in capturing long-range dependencies of the input ultrasound image, resulting in degraded breast lesion segmentation accuracy. In this paper, we develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection (BD) modules for boosting the breast ultrasound lesion segmentation. The GGB utilizes the multi-layer integrated feature map as a guidance information to learn the long-range non-local dependencies from both spatial and channel domains. The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement. Experimental results on a public dataset and a collected dataset show that our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation. Moreover, we also show the application of our network on the ultrasound prostate segmentation, in which our method better identifies prostate regions than state-of-the-art networks.