BAGNet: Bidirectional Aware Guidance Network for Malignant Breast lesions Segmentation

TL;DR

This paper introduces BAGNet, a novel network that improves malignant breast lesion segmentation in ultrasound images by effectively capturing global and local context, outperforming existing methods.

Contribution

The paper proposes a bidirectional aware guidance network that leverages global and local features to enhance segmentation accuracy of malignant breast lesions.

Findings

Achieves superior segmentation performance on public datasets.

Outperforms several state-of-the-art methods.

Demonstrates robustness in challenging heterogeneous tissue conditions.

Abstract

Breast lesions segmentation is an important step of computer-aided diagnosis system, and it has attracted much attention. However, accurate segmentation of malignant breast lesions is a challenging task due to the effects of heterogeneous structure and similar intensity distributions. In this paper, a novel bidirectional aware guidance network (BAGNet) is proposed to segment the malignant lesion from breast ultrasound images. Specifically, the bidirectional aware guidance network is used to capture the context between global (low-level) and local (high-level) features from the input coarse saliency map. The introduction of the global feature map can reduce the interference of surrounding tissue (background) on the lesion regions. To evaluate the segmentation performance of the network, we compared with several state-of-the-art medical image segmentation methods on the public breast ultrasound dataset using six commonly used evaluation metrics. Extensive experimental results indicate that our method achieves the most competitive segmentation results on malignant breast ultrasound images.