Decomposing and Coupling Saliency Map for Lesion Segmentation in Ultrasound Images

TL;DR

This paper introduces DC-Net, a novel decomposition-coupling network that disentangles and fuses saliency maps for improved ultrasound lesion segmentation, addressing the challenge of similar intensities between lesions and background.

Contribution

The work proposes a new decomposition-coupling network with specialized fusion strategies and a harmonic loss for enhanced ultrasound lesion segmentation accuracy.

Findings

Significant performance improvement over state-of-the-art methods

Effective disentanglement of foreground and background saliency maps

Robust segmentation in complex ultrasound images

Abstract

Complex scenario of ultrasound image, in which adjacent tissues (i.e., background) share similar intensity with and even contain richer texture patterns than lesion region (i.e., foreground), brings a unique challenge for accurate lesion segmentation. This work presents a decomposition-coupling network, called DC-Net, to deal with this challenge in a (foreground-background) saliency map disentanglement-fusion manner. The DC-Net consists of decomposition and coupling subnets, and the former preliminarily disentangles original image into foreground and background saliency maps, followed by the latter for accurate segmentation under the assistance of saliency prior fusion. The coupling subnet involves three aspects of fusion strategies, including: 1) regional feature aggregation (via differentiable context pooling operator in the encoder) to adaptively preserve local contextual details with the larger receptive field during dimension reduction; 2) relation-aware representation fusion (via cross-correlation fusion module in the decoder) to efficiently fuse low-level visual characteristics and high-level semantic features during resolution restoration; 3) dependency-aware prior incorporation (via coupler) to reinforce foreground-salient representation with the complementary information derived from background representation. Furthermore, a harmonic loss function is introduced to encourage the network to focus more attention on low-confidence and hard samples. The proposed method is evaluated on two ultrasound lesion segmentation tasks, which demonstrates the remarkable performance improvement over existing state-of-the-art methods.