PBE-UNet: A light weight Progressive Boundary-Enhanced U-Net with Scale-Aware Aggregation for Ultrasound Image Segmentation

2026-04-15

AI Summary

This work addresses the challenge of inaccurate lesion segmentation in ultrasound images caused by low contrast, ambiguous boundaries, and significant scale variations. To this end, the authors propose a lightweight Progressive Boundary Enhancement U-Net (PBE-UNet), which innovatively treats boundary prediction not as a static mask but as a dynamically expanded spatial attention cue. The method incorporates a Scale-Aware Aggregation Module (SAAM) to capture multi-scale contextual information and a Boundary-Guided Feature Enhancement (BGFE) module that progressively dilates narrow boundary regions into broad attention maps, thereby emphasizing hard-to-segment areas. Extensive experiments on four public datasets—BUSI, Dataset B, TN3K, and BP—demonstrate that PBE-UNet consistently outperforms state-of-the-art methods, achieving substantial improvements in segmentation accuracy.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate lesion segmentation in ultrasound images is essential for preventive screening and clinical diagnosis, yet remains challenging due to low contrast, blurry boundaries, and significant scale variations. Although existing deep learning-based methods have achieved remarkable performance, these methods still struggle with scale variations and indistinct tumor boundaries. To address these challenges, we propose a progressive boundary enhanced U-Net (PBE-UNet). Specially, we first introduce a scale-aware aggregation module (SAAM) that dynamically adjusts its receptive field to capture robust multi-scale contextual information. Then, we propose a boundary-guided feature enhancement (BGFE) module to enhance the feature representations. We find that there are large gaps between the narrow boundary and the wide segmentation error areas. Unlike existing methods that treat boundaries as static masks, the BGFE module progressively expands the narrow boundary prediction into broader spatial attention maps. Thus, broader spatial attention maps could effectively cover the wider segmentation error regions and enhance the model's focus on these challenging areas. We conduct expensive experiments on four benchmark ultrasound datasets, BUSI, Dataset B, TN3K, and BP. The experimental results how that our proposed PBE-UNet outperforms state-of-the-art ultrasound image segmentation methods. The code is at https://github.com/cruelMouth/PBE-UNet.

Problem

• ultrasound image segmentation
• scale variations
• blurry boundaries
• lesion segmentation
• low contrast

Innovation

• Scale-Aware Aggregation
• Boundary-Guided Feature Enhancement
• Progressive Boundary Enhancement
• Ultrasound Image Segmentation
• Multi-Scale Context