FreqDINO: Frequency-Guided Adaptation for Generalized Boundary-Aware Ultrasound Image Segmentation

TL;DR

FreqDINO is a novel frequency-guided framework that significantly improves ultrasound image segmentation by enhancing boundary detection and structural consistency, addressing limitations of pre-trained models on ultrasound-specific artifacts.

Contribution

It introduces a multi-scale frequency extraction and alignment strategy, a boundary refinement module, and a boundary-guided decoder to enhance ultrasound segmentation accuracy.

Findings

Outperforms state-of-the-art methods in ultrasound segmentation

Demonstrates superior boundary detection and structural consistency

Shows strong generalization across different ultrasound datasets

Abstract

Ultrasound image segmentation is pivotal for clinical diagnosis, yet challenged by speckle noise and imaging artifacts. Recently, DINOv3 has shown remarkable promise in medical image segmentation with its powerful representation capabilities. However, DINOv3, pre-trained on natural images, lacks sensitivity to ultrasound-specific boundary degradation. To address this limitation, we propose FreqDINO, a frequency-guided segmentation framework that enhances boundary perception and structural consistency. Specifically, we devise a Multi-scale Frequency Extraction and Alignment (MFEA) strategy to separate low-frequency structures and multi-scale high-frequency boundary details, and align them via learnable attention. We also introduce a Frequency-Guided Boundary Refinement (FGBR) module that extracts boundary prototypes from high-frequency components and refines spatial features. Furthermore, we design a Multi-task Boundary-Guided Decoder (MBGD) to ensure spatial coherence between boundary and semantic predictions. Extensive experiments demonstrate that FreqDINO surpasses state-of-the-art methods with superior achieves remarkable generalization capability. The code is at https://github.com/MingLang-FD/FreqDINO.