FreqDINO: Frequency-Guided Adaptation for Generalized Boundary-Aware Ultrasound Image Segmentation
This work addresses ultrasound image segmentation for clinical diagnosis, representing an incremental improvement by adapting DINOv3 with frequency-guided techniques to handle ultrasound-specific boundary degradation.
The paper tackles the problem of ultrasound image segmentation, which is hindered by speckle noise and imaging artifacts, by proposing FreqDINO, a frequency-guided framework that enhances boundary perception and structural consistency, achieving superior performance and generalization capability compared to state-of-the-art methods.
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.