Boosting Ultrasound Image Classification via Attribute-Guided Dual-Branch Framework
Quick Answer
The proposed attribute-guided dual-branch framework enhances ultrasound image classification by integrating domain-agnostic medical attributes, improving both accuracy and interpretability.
Quick Take
This method can be seamlessly integrated into existing architectures, demonstrating consistent performance improvements across various classification tasks with minimal overhead.
Key Points
- Introduces a medical-prior module for enhanced diagnostic performance.
- Baseline branch uses conventional architectures for image category prediction.
- Attribute-guided branch provides human-interpretable decision cues.
- Adaptive decision module fuses outputs from both branches for final predictions.
- Code available at GitHub for implementation and testing.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Ultrasound image classification is essential for computer-aided diagnosis. However, current methods often neglect clinical priors, leading to poor generalization in challenging scenarios and a lack of interpretability that limits clinical adoption. To address these issues, we aim to develop a medical-prior module that can be seamlessly integrated into existing pipelines to enhance both diagnostic performance and interpretability. In this paper, we propose an attribute-guided dual-branch framework for ultrasound classification that introduces domain-agnostic medical attribute priors, improving generalization while offering interpretable evidence. Specifically, a baseline branch follows conventional architectures and predicts image categories via a fully connected classifier. An attribute-guided branch injects domain-agnostic attributes as priors and produces human-interpretable decision cues. Finally, an adaptive decision module fuses the two branches in a data-dependent manner to yield the final prediction. Experiments across diverse ultrasound classification tasks demonstrate that our approach can be integrated into multiple backbones and state-of-the-art methods with low overhead, consistently improving accuracy and interpretability. Code is available at: this https URL.
| Comments: | accepted by MICCAI 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.01648 [cs.CV] |
| (or arXiv:2607.01648v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.01648 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yapeng Li [view email]
[v1]
Thu, 2 Jul 2026 03:20:12 UTC (1,725 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.