Boosting Ultrasound Image Classification via Attribute-Guided Dual-Branch Framework

2026-07-01

AI Summary

Existing ultrasound image classification methods often exhibit limited generalization and poor interpretability due to their neglect of clinical prior knowledge. To address this, this work proposes an attribute-guided dual-branch framework: a primary branch performs standard classification, while an auxiliary branch incorporates domain-agnostic medical attribute priors to generate interpretable diagnostic cues. The outputs of both branches are dynamically integrated through an adaptive, data-dependent fusion module. This design seamlessly embeds into mainstream backbone architectures with negligible computational overhead, significantly improving classification accuracy while yielding human-understandable diagnostic evidence. Extensive experiments demonstrate that the proposed method consistently outperforms current state-of-the-art models across multiple ultrasound classification tasks.

Abstract

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: https://github.com/zhaobo253-crypto/AttrGuide.

Problem

• Ultrasound image classification
• clinical priors
• generalization
• interpretability
• computer-aided diagnosis

Innovation

• attribute-guided
• dual-branch framework
• medical priors
• interpretable AI
• ultrasound classification