TRACE: Training-time Report-guided and Clinically Ordered Concept Editing

2026-08-21

AI Summary

本文提出TRACE框架，通过利用结构化放射学报告作为概念监督来解决乳腺超声诊断中深度学习方法的可解释性和鲁棒性问题。

Abstract

Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigms that lack interpretability and robustness. While concept-based approaches offer a promising alternative, they often assume complete annotations or require multimodal inputs at inference, which significantly limits their real-world applicability. To tackle these issues, we propose Training-time Report-guided and Clinically Ordered Concept Editing (TRACE), a training-time report-guided framework that leverages structured radiology reports as privileged concept supervision while enabling image-only diagnosis at test time. TRACE refines image-derived concepts through a teacher-guided editing mechanism within a malignancy-aware ordered concept space. To address incomplete annotations, we introduce Strategic Concept Missing Training (SCMT) and train an image-only self-editor via edit distillation for autonomous concept refinement. Besides, we introduce BUSC, a concept-enriched benchmark linking images, labels, and structured attributes. Experiments across multiple datasets demonstrate that TRACE achieves superior performance and improved cross-domain robustness compared to existing methods.

Problem

• Breast ultrasound diagnosis
• semantic concepts
• end-to-end image-to-label paradigms
• interpretability and robustness
• concept-based approaches

Innovation

• Training-time Report-guided
• Clinically Ordered Concept Editing
• Strategic Concept Missing Training (SCMT)
• edit distillation
• concept refinement