CXR-LanIC：基于语言的可解释分类器用于胸部X光诊断
CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis
- National University of Singapore（新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出CXR-LanIC，一种基于语言的可解释分类器，通过任务对齐的模式发现解决胸部X光诊断的可解释性挑战，通过训练稀疏自编码器提取可解释的视觉模式，实现高准确率的诊断并支持自然语言解释。
AI中文摘要：
深度学习模型在胸部X光诊断中已取得显著的准确性，但其广泛应用仍受到预测黑盒性质的限制。临床医生需要透明、可验证的解释来信任自动化诊断并识别潜在的故障模式。我们介绍CXR-LanIC（基于语言的可解释分类器用于胸部X光），一种新的框架，通过任务对齐的模式发现解决这一可解释性挑战。我们的方法在BiomedCLIP诊断分类器上训练基于转码的稀疏自编码器，将医学图像表示分解为可解释的视觉模式。通过在MIMIC-CXR数据集上训练100个转码器，我们发现了约5,000个单义模式，涵盖心脏、肺部、胸膜、结构、设备和伪影类别。每个模式在共享特定放射学特征的图像中表现出一致的激活行为，使预测分解为20-50个可解释模式，具有可验证的激活画廊。CXR-LanIC在五个关键发现上实现了竞争性的诊断准确性，同时通过计划的大型多模态模型注释为自然语言解释奠定基础。我们的关键创新在于从在特定诊断目标上训练的分类器中提取可解释特征，而不是通用嵌入，确保发现的模式直接相关于临床决策，证明医疗AI系统可以既准确又可解释，通过透明、基于临床的解释支持更安全的临床部署。
英文摘要：
Deep learning models have achieved remarkable accuracy in chest X-ray diagnosis, yet their widespread clinical adoption remains limited by the black-box nature of their predictions. Clinicians require transparent, verifiable explanations to trust automated diagnoses and identify potential failure modes. We introduce CXR-LanIC (Language-Grounded Interpretable Classifier for Chest X-rays), a novel framework that addresses this interpretability challenge through task-aligned pattern discovery. Our approach trains transcoder-based sparse autoencoders on a BiomedCLIP diagnostic classifier to decompose medical image representations into interpretable visual patterns. By training an ensemble of 100 transcoders on multimodal embeddings from the MIMIC-CXR dataset, we discover approximately 5,000 monosemantic patterns spanning cardiac, pulmonary, pleural, structural, device, and artifact categories. Each pattern exhibits consistent activation behavior across images sharing specific radiological features, enabling transparent attribution where predictions decompose into 20-50 interpretable patterns with verifiable activation galleries. CXR-LanIC achieves competitive diagnostic accuracy on five key findings while providing the foundation for natural language explanations through planned large multimodal model annotation. Our key innovation lies in extracting interpretable features from a classifier trained on specific diagnostic objectives rather than general-purpose embeddings, ensuring discovered patterns are directly relevant to clinical decision-making, demonstrating that medical AI systems can be both accurate and interpretable, supporting safer clinical deployment through transparent, clinically grounded explanations.
