CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tang, Yiming, Zhong, Wenjia, Shah, Rushi, Liu, Dianbo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911697816518656
author Tang, Yiming
Zhong, Wenjia
Shah, Rushi
Liu, Dianbo
author_facet Tang, Yiming
Zhong, Wenjia
Shah, Rushi
Liu, Dianbo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21464
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis
Tang, Yiming
Zhong, Wenjia
Shah, Rushi
Liu, Dianbo
Computer Vision and Pattern Recognition
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.
title CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.21464