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

arXiv: https://arxiv.org/abs/2510.21464 · HTML: https://mlsanity.com/paper/2510.21464/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Transcoders Find Interpretable LLM Feature Circuits](https://mlsanity.com/paper/2406.11944/) (2024)
- [InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2412.12101/) (2024)
- [LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model](https://mlsanity.com/paper/2405.02363/) (2024)
- [An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation](https://mlsanity.com/paper/2410.03334/) (2024)
- [Prompt Engineering Through the Lens of Optimal Control](https://mlsanity.com/paper/2310.14201/) (2023)
- [Human-like Content Analysis for Generative AI with Language-Grounded Sparse Encoders](https://mlsanity.com/paper/2508.18236/) (2025)
- [The Integrated Forward-Forward Algorithm: Integrating Forward-Forward and Shallow Backpropagation With Local Losses](https://mlsanity.com/paper/2305.12960/) (2023)
- [Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions](https://mlsanity.com/paper/2406.10878/) (2024)
- [Sparse Autoencoders Bridge The Deep Learning Model and The Brain](https://mlsanity.com/paper/2506.11123/) (2025)

## Built on by (most cited first, 2 of 2)

- [When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models](https://mlsanity.com/paper/2605.08245/) (2026)
- [Emergent Hierarchical Monosemantic Neurons from the Group-Contrastive Forward-Forward Algorithm](https://mlsanity.com/paper/2607.16295/) (2026)

## Abstract (arXiv)

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.