# CheXLearner: Text-Guided Fine-Grained Representation Learning for Progression Detection

arXiv: https://arxiv.org/abs/2505.06903 · HTML: https://mlsanity.com/paper/2505.06903/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 11 May 2025.

## Builds on (most cited first, 19 of 19)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction](https://mlsanity.com/paper/2403.05396/) (2024)
- [Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation](https://mlsanity.com/paper/2502.20056/) (2025)
- [COVID-19 Prognosis via Self-Supervised Representation Learning and Multi-Image Prediction](https://mlsanity.com/paper/2101.04909/) (2021)
- [MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning](https://mlsanity.com/paper/2402.02045/) (2024)
- [CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships between Chest X-Rays](https://mlsanity.com/paper/2208.03873/) (2022)
- [MAGAN: Aligning Biological Manifolds](https://mlsanity.com/paper/1803.00385/) (2018)
- [Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation](https://mlsanity.com/paper/2405.14905/) (2024)
- [Longformer: Longitudinal Transformer for Alzheimer's Disease Classification with Structural MRIs](https://mlsanity.com/paper/2302.00901/) (2023)
- [The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning](https://mlsanity.com/paper/2207.02797/) (2022)
- [Longitudinal detection of radiological abnormalities with time-modulated LSTM](https://mlsanity.com/paper/1807.06144/) (2018)
- [A Nonlinear Hierarchical Model for Longitudinal Data on Manifolds](https://mlsanity.com/paper/2202.01180/) (2022)
- [Textual Inversion and Self-supervised Refinement for Radiology Report Generation](https://mlsanity.com/paper/2405.20607/) (2024)
- [Manifold-Aware Local Feature Modeling for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2410.10287/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learning Directional Semantic Transitions for Longitudinal Chest X-ray Analysis](https://mlsanity.com/paper/2606.15938/) (2026)

## Abstract (arXiv)

Temporal medical image analysis is essential for clinical decision-making, yet existing methods either align images and text at a coarse level - causing potential semantic mismatches - or depend solely on visual information, lacking medical semantic integration. We present CheXLearner, the first end-to-end framework that unifies anatomical region detection, Riemannian manifold-based structure alignment, and fine-grained regional semantic guidance. Our proposed Med-Manifold Alignment Module (Med-MAM) leverages hyperbolic geometry to robustly align anatomical structures and capture pathologically meaningful discrepancies across temporal chest X-rays. By introducing regional progression descriptions as supervision, CheXLearner achieves enhanced cross-modal representation learning and supports dynamic low-level feature optimization. Experiments show that CheXLearner achieves 81.12% (+17.2%) average accuracy and 80.32% (+11.05%) F1-score on anatomical region progression detection - substantially outperforming state-of-the-art baselines, especially in structurally complex regions. Additionally, our model attains a 91.52% average AUC score in downstream disease classification, validating its superior feature representation.