# Temporal Inversion for Learning Interval Change in Chest X-Rays

arXiv: https://arxiv.org/abs/2604.04563 · HTML: https://mlsanity.com/paper/2604.04563/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [A Survey of Vision-Language Pre-Trained Models](https://mlsanity.com/paper/2202.10936/) (2022)
- [Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning](https://mlsanity.com/paper/2210.06044/) (2022)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation](https://mlsanity.com/paper/2502.20056/) (2025)
- [Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports](https://mlsanity.com/paper/2306.08749/) (2023)
- [ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports](https://mlsanity.com/paper/2505.00228/) (2025)
- [RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning](https://mlsanity.com/paper/2310.13864/) (2023)
- [CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships between Chest X-Rays](https://mlsanity.com/paper/2208.03873/) (2022)
- [Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training](https://mlsanity.com/paper/2405.19654/) (2024)
- [Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation](https://mlsanity.com/paper/2210.17398/) (2022)
- [Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis](https://mlsanity.com/paper/2505.22079/) (2025)
- [Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models](https://mlsanity.com/paper/2506.08990/) (2025)
- [HIST-AID: Leveraging Historical Patient Reports for Enhanced Multi-Modal Automatic Diagnosis](https://mlsanity.com/paper/2411.10684/) (2024)
- [Variability Matters : Evaluating inter-rater variability in histopathology for robust cell detection](https://mlsanity.com/paper/2210.05175/) (2022)
- [Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays](https://mlsanity.com/paper/2509.15234/) (2025)

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

- [CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography](https://mlsanity.com/paper/2605.11304/) (2026)

## Abstract (arXiv)

Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyze radiographs in isolation, overlooking the key clinical task of comparing prior and current images to assess interval change. For chest radiographs (CXRs), capturing interval change is essential, as radiologists must evaluate not only the static appearance of findings but also how they evolve over time. We introduce TILA (Temporal Inversion-aware Learning and Alignment), a simple yet effective framework that uses temporal inversion, reversing image pairs, as a supervisory signal to enhance the sensitivity of existing temporal vision-language models to directional change. TILA integrates inversion-aware objectives across pretraining, fine-tuning, and inference, complementing conventional appearance modeling with explicit learning of temporal order. We also propose a unified evaluation protocol to assess order sensitivity and consistency under temporal inversion, and introduce MS-CXR-Tretrieval, a retrieval evaluation set constructed through a general protocol that can be applied to any temporal CXR dataset. Experiments on public datasets and real-world hospital cohorts demonstrate that TILA consistently improves progression classification and temporal embedding alignment when applied to multiple existing architectures.