# Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseases

arXiv: https://arxiv.org/abs/2603.21935 · HTML: https://mlsanity.com/paper/2603.21935/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization](https://mlsanity.com/paper/1908.00748/) (2019)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [Metadata-enhanced contrastive learning from retinal optical coherence tomography images](https://mlsanity.com/paper/2208.02529/) (2022)
- [Learning to Compare Longitudinal Images](https://mlsanity.com/paper/2304.02531/) (2023)
- [SurvRNC: Learning Ordered Representations for Survival Prediction using Rank-N-Contrast](https://mlsanity.com/paper/2403.10603/) (2024)
- [Deep Learning for Rheumatoid Arthritis: Joint Detection and Damage Scoring in X-rays](https://mlsanity.com/paper/2104.13915/) (2021)
- [LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression](https://mlsanity.com/paper/2404.07091/) (2024)
- [Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer](https://mlsanity.com/paper/2509.14872/) (2025)
- [landmarker: a Toolkit for Anatomical Landmark Localization in 2D/3D Images](https://mlsanity.com/paper/2501.10098/) (2025)
- [Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention](https://mlsanity.com/paper/2410.15029/) (2024)
- [LesiOnTime -- Joint Temporal and Clinical Modeling for Small Breast Lesion Segmentation in Longitudinal DCE-MRI](https://mlsanity.com/paper/2508.00496/) (2025)
- [Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes](https://mlsanity.com/paper/2404.09768/) (2024)
- [Forecasting Disease Progression with Parallel Hyperplanes in Longitudinal Retinal OCT](https://mlsanity.com/paper/2409.20195/) (2024)
- [Interpretable Rheumatoid Arthritis Scoring via Anatomy-aware Multiple Instance Learning](https://mlsanity.com/paper/2508.06218/) (2025)

## Abstract (arXiv)

Quantitative disease severity scoring in medical imaging is costly, time-consuming, and subject to inter-reader variability. At the same time, clinical archives contain far more longitudinal imaging data than expert-annotated severity scores. Existing self-supervised methods typically ignore this chronological structure. We introduce ChronoCon, a contrastive learning approach that replaces label-based ranking losses with rankings derived solely from the visitation order of a patient's longitudinal scans. Under the clinically plausible assumption of monotonic progression in irreversible diseases, the method learns disease-relevant representations without using any expert labels. This generalizes the idea of Rank-N-Contrast from label distances to temporal ordering. Evaluated on rheumatoid arthritis radiographs for severity assessment, the learned representations substantially improve label efficiency. In low-label settings, ChronoCon significantly outperforms a fully supervised baseline initialized from ImageNet weights. In a few-shot learning experiment, fine-tuning ChronoCon on expert scores from only five patients yields an intraclass correlation coefficient of 86% for severity score prediction. These results demonstrate the potential of chronological contrastive learning to exploit routinely available imaging metadata to reduce annotation requirements in the irreversible disease domain. Code is available at https://github.com/cirmuw/ChronoCon.