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

2026-03-23

AI Summary

This work addresses the high cost, time consumption, and inter-reader variability associated with disease severity scoring in medical imaging, as well as the scarcity of expert annotations for abundant longitudinal image data. To tackle these challenges, the authors propose ChronoCon, a fully unsupervised method that leverages only the temporal ordering of longitudinal patient images under the assumption of irreversible, monotonic disease progression. By extending contrastive learning from label-dependent distance supervision to purely time-ordered sequences, ChronoCon achieves the first disease representation learning framework that requires no annotations whatsoever. Evaluated on rheumatoid arthritis X-ray data, the method—after fine-tuning with annotations from just five patients—achieves an intra-class correlation coefficient of 86%, substantially outperforming fully supervised baselines initialized with ImageNet pretraining.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Unsupervised & Self-Supervised Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

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.

Problem

• chronological contrastive learning
• few-shot progression assessment
• irreversible diseases
• longitudinal imaging
• disease severity scoring

Innovation

• Chronological Contrastive Learning
• Self-supervised Learning
• Longitudinal Medical Imaging
• Few-shot Learning
• Temporal Ordering