ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimization

TL;DR

ConPro introduces a novel contrastive learning framework with preference optimization to improve severity assessment in medical images, outperforming existing methods and providing valuable severity ordering.

Contribution

It integrates preference knowledge into contrastive learning for medical image severity assessment, a novel approach enhancing representation quality.

Findings

Achieves 6% and 20% relative improvements over supervised and self-supervised baselines.

Provides meaningful severity ordering in feature space.

Outperforms previous state-of-the-art methods on classification tasks.

Abstract

Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel representation learning method for severity assessment in medical images using Contrastive learningintegrated Preference Optimization. Different from conventional contrastive learning methods that maximize the distance between classes, ConPrO injects into the latent vector the distance preference knowledge between various severity classes and the normal class. We systematically examine the key components of our framework to illuminate how contrastive prediction tasks acquire valuable representations. We show that our representation learning framework offers valuable severity ordering in the feature space while outperforming previous state-of-the-art methods on classification tasks. We achieve a 6% and 20% relative improvement compared to a supervised and a self-supervised baseline, respectively. In addition, we derived discussions on severity indicators and related applications of preference comparison in the medical domain.