Ranking-Guided Semi-Supervised Domain Adaptation for Severity Classification

TL;DR

This paper introduces a novel semi-supervised domain adaptation method for medical image severity classification that uses rank scores to better handle ordered class labels and domain shifts.

Contribution

It proposes a ranking-guided approach combining cross-domain ranking and distribution alignment to improve severity classification across domains.

Findings

Effective alignment of class-specific rank score distributions.

Improved accuracy in ulcerative colitis and diabetic retinopathy classification.

Successful handling of ordered class labels in domain adaptation.

Abstract

Semi-supervised domain adaptation leverages a few labeled and many unlabeled target samples, making it promising for addressing domain shifts in medical image analysis. However, existing methods struggle with severity classification due to unclear class boundaries. Severity classification involves naturally ordered class labels, complicating adaptation. We propose a novel method that aligns source and target domains using rank scores learned via ranking with class order. Specifically, Cross-Domain Ranking ranks sample pairs across domains, while Continuous Distribution Alignment aligns rank score distributions. Experiments on ulcerative colitis and diabetic retinopathy classification validate the effectiveness of our approach, demonstrating successful alignment of class-specific rank score distributions.