A Robust Unsupervised Domain Adaptation Framework for Medical Image Classification Using RKHS-MMD

TL;DR

This paper introduces an unsupervised domain adaptation framework using RKHS-MMD to improve medical image classification across different centers and devices, reducing the need for manual labeling.

Contribution

It combines transfer learning with RKHS-MMD loss for better domain alignment, outperforming standard MMD in medical image classification tasks.

Findings

Significant accuracy improvements on chest X-ray datasets from different centers.

RKHS-MMD outperforms standard MMD in reducing modality gaps.

Enhanced model generalization with less manual annotation effort.

Abstract

Labeling medical images is a major bottleneck in the field of medical imaging, as it requires domain-specific expertise, and it gets further complicated due to variability across different medical centers and different imaging devices. Such heterogeneity introduces domain shifts and modality discrepancies, which limits the generalization of trained models. To address this important challenge, we propose an unsupervised domain adaptation framework that combines transfer learning with a Reproducing Kernel Hilbert Space based Maximum Mean Discrepancy loss for the alignment of source and target domains. By jointly optimizing classification and RKHS-MMD losses, the methodology enhances generalization to unannotated medical datasets while diminishing reliance on manual annotation. Experimental evaluations presented on two chest X-ray datasets, which are obtained from different medical centers, show outstanding improvements over models trained without adaptation. Furthermore, we perform a comparative study to see that RKHS-MMD performs better than the standard Maximum Mean Discrepancy in reducing modality gap, emphasizing its effectiveness for medical image classification and also its strong capability in advanced AI-driven medical diagnostics.