Curriculum Feature Alignment Domain Adaptation for Epithelium-Stroma Classification in Histopathological Images.

Researchers

Journal

Modalities

Models

Abstract

In recent years, deep learning methods have received more attention in epithelial-stroma (ES) classification tasks in histopathological images. Traditional deep learning methods assume that the training and test data have the same distribution, an assumption that is seldom satisfied due to complex imaging procedures. Unsupervised domain adaptation (UDA) transfers knowledge from a labelled source domain to a completely unlabeled target domain, and is more suitable for ES classification tasks to avoid tedious annotation. However, existing UDA methods for this task ignore the semantic alignment across domains. In this paper, we propose a Curriculum Feature Alignment Network (CFAN) to progressively align discriminative features across domains through selecting effective samples from the target domain and minimizing cross-domain intra-class differences. Specifically, we developed the Curriculum Transfer Strategy (CTS) and Adaptive Centroid Alignment (ACA) steps to train our model iteratively. We validated the method using three independent public ES datasets, and experimental results demonstrate that our method achieves better performance in ES classification compared with commonly used deep learning methods and existing deep domain adaptation methods.independent public ES datasets, and experimental results demonstrate that our method achieves better performance in ES classification compared with commonly used deep learning methods and existing deep domain adaptation methods.