Dual Adaptive Pyramid Network for Cross-Stain Histopathology Image Segmentation

TL;DR

This paper introduces a dual adaptive pyramid network that effectively performs cross-stain histopathology image segmentation by addressing domain differences at both image and feature levels through adversarial training.

Contribution

The paper proposes a novel dual adaptive pyramid network (DAPNet) that enhances cross-stain histopathology segmentation by integrating image-level and feature-level domain adaptation.

Findings

Outperforms state-of-the-art methods in cross-stain gland segmentation

Effective domain adaptation at both image and feature levels

Validated on H&E and DAB-H stain datasets

Abstract

Supervised semantic segmentation normally assumes the test data being in a similar data domain as the training data. However, in practice, the domain mismatch between the training and unseen data could lead to a significant performance drop. Obtaining accurate pixel-wise label for images in different domains is tedious and labor intensive, especially for histopathology images. In this paper, we propose a dual adaptive pyramid network (DAPNet) for histopathological gland segmentation adapting from one stain domain to another. We tackle the domain adaptation problem on two levels: 1) the image-level considers the differences of image color and style; 2) the feature-level addresses the spatial inconsistency between two domains. The two components are implemented as domain classifiers with adversarial training. We evaluate our new approach using two gland segmentation datasets with H&E and DAB-H stains respectively. The extensive experiments and ablation study demonstrate the effectiveness of our approach on the domain adaptive segmentation task. We show that the proposed approach performs favorably against other state-of-the-art methods.