Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning
This work addresses the challenge of appearance variations in stained renal pathological images for medical image analysis, representing an incremental advancement in domain adaptation for segmentation tasks.
The paper tackles the problem of segmenting renal biopsy images across different staining types by proposing a multi-level adversarial network, which improves segmentation performance on target stained images and achieves similar accuracy using unlabeled data as with labeled data.
Segmentation from renal pathological images is a key step in automatic analyzing the renal histological characteristics. However, the performance of models varies significantly in different types of stained datasets due to the appearance variations. In this paper, we design a robust and flexible model for cross-stained segmentation. It is a novel multi-level deep adversarial network architecture that consists of three sub-networks: (i) a segmentation network; (ii) a pair of multi-level mirrored discriminators for guiding the segmentation network to extract domain-invariant features; (iii) a shape discriminator that is utilized to further identify the output of the segmentation network and the ground truth. Experimental results on glomeruli segmentation from renal biopsy images indicate that our network is able to improve segmentation performance on target type of stained images and use unlabeled data to achieve similar accuracy to labeled data. In addition, this method can be easily applied to other tasks.