AD-GAN: End-to-end Unsupervised Nuclei Segmentation with Aligned Disentangling Training

TL;DR

AD-GAN is an innovative end-to-end unsupervised framework for nuclei segmentation that leverages representation disentanglement to preserve spatial structure and reduce lossy transformations, outperforming existing methods.

Contribution

The paper introduces AD-GAN, a novel end-to-end unsupervised nuclei segmentation model that employs representation disentanglement and a new training algorithm to improve accuracy and reduce content loss.

Findings

Outperforms existing unsupervised methods by 17.8% in DICE score.

Achieves results comparable to supervised models.

Effective on both 2D and 3D real-world datasets.

Abstract

We consider unsupervised cell nuclei segmentation in this paper. Exploiting the recently-proposed unpaired image-to-image translation between cell nuclei images and randomly synthetic masks, existing approaches, e.g., CycleGAN, have achieved encouraging results. However, these methods usually take a two-stage pipeline and fail to learn end-to-end in cell nuclei images. More seriously, they could lead to the lossy transformation problem, i.e., the content inconsistency between the original images and the corresponding segmentation output. To address these limitations, we propose a novel end-to-end unsupervised framework called Aligned Disentangling Generative Adversarial Network (AD-GAN). Distinctively, AD-GAN introduces representation disentanglement to separate content representation (the underling spatial structure) from style representation (the rendering of the structure). With this framework, spatial structure can be preserved explicitly, enabling a significant reduction of macro-level lossy transformation. We also propose a novel training algorithm able to align the disentangled content in the latent space to reduce micro-level lossy transformation. Evaluations on real-world 2D and 3D datasets show that AD-GAN substantially outperforms the other comparison methods and the professional software both quantitatively and qualitatively. Specifically, the proposed AD-GAN leads to significant improvement over the current best unsupervised methods by an average 17.8% relatively (w.r.t. the metric DICE) on four cell nuclei datasets. As an unsupervised method, AD-GAN even performs competitive with the best supervised models, taking a further leap towards end-to-end unsupervised nuclei segmentation.