Semi-Supervised Semantic Segmentation of Cell Nuclei via Diffusion-based Large-Scale Pre-Training and Collaborative Learning

TL;DR

This paper presents a semi-supervised cell nuclei segmentation framework that leverages diffusion-based pre-training and collaborative learning, significantly improving performance on multiple datasets and demonstrating robustness and generality.

Contribution

The novel framework combines diffusion model pre-training with transformer-based feature aggregation and collaborative learning, advancing semi-supervised segmentation methods.

Findings

Significant performance improvements over existing semi-supervised methods.

Robustness demonstrated through out-of-distribution tests.

Ablation studies confirm the effectiveness of each component.

Abstract

Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While supervised deep learning methods are promising, they necessitate large annotated datasets that are time-consuming and error-prone to acquire. Semi-supervised approaches could provide feasible alternatives to this issue. However, the limited annotated data may lead to subpar performance of semi-supervised methods, regardless of the abundance of unlabeled data. In this paper, we introduce a novel unsupervised pre-training-based semi-supervised framework for cell-nuclei segmentation. Our framework is comprised of three main components. Firstly, we pretrain a diffusion model on a large-scale unlabeled dataset. The diffusion model's explicit modeling capability facilitates the learning of semantic feature representation from the unlabeled data. Secondly, we achieve semantic feature aggregation using a transformer-based decoder, where the pretrained diffusion model acts as the feature extractor, enabling us to fully utilize the small amount of labeled data. Finally, we implement a collaborative learning framework between the diffusion-based segmentation model and a supervised segmentation model to further enhance segmentation performance. Experiments were conducted on four publicly available datasets to demonstrate significant improvements compared to competitive semi-supervised segmentation methods and supervised baselines. A series of out-of-distribution tests further confirmed the generality of our framework. Furthermore, thorough ablation experiments and visual analysis confirmed the superiority of our proposed method.