Instance-Aware Robust Consistency Regularization for Semi-Supervised Nuclei Instance Segmentation

2025-10-10

AI Summary

Instance segmentation of nuclei in histopathological images faces challenges including high annotation costs, insufficient instance-level consistency modeling in semi-supervised methods, sensitivity to pseudo-label noise, and underutilization of domain-specific prior knowledge. To address these, we propose an instance-aware robust consistency regularization framework that jointly integrates matching-driven and prior-driven instance-level consistency constraints. The former employs optimal transport to establish cross-view instance correspondences, while the latter incorporates morphological priors—such as nuclear size and roundness—to guide pseudo-label quality assessment and filtering. Built upon a teacher–student architecture, our method achieves significant improvements over state-of-the-art semi-supervised approaches across multiple public benchmarks; notably, it even surpasses fully supervised baselines under certain settings. Most importantly, it substantially enhances segmentation accuracy in densely overlapping regions, yielding more robust and precise instance-level predictions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Nuclei instance segmentation in pathological images is crucial for downstream tasks such as tumor microenvironment analysis. However, the high cost and scarcity of annotated data limit the applicability of fully supervised methods, while existing semi-supervised methods fail to adequately regularize consistency at the instance level, lack leverage of the inherent prior knowledge of pathological structures, and are prone to introducing noisy pseudo-labels during training. In this paper, we propose an Instance-Aware Robust Consistency Regularization Network (IRCR-Net) for accurate instance-level nuclei segmentation. Specifically, we introduce the Matching-Driven Instance-Aware Consistency (MIAC) and Prior-Driven Instance-Aware Consistency (PIAC) mechanisms to refine the nuclei instance segmentation result of the teacher and student subnetwork, particularly for densely distributed and overlapping nuclei. We incorporate morphological prior knowledge of nuclei in pathological images and utilize these priors to assess the quality of pseudo-labels generated from unlabeled data. Low-quality pseudo-labels are discarded, while high-quality predictions are enhanced to reduce pseudo-label noise and benefit the network's robust training. Experimental results demonstrate that the proposed method significantly enhances semi-supervised nuclei instance segmentation performance across multiple public datasets compared to existing approaches, even surpassing fully supervised methods in some scenarios.

Problem

• Addresses instance-level consistency regularization in semi-supervised nuclei segmentation
• Reduces noisy pseudo-labels using morphological priors and quality assessment
• Improves segmentation for densely distributed and overlapping nuclei in pathology

Innovation

• Instance-aware consistency mechanisms refine segmentation
• Morphological priors assess pseudo-label quality for noise reduction
• Discarding low-quality pseudo-labels enhances robust training