Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring

TL;DR

Disco introduces a novel adjacency-aware framework for dense cell instance segmentation, addressing complex overlaps by leveraging topological graph properties and a collaborative coloring approach, validated on a new large-scale dataset.

Contribution

The paper presents the first systematic analysis of cell adjacency graph chromaticity and proposes a new method combining topological labeling with deep learning for complex tissue segmentation.

Findings

Most real-world cell graphs are non-bipartite with many odd cycles.

Disco effectively resolves complex adjacency conflicts in dense cellular regions.

The approach outperforms existing methods on complex tissue datasets.

Abstract

Accurate cell instance segmentation is foundational for digital pathology analysis. Existing methods based on contour detection and distance mapping still face significant challenges in processing complex and dense cellular regions. Graph coloring-based methods provide a new paradigm for this task, yet the effectiveness of this paradigm in real-world scenarios with dense overlaps and complex topologies has not been verified. Addressing this issue, we release a large-scale dataset GBC-FS 2025, which contains highly complex and dense sub-cellular nuclear arrangements. We conduct the first systematic analysis of the chromatic properties of cell adjacency graphs across four diverse datasets and reveal an important discovery: most real-world cell graphs are non-bipartite, with a high prevalence of odd-length cycles (predominantly triangles). This makes simple 2-coloring theory insufficient for handling complex tissues, while higher-chromaticity models would cause representational redundancy and optimization difficulties. Building on this observation of complex real-world contexts, we propose Disco (Densely-overlapping Cell Instance Segmentation via Adjacency-aware COllaborative Coloring), an adjacency-aware framework based on the "divide and conquer" principle. It uniquely combines a data-driven topological labeling strategy with a constrained deep learning system to resolve complex adjacency conflicts. First, "Explicit Marking" strategy transforms the topological challenge into a learnable classification task by recursively decomposing the cell graph and isolating a "conflict set." Second, "Implicit Disambiguation" mechanism resolves ambiguities in conflict regions by enforcing feature dissimilarity between different instances, enabling the model to learn separable feature representations.