3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence

TL;DR

This paper introduces a geometric framework and a novel Geo-Wasserstein divergence metric to identify and correct oversegmentation errors in 3D cell segmentation, improving accuracy across diverse datasets.

Contribution

The work is the first to formulate 3D oversegmentation correction as a concrete problem and to propose a geometric correction method with a new divergence metric.

Findings

Effective correction of oversegmentation in 3D cell images.

Strong transfer learning performance on out-of-domain datasets.

Ablation study confirms the importance of Geo-Wasserstein divergence.

Abstract

3D cell segmentation methods are often hindered by \emph{oversegmentation}, where a single cell is incorrectly split into multiple fragments. This degrades the final segmentation quality and is notoriously difficult to resolve, as oversegmentation errors often resemble natural gaps between adjacent cells. Our work makes two key contributions. First, for 3D cell segmentation, we are the first work to formulate oversegmentation as a concrete problem and propose a geometric framework to identify and correct these errors. Our approach builds a pre-trained classifier using both 2D geometric and 3D topological features extracted from flawed 3D segmentation results. Second, we introduce a novel metric, Geo-Wasserstein divergence, to quantify changes in 2D geometries. This captures the evolving trends of cell mask shape in a geometry-aware manner. We validate our method through extensive experiments on in-domain plant datasets, including both synthesized and real oversegmented cases, as well as on out-of-domain animal datasets to demonstrate transfer learning performance. An ablation study further highlights the contribution of the Geo-Wasserstein divergence. A clear pipeline is provided for end-users to build pre-trained models to any labeled dataset.