Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform

TL;DR

This paper introduces a skeleton-aware distance transform (SDT) that enhances instance segmentation of complex structures by preserving connectivity and geometric arrangement, outperforming existing methods especially in histopathology images.

Contribution

The paper proposes a novel SDT method that combines skeleton information with distance transform to better handle complex, varying-width structures in instance segmentation.

Findings

SDT achieves state-of-the-art performance on histopathology image segmentation.

SDT effectively preserves intra-object connectivity and geometric structure.

The method outperforms boundary-based and affinity-based segmentation approaches.

Abstract

Objects with complex structures pose significant challenges to existing instance segmentation methods that rely on boundary or affinity maps, which are vulnerable to small errors around contacting pixels that cause noticeable connectivity change. While the distance transform (DT) makes instance interiors and boundaries more distinguishable, it tends to overlook the intra-object connectivity for instances with varying width and result in over-segmentation. To address these challenges, we propose a skeleton-aware distance transform (SDT) that combines the merits of object skeleton in preserving connectivity and DT in modeling geometric arrangement to represent instances with arbitrary structures. Comprehensive experiments on histopathology image segmentation demonstrate that SDT achieves state-of-the-art performance.