Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform
This addresses instance segmentation challenges in histopathology images, where existing methods are vulnerable to errors, but it is incremental as it builds on distance transform and skeleton techniques.
The paper tackles the problem of instance segmentation for objects with complex structures by proposing a skeleton-aware distance transform (SDT) that preserves connectivity and models geometric arrangement, achieving state-of-the-art performance on histopathology image segmentation.
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.