An open benchmark for nuclear segmentation reproducibility across annotation protocols

Yamada H, Berg L

Computational Pathology Journal · Published 30 May 2026 · DOI: 10.00000/cpj.2026.0037

Abstract

Annotation protocol variability is an under-reported source of performance variance in nuclear segmentation. We release a benchmark comprising the same 250 regions annotated under three protocols by five annotators, and quantify the resulting spread in reported model performance.

Keywords

Full text

Introduction

The full text of this article is available in the production system. This demonstration build presents the abstract, metadata, figures and reference structure to illustrate the article page layout.

Methods

Study design, data sources, inclusion criteria, statistical analysis and ethical approval are reported in full in the published version.

Results

Figures, tables and supplementary files accompany the published article.

Discussion

Interpretation, limitations and implications for practice are presented in the published version.

References

1. Reference list is provided with the published article.

Cite this article