Seg-metrics: a Python package to compute segmentation metrics

TL;DR

The paper addresses the lack of standardized MIS evaluation metrics and inconsistent implementations across tools. It introduces seg-metrics, an open-source Python package that unifies overlap-based and distance-based segmentation metrics and enables single-call computation across multi-label outputs, with fast performance and CSV export. The authors demonstrate speed advantages over existing tools and emphasize ease of use, multi-format input, and one-line metric calculation. This work provides a practical, reproducible evaluation toolkit to reduce metric cherry-picking and accelerate MIS model assessment in research and practice.

Abstract

In response to a concerning trend of selectively emphasizing metrics in medical image segmentation (MIS) studies, we introduce \texttt{seg-metrics}, an open-source Python package for standardized MIS model evaluation. Unlike existing packages, \texttt{seg-metrics} offers user-friendly interfaces for various overlap-based and distance-based metrics, providing a comprehensive solution. \texttt{seg-metrics} supports multiple file formats and is easily installable through the Python Package Index (PyPI). With a focus on speed and convenience, \texttt{seg-metrics} stands as a valuable tool for efficient MIS model assessment.