Panoptica -- instance-wise evaluation of 3D semantic and instance segmentation maps

TL;DR

Panoptica is an open-source Python package that provides a versatile, modular framework for instance-wise evaluation of 3D and 2D segmentation maps, enhancing analysis in biomedical imaging.

Contribution

It introduces a comprehensive, performance-optimized tool that extends existing metrics with additional measures like surface distance, tailored for detailed segmentation evaluation.

Findings

Effective on biomedical datasets

Enables detailed, instance-wise segmentation analysis

Supports multiple metrics beyond IoU

Abstract

This paper introduces panoptica, a versatile and performance-optimized package designed for computing instance-wise segmentation quality metrics from 2D and 3D segmentation maps. panoptica addresses the limitations of existing metrics and provides a modular framework that complements the original intersection over union-based panoptic quality with other metrics, such as the distance metric Average Symmetric Surface Distance. The package is open-source, implemented in Python, and accompanied by comprehensive documentation and tutorials. panoptica employs a three-step metrics computation process to cover diverse use cases. The efficacy of panoptica is demonstrated on various real-world biomedical datasets, where an instance-wise evaluation is instrumental for an accurate representation of the underlying clinical task. Overall, we envision panoptica as a valuable tool facilitating in-depth evaluation of segmentation methods.