Defining the boundaries: challenges and advances in identifying cells in microscopy images

TL;DR

This paper reviews recent advances and ongoing challenges in cell segmentation within microscopy images, highlighting deep learning methods like Cellpose and segmentation challenges that drive innovation and standardization.

Contribution

It provides a comprehensive overview of current techniques, challenges, and standards in cell segmentation, emphasizing the progress made with deep learning tools and community efforts.

Findings

Deep learning tools like Cellpose improve accuracy and usability.

Segmentation challenges promote innovation and standardization.

Progress toward universal cell segmentation methods.

Abstract

Segmentation, or the outlining of objects within images, is a critical step in the measurement and analysis of cells within microscopy images. While improvements continue to be made in tools that rely on classical methods for segmentation, deep learning-based tools increasingly dominate advances in the technology. Specialist models such as Cellpose continue to improve in accuracy and user-friendliness, and segmentation challenges such as the Multi-Modality Cell Segmentation Challenge continue to push innovation in accuracy across widely-varying test data as well as efficiency and usability. Increased attention on documentation, sharing, and evaluation standards are leading to increased user-friendliness and acceleration towards the goal of a truly universal method.