Journal Article

The multimodality cell segmentation challenge: toward universal solutions

Upschulte, Eric, Yang, Xin, Espinosa, Leon, Eckardt, Jan-Niklas, Ayyadhury, Shamini, Li, Haofeng, Xie, Ronald, Dickscheid, Timo, Scheder, Maxime, Kim, Joonkee, Rahi, Sahand Jamal, Li, Zhaoyang, Bader, Gary D., Van Valen, David, Labagnara, Marco, Cheung, Trevor, Mignot, Tâm, Cai, Xiaochen, Ge, Cheng, Middeke, Jan Moritz, Zhang, Yao, Lou, Wei, Cimini, Beth A., Gu, Song, Kempster, Carly, de Almeida, José Guilherme, Greenwald, Noah F., Gupta, Anubha, Wang, Yixin, Brück, Oscar, Gupta, Ritu, Han, Lin, Pollitt, Alice, Bai, Bizhe, Li, Wangkai, Gligorovski, Vojislav, Wang, Bo, Lee, Gihun, Weisbart, Erin, Ma, Jun

2024

Overview

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimental settings. Here, we present a multimodality cell segmentation benchmark, comprising more than 1,500 labeled images derived from more than 50 diverse biological experiments. The top participants developed a Transformer-based deep-learning algorithm that not only exceeds existing methods but can also be applied to diverse microscopy images across imaging platforms and tissue types without manual parameter adjustments. This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging. Cell segmentation is crucial in many image analysis pipelines. This analysis compares many tools on a multimodal cell segmentation benchmark. A Transformer-based model performed best in terms of performance and general applicability.

• Publisher: Nature Publishing Group US,Nature Publishing Group
• Subject: 631/114/1305 / 631/114/1564 / Algorithms / Analysis / Animals / Benchmarks / Bioinformatics / Biological Microscopy / Biological Techniques / Biology / Biomedical and Life Sciences / Biomedical Engineering/Biotechnology / Data science / Datasets / Deep Learning / Humans / Image analysis / Image processing / Image Processing, Computer-Assisted - methods / Image segmentation / Life Sciences / Machine learning / Microscopy / Microscopy - methods / Parameters / Proteomics / Segmentation / Single-Cell Analysis - methods / Teams / Transformers