Ultrack: pushing the limits of cell tracking across biological scales

Autor(es):Mostrar menos -

Bragantini, Jordao ; Theodoro, Ilan ; Zhao, Xiang ; Huijben, Teun A. P. M. ; Hirata-Miyasaki, Eduardo ; Vijaykumar, Shruthi ; Balasubramanian, Akilandeswari ; Lao, Tiger ; Agrawal, Richa ; Xiao, Sheng ; Lammerding, Jan ; Mehta, Shalin ; Falcao, Alexandre X. ; Jacobo, Adrian ; Lange, Merlin ; Royer, Loic A.

• Tipo de documento: Artigo Científico
• Fonte: NATURE METHODS; v. N/A, p. 32-pg., 2025-08-25.

Resumo

Tracking live cells across two-dimensional, three-dimensional (3D) and multichannel time-lapse recordings is crucial for understanding tissue-scale biological processes. Despite advancements in imaging technology, accurately tracking cells remains challenging, particularly in complex and crowded tissues where cell segmentation is often ambiguous. We present Ultrack, a versatile and scalable cell tracking method that tackles this challenge by considering candidate segmentations derived from multiple algorithms and parameter sets. Ultrack leverages temporal consistency to select optimal segments, ensuring robust performance even under segmentation uncertainty. We validate our method on diverse datasets, including terabyte-scale developmental time-lapse recordings of zebrafish, fruit fly and nematode embryos, as well as multicolor and label-free cellular imaging. We demonstrate that Ultrack achieves superior or comparable performance in the cell tracking challenge, particularly when tracking densely packed 3D embryonic cells over extended periods. Moreover, we propose an approach to tracking validation via dual-channel sparse labeling that enables high-fidelity ground-truth generation, pushing the boundaries of long-term cell tracking assessment. Our method is freely available as a Python package with Fiji and Napari plugins and can be deployed in a high-performance computing environment, facilitating widespread adoption by the research community. (AU)

• Processo FAPESP: 23/14427-8 - Ciência de Dados para a Indústria Inteligente (CDII)
• Beneficiário: José Alberto Cuminato
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa Aplicada
• Processo FAPESP: 22/07877-4 - Incorporando aprendizado contrastivo na segmentação de imagens por árvores dinâmicas
• Beneficiário: Ilan Francisco da Silva
• Modalidade de apoio: Bolsas no Brasil - Iniciação Científica
• Processo FAPESP: 22/16491-2 - O papel do aprendizado contrastivo para a correção assistida pelo usuário da segmentação de células
• Beneficiário: Ilan Francisco da Silva
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Iniciação Científica