State-of-the-Art Deep Learning Methods for Microscopic Image Segmentation: Applications to Cells, Nuclei, and Tissues DOI Creative Commons
Fatma Krikid, Hugo Rositi, Antoine Vacavant

et al.

Journal of Imaging, Journal Year: 2024, Volume and Issue: 10(12), P. 311 - 311

Published: Dec. 6, 2024

Microscopic image segmentation (MIS) is a fundamental task in medical imaging and biological research, essential for precise analysis of cellular structures tissues. Despite its importance, the process encounters significant challenges, including variability conditions, complex structures, artefacts (e.g., noise), which can compromise accuracy traditional methods. The emergence deep learning (DL) has catalyzed substantial advancements addressing these issues. This systematic literature review (SLR) provides comprehensive overview state-of-the-art DL methods developed over past six years microscopic images. We critically analyze key contributions, emphasizing how specifically tackle challenges cell, nucleus, tissue segmentation. Additionally, we evaluate datasets performance metrics employed studies. By synthesizing current identifying gaps existing approaches, this not only highlights transformative potential enhancing diagnostic research efficiency but also suggests directions future research. findings study have implications improving methodologies applications, ultimately fostering better patient outcomes advancing scientific understanding.

Language: Английский

Ultrack: pushing the limits of cell tracking across biological scales DOI Creative Commons
Jordão Bragantini, Ilan Theodoro, Xiang Zhao

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 3, 2024

Tracking live cells across 2D, 3D, and multi-channel time-lapse recordings is crucial for understanding tissue-scale biological processes. Despite advancements in imaging technology, achieving accurate cell tracking remains challenging, particularly complex crowded tissues where segmentation often ambiguous. We present Ultrack, a versatile scalable cell-tracking method that tackles this challenge by considering candidate segmentations derived from multiple algorithms parameter sets. Ultrack employs temporal consistency to select optimal segments, ensuring robust performance even under uncertainty. validate our on diverse datasets, including terabyte-scale developmental time-lapses of zebrafish, fruit fly, nematode embryos, as well multi-color label-free cellular imaging. show achieves state-of-the-art the Cell Challenge demonstrates superior accuracy densely packed embryonic over extended periods. Moreover, we propose an approach validation via dual-channel sparse labeling enables high-fidelity ground truth generation, pushing boundaries long-term assessment. Our freely available Python package with Fiji napari plugins can be deployed high-performance computing environment, facilitating widespread adoption research community.

Language: Английский

Citations

6
Nuclear instance segmentation and tracking for preimplantation mouse embryos DOI Creative Commons
Hayden Nunley, Binglun Shao, David Denberg

et al.

Development, Journal Year: 2024, Volume and Issue: 151(21)

Published: Oct. 7, 2024

ABSTRACT For investigations into fate specification and morphogenesis in time-lapse images of preimplantation embryos, automated 3D instance segmentation tracking nuclei are invaluable. Low signal-to-noise ratio, high voxel anisotropy, nuclear density, variable shapes can limit the performance methods, while is complicated by cell divisions, low frame rates, sample movements. Supervised machine learning approaches radically improve accuracy enable easier tracking, but they often require large amounts annotated data. Here, we first report a previously unreported mouse line expressing near-infrared reporter H2B-miRFP720. We then generate dataset (termed BlastoSPIM) H2B-miRFP720-expressing embryos with ground truth for instances. Using BlastoSPIM, benchmark seven convolutional neural networks identify Stardist-3D as most accurate method. With our BlastoSPIM-trained models, construct complete pipeline lineage from eight-cell stage to end development (>100 nuclei). Finally, demonstrate usefulness BlastoSPIM pre-train data related problems, both different imaging modality model systems.

Language: Английский

Citations

5
In toto live imaging of Erk signaling dynamics in developing zebrafish hepatocytes DOI
Faraz Ahmed Butt, Alessandro De Simone, Stefano Di Talia

et al.

Developmental Biology, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Nellie: automated organelle segmentation, tracking and hierarchical feature extraction in 2D/3D live-cell microscopy DOI Creative Commons
Austin E.Y.T. Lefebvre,

Gabriel Sturm,

Ting‐Yu Lin

et al.

Nature Methods, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Abstract Cellular organelles undergo constant morphological changes and dynamic interactions that are fundamental to cell homeostasis, stress responses disease progression. Despite their importance, quantifying organelle morphology motility remains challenging due complex architectures, rapid movements the technical limitations of existing analysis tools. Here we introduce Nellie, an automated unbiased pipeline for segmentation, tracking feature extraction diverse intracellular structures. Nellie adapts image metadata employs hierarchical segmentation resolve sub-organellar regions, while its radius-adaptive pattern matching enables precise motion tracking. Through a user-friendly Napari-based interface, comprehensive without coding expertise. We demonstrate Nellie’s versatility by unmixing multiple from single-channel data, mitochondrial ionomycin via graph autoencoders characterizing endoplasmic reticulum networks across types time points. This tool addresses critical need in biology providing accessible, dynamics.

Language: Английский

Citations

0
A Method to Visualize Cell Proliferation of Arabidopsis thaliana: A Case Study of the Root Apical Meristem DOI Creative Commons
J. Irepan Reyes‐Olalde, Miguel Tapia‐Rodríguez, Vadim Pérez‐Koldenkova

et al.

Plant Direct, Journal Year: 2025, Volume and Issue: 9(4)

Published: April 1, 2025

ABSTRACT Plant growth and development rely on a delicate balance between cell proliferation differentiation. The root apical meristem (RAM) of Arabidopsis thaliana is an excellent model to study the cycle due coordinated relationship nucleus shape size at each stage, allowing for precise estimation duration. In this study, we present method high‐resolution visualization RAM cells. This first protocol that allows simultaneous imaging cellular nuclear stains, being compatible with DNA replication markers such as EdU, including fluorescent proteins (H2B::YFP), SYTOX wall stain SR2200. includes clarification procedure enables acquisition 3D images, suitable detailed subsequent analysis.

Language: Английский

Citations

0
State-of-the-Art Deep Learning Methods for Microscopic Image Segmentation: Applications to Cells, Nuclei, and Tissues DOI Creative Commons
Fatma Krikid, Hugo Rositi, Antoine Vacavant

et al.

Journal of Imaging, Journal Year: 2024, Volume and Issue: 10(12), P. 311 - 311

Published: Dec. 6, 2024

Microscopic image segmentation (MIS) is a fundamental task in medical imaging and biological research, essential for precise analysis of cellular structures tissues. Despite its importance, the process encounters significant challenges, including variability conditions, complex structures, artefacts (e.g., noise), which can compromise accuracy traditional methods. The emergence deep learning (DL) has catalyzed substantial advancements addressing these issues. This systematic literature review (SLR) provides comprehensive overview state-of-the-art DL methods developed over past six years microscopic images. We critically analyze key contributions, emphasizing how specifically tackle challenges cell, nucleus, tissue segmentation. Additionally, we evaluate datasets performance metrics employed studies. By synthesizing current identifying gaps existing approaches, this not only highlights transformative potential enhancing diagnostic research efficiency but also suggests directions future research. findings study have implications improving methodologies applications, ultimately fostering better patient outcomes advancing scientific understanding.

Language: Английский

Citations

1