SwinCell: a 3D transformer and flow-based framework for improved cell segmentation

Zhang, Xiao; Lin, Zihan; Wang, Liguo; Chu, Yong S.; Yang, Yang; Xiao, Xianghui; Lin, Yuewei; Liu, Qun

doi:10.1038/s42003-025-08397-x

SwinCell: a 3D transformer and flow-based framework for improved cell segmentation

Journal Article · Tue Jul 01 00:00:00 EDT 2025 · Communications Biology

DOI:https://doi.org/10.1038/s42003-025-08397-x· OSTI ID:2572801

^[1]; Lin, Zihan ^[1]; Wang, Liguo ^[1]; Chu, Yong S. ^[2]; ^[2]; ^[2]; ^[1]; ^[2]

Brookhaven National Laboratory (BNL), Upton, NY (United States)
Brookhaven National Laboratory (BNL), Upton, NY (United States). National Synchrotron Light Source II (NSLS-II)

Segmentation of three-dimensional (3D) cellular images is fundamental for studying and understanding cell structure and function. However, 3D cellular segmentation is challenging, particularly for dense cells and tissues. This challenge arises mainly from the complex contextual information within 3D images, anisotropic properties, and the sensitivity to internal cellular structures, which often lead to incorrect segmentation. In this work, we introduce SwinCell, a 3D transformer-based framework that leverages Swin-transformer to predict flow and differentiate individual cell instances. We demonstrate SwinCell’s utility in the segmentation of nuclei, colon tissue cells, and densely cultured cells. SwinCell strikes a balance between maintaining detailed local feature recognition and understanding broader contextual information. Through extensive testing with both public and in-house 3D cell imaging datasets, SwinCell shows utility in segmenting dense cells, making it a valuable tool for 3D segmentation in cellular analysis that could expedite research in cell biology and tissue engineering.

View Accepted Manuscript (DOE)

Research Organization:: Brookhaven National Laboratory (BNL), Upton, NY (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Biological and Environmental Research (BER)

Grant/Contract Number:: SC0012704

OSTI ID:: 2572801

Alternate ID(s):: OSTI ID: 2998872

Report Number(s):: BNL--228317-2025-JAAM; BNL--228453-2025-JAAM

Journal Information:: Communications Biology, Journal Name: Communications Biology Journal Issue: 1 Vol. 8; ISSN 2399-3642

Publisher:: Springer NatureCopyright Statement

Country of Publication:: United States

Language:: English

References (26)

U-Net: Convolutional Networks for Biomedical Image Segmentation Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28	book	November 2015
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation Çiçek, Özgün; Abdulkadir, Ahmed; Lienkamp, Soeren S. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 https://doi.org/10.1007/978-3-319-46723-8_49	conference	January 2016
Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study Wagner, Sophia J.; Reisenbüchler, Daniel; West, Nicholas P. Cancer Cell, Vol. 41, Issue 9 https://doi.org/10.1016/j.ccell.2023.08.002	journal	September 2023
User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability Yushkevich, Paul A.; Piven, Joseph; Hazlett, Heather Cody NeuroImage, Vol. 31, Issue 3 https://doi.org/10.1016/j.neuroimage.2006.01.015	journal	July 2006
AI under the microscope: the algorithms powering the search for cells Eisenstein, Michael Nature, Vol. 623, Issue 7989 https://doi.org/10.1038/d41586-023-03722-y	journal	November 2023
Improvement of cryo-EM maps by simultaneous local and non-local deep learning He, Jiahua; Li, Tao; Huang, Sheng-You Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-39031-1	journal	June 2023
Structure of native chromatin fibres revealed by Cryo-ET in situ Hou, Zhen; Nightingale, Frank; Zhu, Yanan Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-42072-1	journal	October 2023
Array programming with NumPy Harris, Charles R.; Millman, K. Jarrod; van der Walt, Stéfan J. Nature, Vol. 585, Issue 7825 https://doi.org/10.1038/s41586-020-2649-2	journal	September 2020
Whole-cell organelle segmentation in volume electron microscopy Heinrich, Larissa; Bennett, Davis; Ackerman, David Nature, Vol. 599, Issue 7883 https://doi.org/10.1038/s41586-021-03977-3	journal	October 2021
An open-access volume electron microscopy atlas of whole cells and tissues Xu, C. Shan; Pang, Song; Shtengel, Gleb Nature, Vol. 599, Issue 7883 https://doi.org/10.1038/s41586-021-03992-4	journal	October 2021
Integrated intracellular organization and its variations in human iPS cells Viana, Matheus P.; Chen, Jianxu; Knijnenburg, Theo A. Nature, Vol. 613, Issue 7943 https://doi.org/10.1038/s41586-022-05563-7	journal	January 2023
Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning Greenwald, Noah F.; Miller, Geneva; Moen, Erick Nature Biotechnology, Vol. 40, Issue 4 https://doi.org/10.1038/s41587-021-01094-0	journal	November 2021
Label-free prediction of three-dimensional fluorescence images from transmitted-light microscopy Ounkomol, Chawin; Seshamani, Sharmishtaa; Maleckar, Mary M. Nature Methods, Vol. 15, Issue 11 https://doi.org/10.1038/s41592-018-0111-2	journal	September 2018
A complete data processing workflow for cryo-ET and subtomogram averaging Chen, Muyuan; Bell, James M.; Shi, Xiaodong Nature Methods, Vol. 16, Issue 11 https://doi.org/10.1038/s41592-019-0591-8	journal	October 2019
SciPy 1.0: fundamental algorithms for scientific computing in Python Virtanen, Pauli; Gommers, Ralf; Oliphant, Travis E. Nature Methods https://doi.org/10.1038/s41592-019-0686-2	journal	February 2020
Cellpose: a generalist algorithm for cellular segmentation Stringer, Carsen; Wang, Tim; Michaelos, Michalis Nature Methods, Vol. 18, Issue 1 https://doi.org/10.1038/s41592-020-01018-x	journal	December 2020
Cellpose 2.0: how to train your own model Pachitariu, Marius; Stringer, Carsen Nature Methods, Vol. 19, Issue 12 https://doi.org/10.1038/s41592-022-01663-4	journal	November 2022
ERnet: a tool for the semantic segmentation and quantitative analysis of endoplasmic reticulum topology Lu, Meng; Christensen, Charles N.; Weber, Jana M. Nature Methods, Vol. 20, Issue 4 https://doi.org/10.1038/s41592-023-01815-0	journal	March 2023
Preparing samples from whole cells using focused-ion-beam milling for cryo-electron tomography Wagner, Felix R.; Watanabe, Reika; Schampers, Ruud Nature Protocols, Vol. 15, Issue 6 https://doi.org/10.1038/s41596-020-0320-x	journal	May 2020
Correlative single-cell hard X-ray computed tomography and X-ray fluorescence imaging Lin, Zihan; Zhang, Xiao; Nandi, Purbasha Communications Biology, Vol. 7, Issue 1 https://doi.org/10.1038/s42003-024-05950-y	journal	March 2024
DeepSite: protein-binding site predictor using 3D-convolutional neural networks Jiménez, J.; Doerr, S.; Martínez-Rosell, G. Bioinformatics, Vol. 33, Issue 19 https://doi.org/10.1093/bioinformatics/btx350	journal	May 2017
Matplotlib: A 2D Graphics Environment Hunter, John D. Computing in Science & Engineering, Vol. 9, Issue 3 https://doi.org/10.1109/MCSE.2007.55	journal	January 2007
Segmentation of touching cell nuclei using gradient flow tracking Li, G.; Liu, T.; Nie, J. Journal of Microscopy, Vol. 231, Issue 1 https://doi.org/10.1111/j.1365-2818.2008.02016.x	journal	July 2008
seaborn: statistical data visualization Waskom, Michael Journal of Open Source Software, Vol. 6, Issue 60 https://doi.org/10.21105/joss.03021	journal	April 2021
Visualization of Lipid Droplets in the Alveolar Macrophage Cell Line MH-S with Live-cell Imaging by 3D Holotomographic Microscopy (Nanolive) Pérez-Montero, Andrea; Zaragoza, Oscar; Luque, Alfonso BIO-PROTOCOL, Vol. 13, Issue 5 https://doi.org/10.21769/BioProtoc.4629	journal	January 2023
Jupyter Notebooks – a publishing format for reproducible computational workflows Kluyver, Thomas; Ragan-Kelley, Benjamin; Perez, Fernando Positioning and Power in Academic Publishing: Players, Agents and Agendas https://doi.org/10.3233/978-1-61499-649-1-87	book	January 2021

Similar Records

YOLO2U-Net: Detection-guided 3D instance segmentation for microscopy

Journal Article · Sat Mar 23 20:00:00 EDT 2024 · Pattern Recognition Letters · OSTI ID:2333861

3D-SIFT-Flow for atlas-based CT liver image segmentation

Journal Article · Sun May 15 00:00:00 EDT 2016 · Medical Physics · OSTI ID:22620882

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
cellular imaging
image processing
machine learning

SwinCell: a 3D transformer and flow-based framework for improved cell segmentation

Citation Formats

References (26)

Similar Records

Related Subjects