CellVisioner: A Generalizable Cell Virtual Staining Toolbox Based on Few-Shot Transfer Learning for Mechanobiological Analysis

Overview

Journal Research (Wash D C)

Specialty Biology

Date 2024 Mar 4

PMID 38434246

Authors

Xiayu Xu

Zhanfeng Xiao

Fan Zhang

Changxiang Wang

Bo Wei

Yaohui Wang

Bo Cheng

Yuanbo Jia

Yuan Li

Bin Li

Hui Guo

Feng Xu

Affiliations

Soon will be listed here.

Abstract

Visualizing cellular structures especially the cytoskeleton and the nucleus is crucial for understanding mechanobiology, but traditional fluorescence staining has inherent limitations such as phototoxicity and photobleaching. Virtual staining techniques provide an alternative approach to addressing these issues but often require substantial amount of user training data. In this study, we develop a generalizable cell virtual staining toolbox (termed CellVisioner) based on few-shot transfer learning that requires substantially reduced user training data. CellVisioner can virtually stain F-actin and nuclei for various types of cells and extract single-cell parameters relevant to mechanobiology research. Taking the label-free single-cell images as input, CellVisioner can predict cell mechanobiological status (e.g., Yes-associated protein nuclear/cytoplasmic ratio) and perform long-term monitoring for living cells. We envision that CellVisioner would be a powerful tool to facilitate on-site mechanobiological research.

References

Skylaki S, Hilsenbeck O, Schroeder T . Challenges in long-term imaging and quantification of single-cell dynamics. Nat Biotechnol. 2016; 34(11):1137-1144. DOI: 10.1038/nbt.3713. View

Kandel M, He Y, Lee Y, Chen T, Sullivan K, Aydin O . Phase imaging with computational specificity (PICS) for measuring dry mass changes in sub-cellular compartments. Nat Commun. 2020; 11(1):6256. PMC: 7721808. DOI: 10.1038/s41467-020-20062-x. View

Liu Y, Yuan H, Wang Z, Ji S . Global Pixel Transformers for Virtual Staining of Microscopy Images. IEEE Trans Med Imaging. 2020; 39(6):2256-2266. DOI: 10.1109/TMI.2020.2968504. View

Rice A, Cortes E, Lachowski D, Cheung B, Karim S, Morton J . Matrix stiffness induces epithelial-mesenchymal transition and promotes chemoresistance in pancreatic cancer cells. Oncogenesis. 2017; 6(7):e352. PMC: 5541706. DOI: 10.1038/oncsis.2017.54. View

Heinrich L, Bennett D, Ackerman D, Park W, Bogovic J, Eckstein N . Whole-cell organelle segmentation in volume electron microscopy. Nature. 2021; 599(7883):141-146. DOI: 10.1038/s41586-021-03977-3. View

Qin X, Zhang Y, He Y, Chen K, Zhang Y, Li P . Shear stress triggered circular dorsal ruffles formation to facilitate cancer cell migration. Arch Biochem Biophys. 2021; 709:108967. DOI: 10.1016/j.abb.2021.108967. View

Schlemper J, Oktay O, Schaap M, Heinrich M, Kainz B, Glocker B . Attention gated networks: Learning to leverage salient regions in medical images. Med Image Anal. 2019; 53:197-207. PMC: 7610718. DOI: 10.1016/j.media.2019.01.012. View

Strack R . Imaging without the labels. Nat Methods. 2022; 19(1):30. DOI: 10.1038/s41592-021-01376-0. View

Jo Y, Cho H, Park W, Kim G, Ryu D, Kim Y . Label-free multiplexed microtomography of endogenous subcellular dynamics using generalizable deep learning. Nat Cell Biol. 2021; 23(12):1329-1337. DOI: 10.1038/s41556-021-00802-x. View

10.

Rivenson Y, Wang H, Wei Z, de Haan K, Zhang Y, Wu Y . Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning. Nat Biomed Eng. 2019; 3(6):466-477. DOI: 10.1038/s41551-019-0362-y. View

11.

Ounkomol C, Seshamani S, Maleckar M, Collman F, Johnson G . Label-free prediction of three-dimensional fluorescence images from transmitted-light microscopy. Nat Methods. 2018; 15(11):917-920. PMC: 6212323. DOI: 10.1038/s41592-018-0111-2. View

12.

Wu P, Gilkes D, Phillip J, Narkar A, Cheng T, Marchand J . Single-cell morphology encodes metastatic potential. Sci Adv. 2020; 6(4):eaaw6938. PMC: 6976289. DOI: 10.1126/sciadv.aaw6938. View

13.

Ma J, Fong S, Luo Y, Bakkenist C, Shen J, Mourragui S . Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients. Nat Cancer. 2021; 2(2):233-244. PMC: 8248912. DOI: 10.1038/s43018-020-00169-2. View

14.

Peng Y, Chen Z, Chen Y, Li S, Jiang Y, Yang H . ROCK isoforms differentially modulate cancer cell motility by mechanosensing the substrate stiffness. Acta Biomater. 2019; 88:86-101. DOI: 10.1016/j.actbio.2019.02.015. View

15.

Moen E, Bannon D, Kudo T, Graf W, Covert M, Van Valen D . Deep learning for cellular image analysis. Nat Methods. 2019; 16(12):1233-1246. PMC: 8759575. DOI: 10.1038/s41592-019-0403-1. View

16.

Nia H, Munn L, Jain R . Physical traits of cancer. Science. 2020; 370(6516). PMC: 8274378. DOI: 10.1126/science.aaz0868. View

17.

Stumpf P, Du X, Imanishi H, Kunisaki Y, Semba Y, Noble T . Transfer learning efficiently maps bone marrow cell types from mouse to human using single-cell RNA sequencing. Commun Biol. 2020; 3(1):736. PMC: 7718277. DOI: 10.1038/s42003-020-01463-6. View

18.

Wang H, Zhou Y, Zhang J, Lei J, Sun D, Xu F . Anomaly segmentation in retinal images with poisson-blending data augmentation. Med Image Anal. 2022; 81:102534. DOI: 10.1016/j.media.2022.102534. View

19.

Allen M, Thomas G, Clark S, Dawoud M, Vallath S, Payne S . Altered microenvironment promotes progression of preinvasive breast cancer: myoepithelial expression of αvβ6 integrin in DCIS identifies high-risk patients and predicts recurrence. Clin Cancer Res. 2013; 20(2):344-57. DOI: 10.1158/1078-0432.CCR-13-1504. View

20.

Zhang C, Zhu H, Ren X, Gao B, Cheng B, Liu S . Mechanics-driven nuclear localization of YAP can be reversed by N-cadherin ligation in mesenchymal stem cells. Nat Commun. 2021; 12(1):6229. PMC: 8553821. DOI: 10.1038/s41467-021-26454-x. View