PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI

Junhan Zhao; Xiyue Wang; Junyou Zhu; Chijioke Chukwudi; Andrew Finebaum; Jun Zhang; Sen Yang; Shijie He; Nima Saeidi

doi:10.1038/s41377-023-01296-y

Go to Nature Website

Your Location：

Home >

Browse articles >

PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI

Original Articles

- PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI
- Light: Science & Applications Vol. 12, Issue 12, Pages: 2811-2825(2023)
- Affiliations：
  
  1.Division of Gastrointestinal and Oncologic Surgery, Department of Surgery, Massachusetts General Hospital, Boston, MA 02114, USA
  2.Department of Surgery, Center for Engineering in Medicine and Surgery, Massachusetts General Hospital, Boston, MA 02114, USA
  3.Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA
  4.Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
  5.College of Biomedical Engineering, Sichuan University, Chengdu, Sichuan 610065, China
  6.Shriners Hospital for Children—Boston, Boston, MA 02114, USA
  7.Tencent AI Lab, Shenzhen, Guangdong 518057, China
  8.Harvard Stem Cell Institute, Cambridge, MA 02138, USA
- Author bio：
  
  Shijie He (she9@mgh.harvard.edu)
  Nima Saeidi (nsaeidi@mgh.harvard.edu)
- Funds：
- DOI：10.1038/s41377-023-01296-y
  CLC：
- Published：31 December 2023，
  
  Published Online：14 December 2023，
  
  Received：10 April 2023，
  
  Revised：02 September 2023，
  
  Accepted：24 September 2023
- Accepted：
Scan QR Code
Zhao, J. H. et al. PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI. Light: Science & Applications, 12, 2811-2825 (2023).
DOI：

Zhao, J. H. et al. PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI. Light: Science & Applications, 12, 2811-2825 (2023). DOI： 10.1038/s41377-023-01296-y.

摘要

Abstract

Organoid models have provided a powerful platform for mechanistic investigations into fundamental biological processes involved in the development and function of organs. Despite the potential for image-based phenotypic quantification of organoids

their complex 3D structure

and the time-consuming and labor-intensive nature of immunofluorescent staining present significant challenges. In this work

we developed a virtual painting system

PhaseFIT (phase-fluorescent image transformation) utilizing customized and morphologically rich 2.5D intestinal organoids

which generate virtual fluorescent images for phenotypic quantification via accessible and low-cost organoid phase images. This system is driven by a novel segmentation-informed deep generative model that specializes in segmenting overlap and proximity between objects. The model enables an annotation-free digital transformation from phase-contrast to multi-channel fluorescent images. The virtual painting results of nuclei

secretory cell markers

and stem cells demonstrate that PhaseFIT outperforms the existing deep learning-based stain transformation models by generating fine-grained visual content. We further validated the efficiency and accuracy of PhaseFIT to quantify the impacts of three compounds on crypt formation

cell population

and cell stemness. PhaseFIT is the first deep learning-enabled virtual painting system focused on live organoids

enabling large-scale

informative

and efficient organoid phenotypic quantification. PhaseFIT would enable the use of organoids in high-throughput drug screening applications.

关键词

Keywords

references

Kim, C. J. et al. l-Tryptophan exhibits therapeutic function in a porcine model of dextran sodium sulfate (DSS)-induced colitis.J. Nutr. Biochem.21, 468–475 (2010)..

Okayasu, I. et al. A novel method in the induction of reliable experimental acute and chronic ulcerative colitis in mice.Gastroenterology98, 694–702 (1990)..

Xu, X. et al. Histological and ultrastructural changes of the colon in dextran sodium sulfate‑induced mouse colitis.Exp. Ther. Med.20, 1987–1994 (2020)..

Carlsson, A. H. et al.Faecalibacterium prausnitziisupernatant improves intestinal barrier function in mice DSS colitis.Scand. J. Gastroenterol.48, 1136–1144 (2013)..

Azuma, Y.-T. et al. PPARα contributes to colonic protection in mice with DSS-induced colitis.Int. Immunopharmacol.10, 1261–1267 (2010)..

Sato, T. et al. Paneth cells constitute the niche for Lgr5 stem cells in intestinal crypts.Nature469, 415–418 (2011)..

He, S. et al. Stiffness restricts the stemness of the intestinal stem cells and skews their differentiation towards goblet cells.Gastroenterology164, 1137–1151. e15 (2023)..

Vlachogiannis, G. et al. Patient-derived organoids model treatment response of metastatic gastrointestinal cancers.Science359, 920–926 (2018)..

Kim, J., Koo, B.-K.&Knoblich, J. A. Human organoids: model systems for human biology and medicine.Nat. Rev. Mol. Cell Biol.21, 571–584 (2020)..

Gaudio, E. et al. Dextran sulfate sodium (DSS) colitis in rats (clinical, structural, and ultrastructural aspects).Dig. Dis. Sci.44, 1458–1475 (1999)..

Pérez-González, C. et al. Mechanical compartmentalization of the intestinal organoid enables crypt folding and collective cell migration.Nat. Cell Biol.23, 745–757 (2021)..

Thorne, C. A. et al. Enteroid monolayers reveal an autonomous WNT and BMP circuit controlling intestinal epithelial growth and organization.Dev. Cell44, 624–633. e624 (2018)..

Goodfellow, I. et al. Generative adversarial networks.Commun. ACM63, 139–144 (2020)..

Hu, C. et al. Live-dead assay on unlabeled cells using phase imaging with computational specificity.Nat. Commun.13, 713 (2022)..

Zeng, Y., Fu, J., Chao, H.&Guo, B. Aggregated contextual transformations for high-resolution image inpainting.IEEE Trans. Vis. Comput. Graph.29, 3266–3280 (2022)..

Bry, L. et al. Paneth cell differentiation in the developing intestine of normal andtransgenic mice.Proc. Natl Acad. Sci. USA91, 10335–10339 (1994)..

Nagatake, T., Fujita, H., Minato, N.&Hamazaki, Y. Enteroendocrine cells are specifically marked by cell surface expression of claudin-4 in mouse small intestine.PLoS ONE9, e90638 (2014)..

Fischer, J. et al. Characterization of glycoconjugates of human gastrointestinal mucosa by lectins. I. Histochemical distribution of lectin binding sites in normal alimentary tract as well as in benign and malignant gastric neoplasms.J. Histochem. Cytochem.32, 681–689 (1984)..

Vermeulen, L.&Snippert, H. J. Stem cell dynamics in homeostasis and cancer of the intestine.Nat. Rev. Cancer14, 468–480 (2014)..

Ghahremani, P. et al. Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification.Nat. Mach. Intell.4, 401–412 (2022)..

Isola, P., Zhu, J.-Y, Zhou, T.&Efros, A. Image-to-Image Translation with Conditional Adversarial Networks. In2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)5967–5976 (Honolulu, HI, USA, 2017).

Zhu, J.-Y., Park, T., Isola, P.&Efros, A. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks.In 2017 IEEE International Conference on Computer Vision (ICCV)2242-2251 (Venice, Italy, 2017). .

de Haan, K. et al. Deep learning-based transformation of H&E stained tissues into special stains.Nat. Commun.12, 4884 (2021)..

Rivenson, Y. et al. Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning.Nat. Biomed. Eng.3, 466–477 (2019)..

Zhang, Y. et al. Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissue.Light Sci. Appl.9, 78 (2020)..

Rivenson, Y. et al. PhaseStain: the digital staining of label-free quantitative phase microscopy images using deep learning.Light Sci. Appl.8, 23 (2019)..

Zou, K. H. et al. Statistical validation of image segmentation quality based on a spatial overlap index1: scientific reports.Acad. Radiol.11, 178–189 (2004)..

Hicks, S. A. et al. On evaluation metrics for medical applications of artificial intelligence.Sci. Rep.12, 5979 (2022)..

Wang, Z., Bovik, A. C., Sheikh, H. R.&Simoncelli, E. P. Image quality assessment: from error visibility to structural similarity.IEEE Trans. Image Process13, 600–612, https://doi.org/10.1109/tip.2003.819861 (2004)..

van Es, J. H. et al. Notch/γ-secretase inhibition turns proliferative cells in intestinal crypts and adenomas into goblet cells.Nature435, 959–963 (2005)..

Yin, X. et al. Niche-independent high-purity cultures of Lgr5+ intestinal stem cells and their progeny.Nat. Methods11, 106 (2014)..

Walton, K. D. et al. Villification in the mouse: Bmp signals control intestinal villus patterning.Development143, 427–436 (2016)..

Mahmud, M., Kaiser, M. S., McGinnity, T. M.&Hussain, A. Deep learning in mining biological data.Cogn. Comput.13, 1–33 (2021)..

Wainberg, M., Merico, D.&Delong, A. et al. Deep learning in biomedicine.Nat Biotechnol.36, 829–838 (2018)..

Barker, N. et al. Identification of stem cells in small intestine and colon by marker gene Lgr5.Nature449, 1003–1007 (2007)..

He, S. et al. The tumor suppressor p53 can promote collective cellular migration.PLoS ONE14, e0202065 (2019)..

Cohen, J. P., Luck, M.&Honari, S. InMedical Image Computing and Computer Assisted Intervention—MICCAI 2018, Vol. 11070 (eds Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C., Fichtinger, G.) Lecture Notes in Computer Science (Springer, Cham, 2018). .

Hu, J., Shen, L.&Sun, G. inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7132–7141.

Yeung, M., Sala, E., Sch"nlieb, C. B.&Rundo, L. Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation.Computerized Medical Imaging and Graphics95, 102026 (2022)..

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰