Semi-automatic method of annotating phase-contrast images of live cell cultures for nuclei segmentation based on machine learning

This study developed a comprehensive approach for identifying live cell nuclei in images without fluorescent labels. Since cell biology involves counting cells and assessing cell growth dynamics and confluence, it is expedient to automate the collection of this data. Machine learning algorithms are used for automation, which must be trained on images of specific cell cultures. Training algorithms is a labor-intensive process and requires lengthy manual annotation. Also, available machine learning-based analysis methods have low accuracy in identifying living cells without fluorescent staining. Aim of the study. To simplify the creation of a dataset of annotated cells with subsequent training of algorithms on images of living cell cultures. Materials and methods. The methodology involved the use of convolutional neural networks based on an algorithm for segmenting cell nuclei in fluorescent and histological images using StarDist. To create annotated phase-contrast images of cell cultures, samples were stained with the nuclear fluorescent dye DAPI, followed by the rejection of poor-quality images using classification in the Cellprofiler Analyst program. The StarDist-based model was trained on 1,130 images of automatically annotated nuclei in phase-contrast images of human respiratory tract epithelial cell cultures, obtained with a 10x lens, 1,600x1,200 pixels in size, and 16-bit color depth. Results. The resulting model showed good accuracy (F₁ = 0.765) in segmenting nuclei on the validation dataset. The model was used to determine the population doubling time of the epithelial cell culture population. Conclusion. The developed approach made it possible to create annotations and train a machine learning model to obtain data without the use of fluorescent labels (“label-free”) on live cell cultures.

1. Ayanzadeh A., Yağar H.O., Özuysal Ö.Y., Okvur D.P., Töreyin B.U., Ünay D., Önal S. Cell segmentation of 2D phase-contrast microscopy images with deep learning method // 2019 Medical Technologies Congress (TIPTEKNO). IEEE, 2019. P. 1–4.

2. Kirillov A., Mintun E., Ravi N., Mao H., Rolland C., Gustafson L., et al. Segment anything // Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023. P. 4015–4026.

3. Kakumani A.K., Padma Sree L. A Deep Learning Approach for Segmenting Time-Lapse Phase Contrast Images of NIH 3T3 Fibroblast Cells // New Trends in Computational Vision and Bio-inspired Computing: Selected works presented at the ICCVBIC 2018, Coimbatore, India. Cham: Springer International Publishing, 2020. P. 855–862.

4. Shamshad F., Khan S., Zamir S.W., Khan M.H., Hayat M., Khan F.S., Fu H. Transformers in medical imaging: A survey // Medical Image Analysis. 2023. Vol. 88. P. 102802.

5. Greenwald N.F., Miller G., Moen E., Kong A., Kagel A., Dougherty T., et al. Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning // Nature Biotechnology. 2022. Vol. 40, № 4. P. 555–565.

6. Stringer C., Wang T., Michaelos M., Pachitariu M. Cellpose: a generalist algorithm for cellular segmentation // Nature Methods. 2021. Vol. 18, № 1. P. 100–106.

7. Lee M.Y., Bedia J.S., Bhate S.S., Barlow G.L., Phillips D., Fantl W.J., et al. CellSeg: a robust, pre-trained nucleus segmentation and pixel quantification software for highly multiplexed fluorescence images // BMC Bioinformatics. 2022. Vol. 23, № 1. P. 46.

8. Holme B., Bjørnerud B., Pedersen N.M., de la Ballina L.R., Wesche J., Haugsten E.M. Automated tracking of cell migration in phase contrast images with CellTraxx // Scientific Reports. 2023. Vol. 13, № 1. P. 22982.

9. Hörst F., Rempe M., Heine L., Seibold C., Keyl J., Baldini G., et al. Cellvit: Vision transformers for precise cell segmentation and classification // Medical Image Analysis. 2024. Vol. 94. P. 103143.

10. Berg S., Kutra D., Kroeger T., Straehle C.N., Kausler B.X., Haubold C., et al. Ilastik: interactive machine learning for (bio) image analysis // Nature Methods. 2019. Vol. 16, № 12. P. 1226–1232.

11. Ali R., Gooding M., Szilágyi T., Vojnovic B., Christlieb M., Brady M. Automatic segmentation of adherent biological cell boundaries and nuclei from brightfield microscopy images // Machine Vision and Applications. 2012. Vol. 23, № 4. P. 607–621.

12. Cross-Zamirski J.O., Mouchet E., Williams G., Schönlieb C.B., Turkki R., Wang Y. Label-free prediction of cell painting from brightfield images // Scientific Reports. 2022. Vol. 12, № 1. P. 10001.

13. Pachitariu M., Stringer C. Cellpose 2.0: how to train your own model // Nature Methods. 2022. Vol. 19, № 12. P. 1634–1641.

14. Demchenko A., Belova L., Balyasin M., Kochergin-Nikitsky K., Kondrateva E., Voronina E., et al. Airway basal cells from human-induced pluripotent stem cells: a new frontier in cystic fibrosis research // Frontiers in Cell and Developmental Biology. 2024. Vol. 12. P. 1336392.

15. Stirling D.R., Swain-Bowden M.J., Lucas A.M., Carpenter A.E., Cimini B.A., Goodman A. Cell-Profiler 4: improvements in speed, utility and usability // BMC Bioinformatics. 2021. Vol. 22, № 1. P. 433.

16. Stirling D.R., Carpenter A.E., Cimini B.A. CellProfiler Analyst 3.0: accessible data exploration and machine learning for image analysis // Bioinformatics. 2021. Vol. 37, № 21. P. 3992–3994.

17. Schmidt U., Weigert M., Broaddus C., Myers G. Cell detection with star-convex polygons // International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2018. P. 265–273.

18. Tsai H.F., Gajda J., Sloan T.F., Rares A., Shen A.Q. Usiigaci: Instance-aware cell tracking in stain-free phase contrast microscopy enabled by machine learning // SoftwareX. 2019. Vol. 9. P. 230–237.

19. Fazeli E., Roy N.H., Follain G., Laine R.F., von Chamier L., Hänninen P.E., et al. Automated cell tracking using StarDist and TrackMate // F1000Research. 2020. Vol. 9. P. 1279.

20. Moen E., Borba E., Miller G., Schwartz M., Bannon D., Koe N., et al. Accurate cell tracking and lineage construction in live-cell imaging experiments with deep learning // bioRxiv. 2019. 803205.