danДоклады Национальной академии наук БеларусиDoklady of the National Academy of Sciences of Belarus1561-83232524-2431The Republican Unitary Enterprise Publishing House "Belaruskaya Navuka"10.29235/1561-8323-2023-67-4-315-321dan-1143Research ArticleМЕДИЦИНАMEDICINEАнализ изображений клеток коры головного мозга in vitro с применением метода глубокого обученияImage analysis of brain cortex cells in vitro using deep learning methodДенисовА. А.DenisovA. A.

Денисов Андрей Анатольевич – кандидат биологических наук, заведующий лабораторией. Белорусский государственный университет

пр. Независимости, 4, 220030, Минск

Denisov Andrey A. – Ph. D. (Biology), Head of the Laboratory

4, Nezavisimosti Ave., 220030, Minsk

an.denisov@gmail.comНикифоровА. В.NikiforovA. V.

Никифоров Антон Владимирович – стажер младший научный сотрудника

ул. Академическая, 28, 220072, Минск

Nikiforov Anton V. – Trainee Junior Researcher

Akademicheskaya Str., 220072, Minsk

sky92033@live.comБогдановаА. В.BahdanavaA. V.

Богданова Анастасия Валерьевна – младший научный сотрудник

ул. Академическая, 28, 220072, Минск

Bahdanava Anastasiya V. – Junior Researcher

Akademicheskaya Str., 220072, Minsk

bognastya23@mail.ruПашкевичС. Г.PashkevichS. G.

Пашкевич Светлана Георгиевна – кандидат биологических наук, доцент, заведующий лабораторией

ул. Академическая, 28, 220072, Минск

Pashkevich Svetlana G. – Ph. D. (Biology), Associate Professor, Head of the Laboratory

Akademicheskaya Str., 220072, Minsk

skypasht@mail.ruСердюченкоН. С.SerdyuchenkoN. S.

Сердюченко Николай Сергеевич – член-корреспондент, доктор медицинских наук, профессор

ул. Академическая, 28, 220072, Минск

Serdyuchenko Nikolai S. – Corresponding Member, D. Sc. (Medicine), Professor

Akademicheskaya Str., 220072, Minsk

temporo@mail.ruИнститут физиологии Национальной академии наук Беларуси; Белорусский государственный университетInstitute of Physiology of the National Academy of Sciences of Belarus; Belarusian State UniversityИнститут физиологии Национальной академии наук БеларусиInstitute of Physiology of the National Academy of Sciences of Belarus202301092023674315321Copyright © Денисов А.А., Никифоров А.В., Богданова А.В., Пашкевич С.Г., Сердюченко Н.С., 20232023Денисов А.А., Никифоров А.В., Богданова А.В., Пашкевич С.Г., Сердюченко Н.С.Denisov A.A., Nikiforov A.V., Bahdanava A.V., Pashkevich S.G., Serdyuchenko N.S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.belnauka.by/jour/article/view/1143

Представлен метод анализа изображений культивируемых клеток коры головного мозга для количественной оценки параметров развития биологических нейронных сетей с применением средств машинного обучения. Разработаны программные модули сегментации изображений на клетки, кластеры и нейриты с применением нейросетевой модели и метода глубокого обучения, сформирован обучающий набор изображений культивируемых нейронов и соответствующих масок сегментации. Результаты апробированы при анализе развития сети культивируемых нейронов in vitro на основе подсчета длины нейритов на различных стадиях роста культуры. Разработанные методики мониторинга процессов формирования биологических нейронных сетей на основе анализа роста нейронов в различных условиях и на различных субстратах предоставляют возможность контроля процессов дифференцировки стволовых клеток в нейрогенном направлении. Результаты могут применяться для мониторинга формирования органоидов в биоинженерных приложениях, а также при моделировании процессов регенерации нервной ткани.

The article presents a method for analyzing images of cultured cortical cells for a quantitative analysis of the parameters of development of biological neural networks using machine learning approaches. We have developed software modules for segmentation of images into cells, clusters, and neurites using the neural network model and the deep learning method; a training set of images of cultivated neurons and corresponding segmentation masks have been generated. The results were validated by analyzing the development of cultivated neurons in vitro based on the length count of neutrites at different growth stages of the culture. The developed methods for monitoring the processes of formation of biological neuronal networks based on the analysis of the neuronal growth under different conditions and on different substrates provide an opportunity to monitor the processes of stem cell differentiation in the neurogenic direction. The results can be used in monitoring the formation of organoids in bioengineering applications, as well as in modeling the processes of nerve tissue regeneration.

биологические нейронные сетисегментация изображенийглубокое обучениеbiological neural networksimage segmentationdeep learningReferencesThe application of in vitro-derived human neurons in neurodegenerative disease modeling / G. X. D’Souza [et al.] // J. Neurosci. Res. – 2021. – Vol. 99, N 1. – P. 124–140. https://doi.org/10.1002/jnr.24615D’Souza G. X., Rose S. E., Knupp A., Nicholson D. A., Keene C. D., Young J. E. The application of in vitro-derived human neurons in neurodegenerative disease modeling. Journal of Neuroscience Research, 2021, vol. 99, no. 1, pp. 124–140. https://doi.org/10.1002/jnr.24615Pacitti, D. Organs to Cells and Cells to Organoids: The Evolution of in vitro Central Nervous System Modelling / D. Pacitti, R. Privolizzi, B. E. Bax // Front. Cell. Neurosci. – 2019. – Vol. 13. https://doi.org/10.3389/fncel.2019.00129Pacitti D., Privolizzi R., Bax B. E. Organs to Cells and Cells to Organoids: The Evolution of in vitro Central Nervous System Modelling. Frontiers in Cellular Neuroscience, 2019, vol. 13. https://doi.org/10.3389/fncel.2019.00129Advances in ex vivo models and lab-on-a-chip devices for neural tissue engineering / S. Mobini [et al.] // Biomaterials. – 2019. – Vol. 198. – P. 146–166. https://doi.org/10.1016/j.biomaterials.2018.05.012Mobini S., Hye Y. S., McCrary M. W., Schmidt C. E. Advances in ex vivo models and lab-on-a-chip devices for neural tissue engineering. Biomaterials, 2019, vol. 198, pp. 146–166. https://doi.org/10.1016/j.biomaterials.2018.05.012A rapid and accurate method to quantify neurite outgrowth from cell and tissue cultures: Two image analytic approaches using adaptive thresholds or machine learning / A. Ossinger [et al.] // J. Neurosci. Methods. – 2020. – Vol. 331. – Art. 108522. https://doi.org/10.1016/j.jneumeth.2019.108522Ossinger A., Bajic A., Pan S., Andersson B., Ranefall P., Hailer N. P., Schizas N. A rapid and accurate method to quantify neurite outgrowth from cell and tissue cultures: Two image analytic approaches using adaptive thresholds or machine learning. Journal of Neuroscience Methods, 2020, vol. 331, art. 108522. https://doi.org/10.1016/j.jneumeth.2019.108522NeuriTES. Monitoring neurite changes through transfer entropy and semantic segmentation in bright-field time-lapse microscopy / A. Mencattini [et al.] // Patterns. – 2021. – Vol. 2, N 6. – Art. 100261. https://doi.org/10.1016/j.patter.2021.100261Mencattini A., Spalloni A., Casti P., Comes M. C., Giuseppe D. D., Antonelli G., D’Orazio M., Filippi J., Corsi F., Isambert H., Di Natale C., Longone P., Martinelli E. NeuriTES. Monitoring neurite changes through transfer entropy and semantic segmentation in bright-field time-lapse microscopy. Patterns, 2021, vol. 2, no. 6, art. 100261. https://doi.org/10.1016/j.patter.2021.100261U-Net and its Variants for Medical Image Segmentation: A Review of Theory and Applications / N. Siddique [et al.] // IEEE Access. – 2021. – Vol. 9. – P. 82031–82057. https://doi.org/10.1109/access.2021.3086020Siddique N., Paheding S., Elkin C. P., Devabhaktuni V. U-Net and its Variants for Medical Image Segmentation: A Review of Theory and Applications. IEEE Access, 2021, vol. 9, pp. 82031–82057. https://doi.org/10.1109/access.2021.3086020Facci, L. Culture of rodent cortical and hippocampal neurons / L. Facci, S. D. Skaper // Neurotrophic Factors. – 2012. – Vol. 846. – P. 49–56. https://doi.org/10.1007/978-1-61779-536-7_5Facci L., Skaper S. D. Culture of rodent cortical and hippocampal neurons. Neurotrophic Factors, 2012, vol. 846, pp. 49–56. https://doi.org/10.1007/978-1-61779-536-7_5Reza, A. M. Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement / A. M. Reza // J. VLSI Signal Process. Syst. Signal Image Video Technol. – 2004. – Vol. 38, N 1. – P. 35–44. https://doi.org/10.1023/b:vlsi.0000028532.53893.82Reza A. M. Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement. Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology, 2004, vol. 38, no. 1, pp. 35–44. https://doi.org/10.1023/b:vlsi.0000028532.53893.82MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy / G. Lee [et al.] // arXiv:2212.03465. – 2022. https://doi.org/10.48550/arXiv.2212.03465Lee G., Kim S., Kim J., Yun S.-Y. MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy. arXiv:2212.03465, 2022. https://doi.org/10.48550/arXiv.2212.03465Rother, C. “GrabCut”: interactive foreground extraction using iterated graph cuts / C. Rother, V. Kolmogorov, A. Blake // ACM Trans. Graph. – 2004. – Vol. 23, N 3. – P. 309–314. https://doi.org/10.1145/1015706.1015720Rother C., Kolmogorov V., Blake A. “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics, 2004, vol. 23, no. 3, pp. 309–314. https://doi.org/10.1145/1015706.1015720SNT: a unifying toolbox for quantification of neuronal anatomy / C. Arshadi [et al.] // Nat. Methods. – 2021. – Vol. 18, N 4. – P. 374–377. https://doi.org/10.1038/s41592-021-01105-7Arshadi C., Günther U., Eddison M., Harrington K. I. S., Ferreira T. A. SNT: a unifying toolbox for quantification of neuronal anatomy. Nature Methods, 2021, vol. 18, no. 4, pp. 374–377. https://doi.org/10.1038/s41592-021-01105-7Sholl analysis: a quantitative comparison of semi-automated methods / K. E. Binley [et al.] // J. Neurosci. Methods. – 2014. – Vol. 225. – P. 65–70. https://doi.org/10.1016/j.jneumeth.2014.01.017Binley K. E., Ng W. S., Tribble J. R., Song B., Morgan J. E. Sholl analysis: a quantitative comparison of semiautomated methods. Journal of Neuroscience Method, 2014, vol. 225, pp. 65–70. https://doi.org/10.1016/j.jneumeth.2014.01.017Stukel, J. M. The interplay of peptide affinity and scaffold stiffness on neuronal differentiation of neural stem cells / J. M. Stukel, R. K. Willits // Biomed. Mater. – 2018. – Vol. 13, N 2. – Art. 024102. https://doi.org/10.1088/1748-605x/aa9a4bStukel J. M., Willits R. K. The interplay of peptide affinity and scaffold stiffness on neuronal differentiation of neural stem cells. Biomedical Materials, 2018, vol. 13, no. 2, art. 024102. https://doi.org/10.1088/1748-605x/aa9a4bHuman brain organoid-on-a-chip to model prenatal nicotine exposure / Y. Wang [et al.] // Lab Chip. – 2018. – Vol. 18, N 6. – P. 851–860. https://doi.org/10.1039/c7lc01084bWang Y., Wang L., Zhu Y., Qin J. Human brain organoid-on-a-chip to model prenatal nicotine exposure. Lab on a Chip, 2018, vol. 18, no. 6, pp. 851–860. https://doi.org/10.1039/c7lc01084bCostamagna, G. Advancing Drug Discovery for Neurological Disorders Using iPSC-Derived Neural Organoids / G. Costamagna, G. P. Comi, S. Corti // Int. J. Mol. Sci. – 2021. – Vol. 22, N 5. – Art. 2659. https://doi.org/10.3390/ijms22052659Costamagna G., Comi G. P., Corti S. Advancing Drug Discovery for Neurological Disorders Using iPSC-Derived Neural Organoids. International Journal of Molecular Sciences, 2021, vol. 22, no. 5, art. 2659. https://doi.org/10.3390/ijms22052659

The authors declare that there are no conflicts of interest present.