Classification of Structural and Functional Development Stage of Cardiomyocytes Using Machine Learning Techniques
DOI:
https://doi.org/10.20535/RADAP.2024.98.55-65Keywords:
cardiomyocyte, stem cells, image processing, machine learning, machine learning problem, classification, classification accuracy, neural network, convolutional neural networkAbstract
The study is dedicated to the problem of classification of structural and functional development stage of cardiomyocytes derived from the induced pluripotent stem cells with application of the digital image processing methods and machine learning algorithms, in particular, neural networks. Cell regenerative therapy has become one of the most promising treatment options for patients with heart failure. But since cardiomyocytes are objects with a high level of complexity and have significant morphological variability, automatic classification is complicated by the lack of implemented methods. That's why researches in this area are a major global public health priority. The initial data set used in this study is a publicly open set of confocal microscopic images of cardiomyocytes which can be divided into five classes based on the morphological features (the structure of the transverse T-tubule). A small amount of input data leads to the need of using augmentation methods. Methods that prevent the alteration of the transverse T-tubule, which is an important parameter for correct classification of the development of cardiomyocytes, are used. Histogram equalization technique is used to enhance the contrast and dynamic range of the confocal microscopic images with the method of contrast-limited adaptive equalization. This helped to improve the local contrast of the analyzed images and highlight the main elements of the cardiomyocyte. Finally, Chan–Vese method, which belongs to the regional segmentation methods, is chosen for the image segmentation and removing artifacts and/or parts of other cells from the image. A pre-processed and augmented dataset is used for training of the convolutional neural network having an architecture with hierarchical structure and residual block usage. The model is evaluated based on the confusion matrix and the heat maps of different convolutional layers are analyzed. Images from the classes with a large number of mutual errors are also considered. Based on the analysis, several classes of structural and functional development of cardiomyocytes are combined. Final accuracy of the model for defining the cardiomyocytes maturation stage achieved 77%.
References
References
Lainscak, M., Spoletini, I., & Coats, A. J. (2017). Definition and Classification of Heart Failure. International Cardiovascular Forum Journal, Vol. 10, pp. 3-7, DOI: 10.17987/icfj.v10i0.419.
The top 10 causes of death. World Health Organization, date of access: 7 August 2024.
Savarese G., Becher P. M., Lund L. H., Seferovic P., Rosano G. M. C., Coats A. J. S. (2022). Global burden of heart failure: a comprehensive and updated review of epidemiology. Cardiovascular Research, Vol. 118, Iss. 17, pp. 3272–3287, doi:10.1093/cvr/cvac013.
Donald M. Bers (2001). Excitation-Contraction Coupling and Cardiac Contractile Force (2nd ed.). Kluwer Academic Publishers, 427 p., doi:10.1007/978-94-010-0658-3.
Reinecke H., Minami E., Zhu W. Z., Laflamme M. A. (2008). Cardiogenic Differentiation and Transdifferentiation of Progenitor Cells. Circulation Research, Vol. 103, Num. 10, pp. 1058–1071, doi:10.1161/CIRCRESAHA.108.180588.
Zhu W. Z., Hauch K. D., Xu C., Laflamme M. A. (2009). Human embryonic stem cells and cardiac repair. Transplant Rev (Orlando), Vol. 23, Iss. 1, pp. 53-68, doi: 10.1016/j.trre.2008.05.005.
Kupatt C., Horstkotte J., Vlastos G. A., Pfosser A., Lebherz C., Semisch M., et al. (2005). Embryonic endothelial progenitor cells expressing a broad range of pro-angiogenic and remodeling factors enhance vascularization and tissue recovery in acute and chronic ischemia. The FASEB Journal, Vol. 19, Iss. 11, doi:10.1096/fj.04-3282fje.
Caspi O., Huber I., Kehat I., Habib M., Arbel G., Gepstein A., et al. (2007). Transplantation of Human Embryonic Stem Cell-Derived Cardiomyocytes Improves Myocardial Performance in Infarcted Rat Hearts. Journal of the American College of Cardiology, Vol. 50, Iss. 19, pp. 1884-1893, doi:10.1016/j.jacc.2007.07.054.
Shimizu T., Yamato M., Kikuchi A., Okano T. (2003). Cell sheet engineering for myocardial tissue reconstruction. Biomaterials, Vol. 24, Iss. 13, pp. 2309-2316, doi:10.1016/S0142-9612(03)00110-8.
Pointon A., Harmer A. R., Dale I. L., Abi-Gerges N., Bowes J., Pollard C., Garside H. (2015). Assessment of Cardiomyocyte Contraction in Human-Induced Pluripotent Stem Cell-Derived Cardiomyocytes. Toxicological Sciences, Vol. 144, Iss. 2, pp. 227–237, doi:10.1093/toxsci/kfu312.
Zhu, W.-Z., Van Biber, B., and Laflamme, M. A. (2011). Methods for the Derivation and Use of Cardiomyocytes from Human Pluripotent Stem Cells. In: Schwartz, P., Wesselschmidt, R. (eds) Human Pluripotent Stem Cells. Methods in Molecular Biology, Vol. 767, pp. 419–431, doi:10.1007/978-1-61779-201-4_31.
Zahradnikova jr. A., Skrabanek P. (2019). Сonfocal microscopy images of cardiomyocyte development stages. IEEE DataPort, date of access: sept. 2023.
Shigang Liu, Yali Peng. (2012). A local region-based Chan–Vese model for image segmentation. Pattern Recognition, Vol. 45, Iss. 7, pp. 2769-2779, doi:10.1016/j.patcog.2011.11.019.
Getreuer P. (2012). Chan-Vese Segmentation. Image Processing On Line, Vol. 2, pp. 214–224, doi:10.5201/ipol.2012.g-cv.
Pizer S. M., Johnston R. E., Ericksen J. P., Yankaskas B. C. and Muller K. E. (1990). Contrast-limited adaptive histogram equalization: speed and effectiveness. Proceedings of the First Conference on Visualization in Biomedical Computing, pp. 337-345, doi:10.1109/VBC.1990.109340.
Vij K., Singh Y. (2009). Enhancement of Images Using Histogram Processing Techniques. Int. J. Comp. Tech. Appl., Vol. 2, iss. 2, pp. 309-313.
Shorten, C., Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, Vol. 6, Article number: 60, doi:10.1186/s40537-019-0197-0.
Gaster B. R., Howes L., Kaeli D. R., Mistry P., Schaa D. (2013). Heterogeneous Computing with OpenCL. Morgan Kaufmann Publishers Inc., 291 p.
Grossi E., Buscema M. (2007). Introduction to artificial neural networks. European Journal of Gastroenterology & Hepatology, Vol. 19, Iss. 12, pp. 1046-1054, DOI: 10.1097/MEG.0b013e3282f198a0.
Purwono, P., Ma'arif, A., Rahmaniar, W., Fathurrahman, H., Frisky, A., & Haq, Q. (2022). Understanding of Convolutional Neural Network (CNN): A Review. International Journal of Robotics and Control Systems, Vol. 2, No. 4, pp. 739-748. doi:10.31763/ijrcs.v2i4.888.
Alpaydin, E. (2010). Introduction to Machine Learning, Second Edition. The MIT Press, 579 p., ISBN 978-0-262-01243-0.
Ziaee A. and ÇAno E. (2022). Batch Layer Normalization A new normalization layer for CNNs and RNNs. ICAAI'22: Proceedings of the 2022 6th International Conference on Advances in Artificial Intelligence, pp. 40-49, doi:org/10.1145/3571560.3571566.
Ebrahimi, M. S., & Abadi, H. K. (2018). Study of Residual Networks for Image Recognition. ArXiv, doi:10.48550/arXiv.1805.00325.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Viacheslav Bondarev, Катерина Іванько, Наталія Іванушкіна
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
