Computer assisted image acquisition techniques, including confocal microscopy, require efficient tools for an automatic sorting of vast amount of generated image data. The complexity of the classification process, absence of adequate tools, and insufficient amount of reference data has made the automated processing of images challenging. Mastering of this issue would allow implementation of statistical analysis in research areas such as in research on formation of t-tubules in cardiac myocytes. We developed a system aimed at automatic assessment of cardiomyocyte development stages (SAACS). The system classifies confocal images of cardiomyocytes with fluorescent dye stained sarcolemma. We based SAACS on a densely connected convolutional network (DenseNet) topology. We created a set of labelled source images, proposed an appropriate data augmentation technique and designed a class probability graph. We showed that the DenseNet topology, in combination with the augmentation technique is suitable for the given task, and that high-resolution images are instrumental for image categorization. SAACS, in combination with the automatic high-throughput confocal imaging, will allow application of statistical analysis in the research of the tubular system development or remodelling and loss.

Department of Cellular Cardiology Inst of Experimental Endocrinology Biomedical Research Center SAS Bratislava Slovakia

Institute of Automation and Computer Science Brno University of Technology Brno Czech Republic

Institute of Molecular Physiology and Genetics Centre of Biosciences SAS Bratislava Slovakia

Zobrazit více v PubMed

Bers DM. Calcium fluxes involved in control of cardiac myocyte contraction. Circulation Research. 2000;87(4):275–281. 10.1161/01.RES.87.4.275 PubMed DOI

Franzini-Armstrong C. The relationship between form and function throughout the history of excitation–contraction coupling. The Journal of General Physiology. 2018. PubMed PMC

Louch WE, Koivumäki JT, P T. Calcium signalling in developing cardiomyocytes: implications for model systems and disease. The Journal of physiology. 2015;593(Pt 5):1047–1063. 10.1113/jphysiol.2014.274712 PubMed DOI PMC

Parikh SS, Blackwell DJ, Gomez-Hurtado N, Frisk M, Wang L, Kim K, et al. Thyroid and Glucocorticoid Hormones Promote Functional T-Tubule Development in Human-Induced Pluripotent Stem Cell-Derived Cardiomyocytes. Circulation Research. 2017;121(12):1323–1330. 10.1161/CIRCRESAHA.117.311920 PubMed DOI PMC

Macková K, Zahradníková A, Hot́ka M, Hoffmannová B, Zahradník I, Zahradníková A. Calcium release-dependent inactivation precedes formation of the tubular system in developing rat cardiac myocytes. European Biophysics Journal. 2017;46(8):691–703. 10.1007/s00249-017-1249-z PubMed DOI

High-Throughput Calcium and Contractility System; 2018. Available from: http://www.ionoptix.com/wp-content/uploads/2017/11/multicell_online.pdf.

Klimas A, Ambrosi CM, Yu J, Williams JC, Bien H, Entcheva E. OptoDyCE as an automated system for high-throughput all-optical dynamic cardiac electrophysiology. Nature Communications. 2016;7(11542):1–12. PubMed PMC

Guo A, Song LS. AutoTT: automated detection and analysis of T-tubule architecture in cardiomyocytes. Biophysical Journal. 2014;106(12):2729–2736. 10.1016/j.bpj.2014.05.013 PubMed DOI PMC

Frisk M, Ruud M, Espe EKS, Aronsen JM, Røe ÅT, Zhang L, et al. Elevated ventricular wall stress disrupts cardiomyocyte t-tubule structure and calcium homeostasis. Cardiovascular Research. 2016;112(1):443–451. 10.1093/cvr/cvw111 PubMed DOI PMC

Singh JK, Barsegyan V, Bassi N, Marszalec W, Tai S, Mothkur S, et al. T-tubule remodeling and increased heterogeneity of calcium release during the progression to heart failure in intact rat ventricle. Physiological Reports. 2017;5(24):e13540 10.14814/phy2.13540 PubMed DOI PMC

Zhang C, Chen B, Wang Y, Guo A, Tang Y, Khataei T, et al. MG53 is dispensable for T-tubule maturation but critical for maintaining T-tubule integrity following cardiac stress. Journal of Molecular and Cellular Cardiology. 2017;112:123–130. 10.1016/j.yjmcc.2017.08.007 PubMed DOI PMC

DiCarlo JJ, Zoccolan D, Rust NC. How does the brain solve visual object recognition? Neuron. 2012;73(3):415–434. 10.1016/j.neuron.2012.01.010 PubMed DOI PMC

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. 10.1038/nature14539 PubMed DOI

Pinto N, Cox DD, DiCarlo JJ. Why is Real-World Visual Object Recognition Hard? PLOS Computational Biology. 2008;4(1):1–6. 10.1371/journal.pcbi.0040027 PubMed DOI PMC

Lemnaru C, Potolea R. Imbalanced Classification Problems: Systematic Study, Issues and Best Practices In: Enterprise Information Systems. Berlin, Heidelberg: Springer Berlin Heidelberg; 2012. p. 35–50.

Gao Z, Wang L, Zhou L, Zhang J. HEp-2 Cell Image Classification With Deep Convolutional Neural Networks. IEEE Journal of Biomedical and Health Informatics. 2017;21(2):416–428. 10.1109/JBHI.2016.2526603 PubMed DOI

Xu Y, Jia Z, Ai Y, Zhang F, Lai M, Chang EI. Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2015. p. 947–951.

Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, et al. Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? IEEE Transactions on Medical Imaging. 2016;35(5):1299–1312. 10.1109/TMI.2016.2535302 PubMed DOI

Zeiler MD, Fergus R. Visualizing and Understanding Convolutional Networks In: Computer Vision—ECCV 2014. Cham: Springer International Publishing; 2014. p. 818–833.

Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR. 2014;abs/1409.1556.

Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM. 2017;60(6):84–90. 10.1145/3065386 DOI

Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks. 1994;5(2):157–166. 10.1109/72.279181 PubMed DOI

Xu M, Papageorgiou DP, Abidi SZ, Dao M, Zhao H, Karniadakis GE. A deep convolutional neural network for classification of red blood cells in sickle cell anemia. PLOS Computational Biology. 2017;13(10):1–27. 10.1371/journal.pcbi.1005746 PubMed DOI PMC

Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015. p. 1–9.

Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. p. 2818–2826.

Srivastava RK, Greff K, Schmidhuber J. Training Very Deep Networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems—Volume 2. NIPS’15. Cambridge, MA, USA: MIT Press; 2015. p. 2377–2385.

He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. p. 770–778.

He K, Zhang X, Ren S, Sun J. Identity Mappings in Deep Residual Networks In: Computer Vision—ECCV 2016. Cham: Springer International Publishing; 2016. p. 630–645.

Huang G, Sun Y, Liu Z, Sedra D, Weinberger KQ. Deep Networks with Stochastic Depth In: Leibe B, Matas J, Sebe N, Welling M, editors. Computer Vision—ECCV 2016. Cham: Springer International Publishing; 2016. p. 646–661.

Han D, Kim J, Kim J. Deep Pyramidal Residual Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017. p. 6307–6315.

Huang G, Liu Z, v d Maaten L, Weinberger KQ. Densely Connected Convolutional Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017. p. 2261–2269.

Yu Z, Li T, Luo G, Fujita H, Yu N, Pan Y. Convolutional networks with cross-layer neurons for image recognition. Information Sciences. 2018;433-434:241–254. 10.1016/j.ins.2017.12.045 DOI

Wang S, Liu W, Wu J, Cao L, Meng Q, Kennedy PJ. Training deep neural networks on imbalanced data sets. In: 2016 International Joint Conference on Neural Networks (IJCNN); 2016. p. 4368–4374.

Škrabánek P, Doležel P. On reporting performance of binary classifiers. Scientific Papers of the University of Pardubice, Series D: Faculty of Economics and Administration. 2017;24(41):181–192.

Zahradníková jr A, Škrabánek P. Confocal Microscopy Images of Cardiomyocyte Development Stages; 2019. Available from: 10.6084/m9.figshare.8063369. PubMed DOI PMC

Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015. vol. 37 of Proceedings of Machine Learning Research. PMLR; 2015. p. 448–456.

Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Information Processing & Management. 2009;45(4):427–437. 10.1016/j.ipm.2009.03.002 DOI

Ruder S. An overview of gradient descent optimization algorithms. CoRR. 2016;abs/1609.04747.

Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems; 2015. Available from: https://www.tensorflow.org/.

Automatic assessment of the cardiomyocyte development stages from confocal microscopy images using deep convolutional networks