{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T09:49:26Z","timestamp":1743846566816,"version":"3.37.3"},"reference-count":48,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministerium f\u00fcr Kultur und Wissenschaft","award":["NW21-059A"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"Novel neural network models that can handle complex tasks with fewer examples than before are being developed for a wide range of applications. In some fields, even the creation of a few labels is a laborious task and impractical, especially for data that require more than a few seconds to generate each label. In the biotechnological domain, cell cultivation experiments are usually done by varying the circumstances of the experiments, seldom in such a way that hand-labeled data of one experiment cannot be used in others. In this field, exact cell counts are required for analysis, and even by modern standards, semi-supervised models typically need hundreds of labels to achieve acceptable accuracy on this task, while classical image processing yields unsatisfactory results. We research whether an unsupervised learning scheme is able to accomplish this task without manual labeling of the given data. We present a VAE-based Siamese architecture that is expanded in a cyclic fashion to allow the use of labeled synthetic data. In particular, we focus on generating pseudo-natural images from synthetic images for which the target variable is known to mimic the existence of labeled natural data. We show that this learning scheme provides reliable estimates for multiple microscopy technologies and for unseen data sets without manual labeling. We provide the source code as well as the data we use. The code package is open source and free to use (MIT licensed).<\/jats:p>","DOI":"10.3390\/a16040205","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T08:51:01Z","timestamp":1681289461000},"page":"205","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Cyclic Siamese Networks Automating Cell Imagery Analysis"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3809-2356","authenticated-orcid":false,"given":"Dominik","family":"Stallmann","sequence":"first","affiliation":[{"name":"Faculty of Technology, University of Bielefeld, Universit\u00e4tsstra\u00dfe 25, 33615 Bielefeld, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-5591","authenticated-orcid":false,"given":"Barbara","family":"Hammer","sequence":"additional","affiliation":[{"name":"Faculty of Technology, University of Bielefeld, Universit\u00e4tsstra\u00dfe 25, 33615 Bielefeld, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1039\/D1LC01030A","article-title":"Recent advances in microfluidic devices for single-cell cultivation: methods and applications","volume":"22","author":"Anggraini","year":"2022","journal-title":"Lab Chip"},{"key":"ref_2","unstructured":"Sachs, C.C. (2018). Online high throughput microfluidic single cell analysis for feed-back experimentation. [Ph.D. Thesis, Technische Hochschule Aachen]. RWTH-2018-231907."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3632","DOI":"10.1093\/bioinformatics\/btab386","article-title":"Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation","volume":"37","author":"Stallmann","year":"2020","journal-title":"Bioinformatics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8423","DOI":"10.1007\/s00521-022-08115-2","article-title":"Novel transfer learning schemes based on Siamese networks and synthetic data","volume":"35","author":"Kenneweg","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1093\/bioinformatics\/bty776","article-title":"When a single lineage is not enough: Uncertainty-Aware Tracking for spatio-temporal live-cell image analysis","volume":"35","author":"Theorell","year":"2019","journal-title":"Bioinformatics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1038\/s41467-021-22078-3","article-title":"Qualitative similarities and differences in visual object representations between brains and deep networks","volume":"12","author":"Jacob","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_7","first-page":"3042064","article-title":"Deep Learning Advances in Computer Vision with 3D Data: A Survey","volume":"50","author":"Ioannidou","year":"2017","journal-title":"ACM Comput. Surv."},{"key":"ref_8","unstructured":"Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., and Culotta, A. Learning To Count Objects in Images. Proceedings of the Advances in Neural Information Processing Systems 23."},{"key":"ref_9","unstructured":"Razzak, M.I., Naz, S., and Zaib, A. (2018). Classification in BioApps: Automation of Decision Making, Springer."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1038\/s41592-019-0403-1","article-title":"Deep learning for cellular image analysis","volume":"16","author":"Moen","year":"2019","journal-title":"Nat. Methods"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1038\/nmeth.4473","article-title":"An objective comparison of cell-tracking algorithms","volume":"14","author":"Ulman","year":"2017","journal-title":"Nat. Methods"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1038\/s41592-019-0582-9","article-title":"ilastik: interactive machine learning for (bio)image analysis","volume":"16","author":"Berg","year":"2019","journal-title":"Nat. Methods"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1038\/s41592-018-0069-0","article-title":"Quanti.us: a tool for rapid, flexible, crowd-based annotation of images","volume":"15","author":"Hughes","year":"2018","journal-title":"Nat. Methods"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1016\/j.tibtech.2018.11.007","article-title":"Heterogeneity Studies of Mammalian Cells for Bioproduction: From Tools to Application","volume":"37","author":"Schmitz","year":"2019","journal-title":"Trends Biotechnol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1038\/s41592-018-0194-9","article-title":"Deep learning to predict microscope images","volume":"15","author":"Brent","year":"2018","journal-title":"Nat. Methods"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41592-018-0261-2","article-title":"U-Net: deep learning for cell counting, detection, and morphometry","volume":"16","author":"Falk","year":"2019","journal-title":"Nat. Methods"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1039\/b605937f","article-title":"Dynamic single cell culture array","volume":"6","author":"Wu","year":"2006","journal-title":"Lab Chip"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4732","DOI":"10.1039\/c2lc40569e","article-title":"Vacuum-assisted cell loading enables shear-free mammalian microfluidic culture","volume":"12","author":"Kolnik","year":"2012","journal-title":"Lab Chip"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1007\/978-3-319-10578-9_33","article-title":"Interactive Object Counting","volume":"Volume 8691","author":"Fleet","year":"2014","journal-title":"Computer Vision\u2014ECCV 2014"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.media.2015.03.002","article-title":"Detecting overlapping instances in microscopy images using extremal region trees","volume":"27","author":"Arteta","year":"2016","journal-title":"Med Image Anal."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1109\/LRA.2017.2651944","article-title":"Counting Apples and Oranges With Deep Learning: A Data-Driven Approach","volume":"2","author":"Chen","year":"2017","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1080\/21681163.2016.1149104","article-title":"Microscopy cell counting and detection with fully convolutional regression networks","volume":"6","author":"Xie","year":"2018","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"767897","DOI":"10.3389\/fcell.2021.767897","article-title":"MapCell: Learning a Comparative Cell Type Distance Metric with Siamese Neural Nets With Applications Toward Cell-Type Identification Across Experimental Datasets","volume":"9","author":"Koh","year":"2021","journal-title":"Front. Cell Dev. Biol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., P\u00e9rez-Torr\u00f3, G., and Franco-Salvador, M. (2022, January 22\u201327). Few-Shot Learning with Siamese Networks and Label Tuning. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-long.584"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yang, L., Chen, Y., Song, S., Li, F., and Huang, G. (2021). Deep Siamese Networks Based Change Detection with Remote Sensing Images. Remote. Sens., 13.","DOI":"10.3390\/rs13173394"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mehmood, A., Maqsood, M., Bashir, M., and Shuyuan, Y. (2020). A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease. Brain Sci., 10.","DOI":"10.3390\/brainsci10020084"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Figueroa-Mata, G., and Mata-Montero, E. (2020). Using a Convolutional Siamese Network for Image-Based Plant Species Identification with Small Datasets. Biomimetics, 5.","DOI":"10.3390\/biomimetics5010008"},{"key":"ref_28","unstructured":"Tan, M., and Le, Q.V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Rahman, M.S., and Islam, M.R. (2013, January 22\u201323). Counting objects in an image by marker controlled watershed segmentation and thresholding. Proceedings of the 3rd IEEE International Advance Computing Conference (IACC), Ghaziabad, India.","DOI":"10.1109\/IAdCC.2013.6514407"},{"key":"ref_30","unstructured":"Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., and Houlsby, N. (2019). Large Scale Learning of General Visual Representations for Transfer. arXiv."},{"key":"ref_31","first-page":"8868","article-title":"Almost Unsupervised Learning for Dense Crowd Counting","volume":"33","author":"Sam","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nfeld, E., Ebrahimi, S., Sinha, S., Darrell, T., and Akata, Z. (2019). Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders. arXiv.","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref_33","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., and Zisserman, A. (2018, January 7). Synthetic data and artificial neural networks for natural scene text recognition. Proceedings of the Workshop on Deep Learning, Advances in Neural Information Processing Systems (NIPS); Palais des Congr\u00e8s de Montr\u00e9al, Montr\u00e9al, QC, Canada."},{"key":"ref_34","unstructured":"Nikolenko, S.I. (2019). Synthetic Data for Deep Learning. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","article-title":"A survey on semi-supervised learning","volume":"109","author":"Hoos","year":"2020","journal-title":"Mach. Learn."},{"key":"ref_36","unstructured":"Beygelzimer, A., and Hsu, D. (2019, January 25\u201328). When can unlabeled data improve the learning rate?. Proceedings of the Conference on Learning Theory, COLT 2019, PMLR, Phoenix, AZ, USA. Proceedings of Machine Learning Research."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"G\u00f6pfert, J.P., G\u00f6pfert, C., Botsch, M., and Hammer, B. (December, January 27). Effects of variability in synthetic training data on convolutional neural networks for 3D head reconstruction. Proceedings of the 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, HI, USA.","DOI":"10.1109\/SSCI.2017.8285305"},{"key":"ref_38","unstructured":"Ullrich, K., Meeds, E., and Welling, M. (2017). Soft Weight-Sharing for Neural Network Compression. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform Manifold Approximation and Projection","volume":"3","author":"McInnes","year":"2018","journal-title":"J. Open Source Softw."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1002\/bit.27627","article-title":"Development and application of a cultivation platform for mammalian suspension cell lines with single-cell resolution","volume":"118","author":"Schmitz","year":"2021","journal-title":"Biotechnol. Bioeng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"16884","DOI":"10.1038\/s41598-019-52737-x","article-title":"Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks","volume":"9","author":"Sandfort","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_42","unstructured":"Saxe, A.M., McClelland, J.L., and Ganguli, S. (2013, January 2\u20134). Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. Proceedings of the International Conference on Learning Representations, ICLR 2013, Scottsdale, AZ, USA."},{"key":"ref_43","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., and Han, J. (2020). On the Variance of the Adaptive Learning Rate and Beyond. arXiv."},{"key":"ref_44","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_45","unstructured":"Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., and Weinberger, K.Q. (2011). Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_46","unstructured":"Touretzky, D.S., Mozer, M.C., and Hasselmo, M.E. (1996). Advances in Neural Information Processing Systems 8, MIT Press."},{"key":"ref_47","unstructured":"Tan, M., and Le, Q.V. (2021). EfficientNetV2: Smaller Models and Faster Training. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/4\/205\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T09:01:54Z","timestamp":1681290114000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/4\/205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,12]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["a16040205"],"URL":"https:\/\/doi.org\/10.3390\/a16040205","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2023,4,12]]}}}