Abstract
Observing chromosomes is a time-consuming and labor-intensive process, and chromosomes have been analyzed manually for many years. In the last decade, automated acquisition systems for microscopic images have advanced dramatically due to advances in their controlling computer systems, and nowadays, it is possible to automatically acquire sets of tiling-images consisting of large number, more than 1000, of images from large areas of specimens. However, there has been no simple and inexpensive system to efficiently select images containing mitotic cells among these images. In this paper, a classification system of chromosomal images by deep learning artificial intelligence (AI) that can be easily handled by non-data scientists was applied. With this system, models suitable for our own samples could be easily built on a Macintosh computer with Create ML. As examples, models constructed by learning using chromosome images derived from various plant species were able to classify images containing mitotic cells among samples from plant species not used for learning in addition to samples from the species used. The system also worked for cells in tissue sections and tetrads. Since this system is inexpensive and can be easily trained via deep learning using scientists’ own samples, it can be used not only for chromosomal image analysis but also for analysis of other biology-related images.
Similar content being viewed by others
Data availability
The models created in this study can be downloaded from GuiHub (https://github.com/tomoyukif/nagakiCreateMLmodels).
Code availability
CutSort is freely available on GitHub (https://github.com/tomoyukif/CutSort).
Abbreviations
- Asa:
-
Allium sativum
- Ace:
-
Allium cepa
- Afi:
-
Allium fistulosum
- AI:
-
Artificial intelligence
- At:
-
Arabidopsis thaliana
- Asa:
-
Allium sativum
- AtCell:
-
Arabidopsis thaliana Cultured cell
- Atu:
-
Allium tuberosum
- BY-2:
-
Nicotiana tabacum Cultured cell line BY-2
- CLI:
-
Command line interface
- Eg:
-
Elaeis guineensis
- GUI:
-
Graphical user interface
- Ha:
-
Helianthus annuus
- IC:
-
Image classifier
- IC (+ op):
-
Image classifier with options
- Ini:
-
Ipomoea nil
- Je:
-
Juncus effusus
- Ln:
-
Luzula nivea
- Mw:
-
Microcoelum weddelliana
- Ns:
-
Nicotiana sylvestris
- Nt:
-
Nicotiana tabacum
- Nto:
-
Nicotiana tomentosiformis
- OD:
-
Object detector
- Os:
-
Oryza sativa
- OsCell:
-
Oryza sativa Cultured cell
- PNG:
-
Portable network graphics
- So:
-
Saccharum officinarum
- Ta:
-
Triticum aestivum
References
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jozefowicz R, Jia Y, Kaiser L, Kudlur M, Levenberg J, Mané D, Schuster M, Monga R, Moore S, Murray D, Olah C, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2016) TensorFlow: a system for large-scale machine learning. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf. Accessed 10/12/2021
Abid F, Hamami L, Badache F, Derdour H (2017) A system on chip for automatic karyotyping system. Computers Electrical Engineering 64:1–14
Al-Kofahi Y, Zaltsman A, Graves R, Marshall W, Rusu M (2018) A deep learning-based algorithm for 2-D cell segmentation in microscopy images. BMC Bioinformatics 19:365
Cremer T, Cremer C (1988) Centennial of Wilhelm Waldeyer’s introduction of the term “chromosome” in 1888. Cytogenet Cell Genet 48:66–67
Du TH, Puah WC, Wasser M (2011) Cell cycle phase classification in 3D in vivo microscopy of Drosophila embryogenesis. BMC Bioinformatics 12:S18
Ferguson-Smith MA, Trifonov V (2007) Mammalian karyotype evolution. Nat Rev Genet 8:950–962
Hernández-Mier Y, Nuño-Maganda MA, Polanco-Martagón S, García-Chávez MdR (2020) Machine learning classifiers evaluation for automatic karyogram generation from G-banded metaphase images. Appl Sci 10(8):2758
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional srchitecture for fast feature embedding. Proceedings of the 22nd ACM international conference on Multimedia:675–678. https://doi.org/10.1145/2647868.2654889
Kato K, Matsumoto T, Koiwai A, Mizusaki S, Nishida K, Noguchi M, Tamaki E (1972) Liquid suspension culture of tobacco cells. Proc. IV IFS: Ferment Technol Today 689–695
Kuniyoshi D, Masuda I, Kanaoka Y, Shimazaki-Kishi Y, Okamoto Y, Yasui H, Yamamoto T, Nagaki K, Hoshino Y, Koide Y, Takamure I, Kishima Y (2020) Diploid male gametes circumvent hybrid sterility between Asian and African rice species. Frontiers in Plant Science 11:579305
Kutsuna N, Higaki T, Matsunaga S, Otsuki T, Yamaguchi M, Fujii H, Hasezawa S (2012) Active learning framework with iterative clustering for bioimage classification. Nat Commun 3:1032
Li Y, Knoll JH, Wilkins RC, Flegal FN, Rogan PK (2016) Automated discrimination of dicentric and monocentric chromosomes by machine learning-based image processing. Microsc Res Tech 79:393–402
Mahdessian D, Cesnik AJ, Gnann C, Danielsson F, Stenström L, Arif M, Zhang C, Le T, Johansson F, Shutten R, Bäckström A, Axelsson U, Thul P, Cho NH, Carja O, Uhlén M, Mardinoglu A, Stadler C, Lindskog C, Ayoglu B, Leonetti MD, Pontén F, Sullivan DP, Lundberg E (2021) Spatiotemporal dissection of the cell cycle with single-cell proteogenomics. Nature 590:649–654
Mandáková T, Lysak MA (2008) Chromosomal phylogeny and karyotype evolution in x=7 Crucifer species (Brassicaceae). Plant Cell 20:2559–2570
McQuin C, Goodman A, Chernyshev V, Kamentsky L, Cimini BA, Karhohs KW, Doan M, Ding L, Rafelski SM, Thirstrup D, Wiegraebe W, Singh S, Becker T, Caicedo JC, Carpenter AE (2018) CellProfiler 3.0: Next-generation image processing for biology. PLoS Biol 16:e2005970
Munot MV, Joshi MA, Sharma N (2011) Automated karyotyping of metaphase cells with touching chromosomes. Int J Comput Appl 29. https://citeseerx.ist.psu.edu/viewdoc/download?
Nagaki K, Cheng Z, Ouyang S, Talbert PB, Kim M, Jones KM, Henikoff S, Buell CR, Jiang J (2004) Sequencing of a rice centromere uncovers active genes. Nat Genet 36(2):138–145. https://doi.org/10.1038/ng1289
Nagaki K, Terada K, Wakimoto M, Kashihara K, Murata M (2010) Centromere targeting of alien CENH3s in Arabidopsis and tobacco cells. Chromosome Res 18(2):203–211. https://doi.org/10.1007/s10577-009-9108-0
Nagaki K, Yamamoto M, Yamaji N, Mukai Y, Murata M (2012) Chromosome dynamics visualized with an anti-centromeric histone H3 antibody in Allium. PLoS ONE 7(12):e51315. https://doi.org/10.1371/journal.pone.0051315
O’Connor C (2008) Karyotyping for chromosomal abnormalities. Nature. Education 1(1):27
Pellicer J, Leitch IJ (2020) The plant DNA C-values database (release 7.1): an updated online repository of plant genome size data for comparative studies. New Phytol 226:301–305
Sears ER (1969) Wheat cytogenetics. Annu Rev Genet 3:451–468
Shimahara Y, Sugawara K, Kojo KH, Kawai H, Yoshida Y, Hasezawa S, Kutsuna N (2019) IMACEL: a cloud-based bioimage analysis platform for morphological analysis and image classification. PLOS One 14(2):e0212619
Shirley B, Li Y, Knoll JHM, Rogan PK (2017) Expedited radiation biodosimetry by automated dicentric chromosome identification (ADCI) and dose estimation. J vis Exp 4:56245
Waldeyer W (1888) Über Karyokinese und ihre Beziehung zu den Befruchtungsvorgängen. Arch Mikrosk Anat 32:1–122
Xiao L, Luo C, Yu T, Luo Y, Wang M, Yu F, Li Y, Tian C, Qiao J (2020) DeepACEv2: Automated chromosome enumeration in metaphase cell images using deep convolutional neural networks. IEEE Trans Med Imaging
Acknowledgements
I. nil seeds were provided by the National BioResource Project (NBRP). The seeds of N. tabacum, N. sylvestris, and N. tomentosiformis were gifts from Japan Tobacco, Inc. The stems of S. officinarum were gifts from the Japan International Research Center for Agricultural Sciences.
Funding
This work was partly supported by grants from JSPS KAKENHI (No. 19H00937 to Yuji Kishima), the Joint Usage/Research Center, Institute of Plant Science and Resources, Okayama University (Nos. 2838 to Hirotomo Takatsuka, 2839 to Atsushi Hoshino, R240 to Yuji Kishima, and IP2019 to Minoru Murata), and the NIBB Collaborative Research Program (20–328 to Atsushi Hoshino).
Author information
Authors and Affiliations
Contributions
Kiyotaka Nagaki conceived the study and conducted the experiments except the CLSM imaging and the preparation and capture of the I. nil, A. thaliana, E. guineensis, and S. weddelliana chromosome images and tetrad images; performed the deep learning; produced all the figures; and wrote the manuscript. Tomoyuki Furuta developed the sorting application and reviewed the manuscript. Naoki Yamaji conducted the CLSM imaging. Daichi Kuniyoshi, Megumi Ishihara, and Yuji Kishima conducted the tetrad analysis. Atsushi Hoshino (I. nil), Hirotomo Takatsuka (A. thaliana), and Minoru Murata (E. guineensis and S. weddelliana) prepared and captured the chromosome images.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Disclaimer
Authors are responsible for correctness of the statements provided in the manuscript. See also Authorship Principles. The Editor-in-Chief reserves the right to reject submissions that do not meet the guidelines described in this section.
Additional information
Responsible Editor: Rachel O'Neill.
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Nagaki, K., Furuta, T., Yamaji, N. et al. Effectiveness of Create ML in microscopy image classifications: a simple and inexpensive deep learning pipeline for non-data scientists. Chromosome Res 29, 361–371 (2021). https://doi.org/10.1007/s10577-021-09676-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10577-021-09676-z