Deep Learning-Based In Vitro Detection Method for Cellular Impurities in Human Cell-Processed Therapeutic Products
Source abstract
Abstract
Automated detection of impurities is in demand for evaluating the quality and safety of human cell-processed therapeutic products in regenerative medicine. Deep learning (DL) is a powerful method for classifying and recognizing images in cell biology, diagnostic medicine, and other fields because it automatically extracts the features from complex cell morphologies. In the present study, we construct prediction models that recognize cancer-cell contamination in continuous long-term (four-day) cell cultures. After dividing the whole dataset into Early- and Late-stage cell images, we found that Late-stage images improved the DL performance. The performance was further improved by optimizing the DL hyperparameters (batch size and learning rate). These findings are first report for the implement of DL-based systems in disease cell-type classification of human cell-processed therapeutic products (hCTPs), that are expected to enable the rapid, automatic classification of induced pluripotent stem cells and other cell treatments for life-threatening or chronic diseases.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Printing in Biomedical Research · Cell Image Analysis Techniques · Biomedical Ethics and Regulation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Medical Molecular Informatics, Meiji Pharmaceutical University, Kiyose 204-8588, Tokyo, Japan
Division of Molecular and Medical Genetics, Center for Gene and Cell Therapy, The Institute of Medical Science, University of Tokyo, Minato-ku 108-8639, Tokyo, Japan
Division of Cell-Based Therapeutic Producers, National Institute of Health Sciences, Kawasaki 201-9501, Kanagawa, Japan
Department of Toxicology and Pharmacology, Faculty of Pharmaceutical Sciences, Meiji Pharmaceutical University, Kiyose 204-8588, Tokyo, Japan
Funding
JSPS KAKENHI
References (83)
Show source-provided references
1. Tumorigenicity assessment of human cell-processed therapeutic products10.1016/j.biologicals.2015.05.008 ↗
2. Development of selective cytotoxic viral vectors for concentration of undifferentiated cells in cardiomyocytes derived from human induced pluripotent stem cells10.1038/s41598-018-36848-5 ↗
3. Differentiation and application of human pluripotent stem cells derived cardiovascular cells for treatment of heart diseases: Promises and challenges10.3389/fcell.2021.658088 ↗
4. McGarvey, S.S., Ferreyros, M., Kogut, I., and Bilousova, G. (2021). Differentiating induced pluripotent stem cells toward mesenchymal stem/stromal cells. Methods Mol. Biol., in press.10.1007/7651_2021_383 ↗
5. Graft site malignancy following treatment of full-thickness burn with cultured epidermal autograft10.1097/01.PRS.0000135871.79735.02 ↗
6. Amariglio, N., Hirshberg, A., Scheithauer, B.W., Cohen, Y., Loewenthal, R., Trakhtenbrot, L., Paz, N., Koren-Michowitz, M., Waldman, D., and Leider-Trejo, L. (2009). Donor-derived brain tumor following neural stem cell transplantation in an ataxia telangiectasia patient. PLoS Med., 6.10.1371/journal.pmed.1000029 ↗
7. The tumorigenicity of human embryonic and induced pluripotent stem cells10.1038/nrc3034 ↗
8. Autograft-derived spinal cord mass following olfactory mucosal cell transplantation in a spinal cord injury patient: Case report10.3171/2014.5.SPINE13992 ↗
9. Characterization of in vivo tumorigenicity tests using severe immunodeficient NOD/Shi-scid IL2Rgamma(null) mice for detection of tumorigenic cellular impurities in human cell-processed therapeutic products10.1016/j.reth.2014.12.001 ↗
10. Ultra-sensitive detection of tumorigenic cellular impurities in human cell-processed therapeutic products by digital analysis of soft agar colony formation10.1038/srep17892 ↗
11. Application of cell growth analysis to the quality assessment of human cell-processed therapeutic products as a testing method for immortalized cellular impurities10.1016/j.reth.2016.06.005 ↗
12. Lee, B., Borys, B.S., Kallos, M.S., Rodrigues, C.A.V., Silva, T.P., and Cabral, J.M.S. (2020). Challenges and solutions for commercial scale manufacturing of allogeneic pluripotent stem cell products. Bioengineering., 7.10.3390/bioengineering7020031 ↗
13. Tumorigenic and immunogenic properties of induced pluripotent stem cells: A promising cancer vaccine10.1007/s12015-020-10042-5 ↗
14. Markossian, S., Grossman, A., Brimacombe, K., Arkin, M., Auld, D., Austin, C.P., Baell, J., Chung, T.D.Y., Coussens, N.P., and Dahlin, J.L. (2021). Pluripotent stem cell culture scale-out. Assay Guidance Manual, Eli Lilly & Company and the National Center for Advancing Translational Sciences.
15. Quality control assays for clinical-grade human mesenchymal stromal cells: Validation strategy10.1007/978-1-4939-3584-0_20 ↗
16. Quality control assays for clinical-grade human mesenchymal stromal cells: Methods for ATMP release10.1007/978-1-4939-3584-0_19 ↗
17. Cell-based therapy manufacturing in stirred suspension bioreactor: Thoughts for cGMP compliance10.3389/fbioe.2020.599674 ↗
18. Quality Management Systems (QMSs) of human-based tissue and cell product manufacturing facilities10.1007/7651_2020_341 ↗
19. Understanding cell culture dynamics: A tool for defining protocol parameters for improved processes and efficient manufacturing using human embryonic stem cells10.1080/21655979.2021.1902696 ↗
20. Tigges, J., Bielec, K., Brockerhoff, G., Hildebrandt, B., Hübenthal, U., Kapr, J., Koch, K., Teichweyde, N., Wieczorek, D., and Rossi, A. (2021). Academic application of good cell culture practice for induced pluripotent stem cells. Altern. Anim. Exp., in press.10.14573/altex.2101221 ↗
21. Outgrowth of a transformed cell population derived from normal human BM mesenchymal stem cell culture10.1080/14653240500363216 ↗
22. Tumor progression of culture-adapted human embryonic stem cells during long-term culture10.1002/gcc.20574 ↗
23. Long-term cultures of bone marrow-derived human mesenchymal stem cells frequently undergo spontaneous malignant transformation10.1158/0008-5472.CAN-08-4630 ↗
24. Pitfalls in spontaneous in vitro transformation of human mesenchymal stem cells10.1016/j.yexcr.2010.02.016 ↗
25. Check your cultures! A list of cross-contaminated or misidentified cell lines10.1002/ijc.25242 ↗
26. Spontaneous malignant transformation of human mesenchymal stem cells reflects cross-contamination: Putting the research field on track-letter10.1158/0008-5472.CAN-10-1305 ↗
27. In vitro generation of functional insulin-producing cells from human bone marrow-derived stem cells, but long-term culture running risk of malignant transformation
28. Horbach, S.P.J.M., and Halffman, W. (2017). The ghosts of HeLa: How cell line misidentification contaminates the scientific literature. PLoS ONE, 12.10.1371/journal.pone.0186281 ↗
29. Cross-contamination of the human salivary gland HSG cell line with HeLa cells: A STR analysis study10.1111/odi.12920 ↗
30. Essentiality of CTNNB1 in malignant transformation of human embryonic stem cells under long-term suboptimal conditions10.1155/2020/5823676 ↗
31. An artificial intelligent platform for live cell identification and the detection of cross-contamination10.21037/atm.2019.07.105 ↗
32. Yasuda, S., Kusakawa, S., Kuroda, T., Miura, T., Tano, K., Takada, N., Matsuyama, S., Matsuyama, A., Nasu, M., and Umezawa, A. (2018). Tumorigenicity-associated characteristics of human iPS cell lines. PLoS ONE, 13.10.1371/journal.pone.0205022 ↗
33. A comprehensive view on mechanistic approaches for cancer risk assessment of non-genotoxic agrochemicals10.1016/j.yrtph.2020.104789 ↗
34. Method for selective ablation of undifferentiated human pluripotent stem cell populations for cell-based therapies10.1172/jci.insight.142000 ↗
35. CellCognition: Time-resolved phenotype annotation in high-throughput live cell imaging10.1038/nmeth.1486 ↗
36. Prospective identification of hematopoietic lineage choice by deep learning10.1038/nmeth.4182 ↗
37. Classification of C2C12 cells at differentiation by convolutional neural network of deep learning using phase contrast images10.1007/s13577-017-0191-9 ↗
38. Cell type classification and unsupervised morphological phenotyping from low-resolution images using deep learning10.1038/s41598-019-50010-9 ↗
39. Raman spectra-based deep learning: A tool to identify microbial contamination10.1002/mbo3.1122 ↗
40. Towards image-based cancer cell lines authentication using deep neural networks10.1038/s41598-020-76670-6 ↗
41. Deep learning provides high accuracy in automated chondrocyte viability assessment in articular cartilage using nonlinear optical microscopy10.1364/BOE.417478 ↗
42. An adaptive learning method of anchor shape priors for biological cells detection and segmentation10.1016/j.cmpb.2021.106260 ↗
43. Iseoka, H., Sasai, M., Miyagawa, S., Takekita, K., Date, S., Ayame, H., Nishida, A., Sanami, S., Hayakawa, T., and Sawa, Y. (2021). Rapid and sensitive mycoplasma detection system using image-based deep learning. J. Artif. Organs, in press.10.1007/s10047-021-01282-4 ↗
44. Cell morphology classification and clutter mitigation in phase-contrast microscopy images using machine learning10.1007/s00138-011-0345-9 ↗
45. Matsuoka, F., Takeuchi, I., Agata, H., Kagami, H., Shiono, H., Kiyota, Y., Honda, H., and Kato, R. (2013). Morphology-based prediction of osteogenic differentiation potential of human mesenchymal stem cells. PLoS ONE, 8.10.1371/journal.pone.0055082 ↗
46. Computational image analysis of colony and nuclear morphology to evaluate human induced pluripotent stem cells10.1038/srep06996 ↗
47. Non-invasive quality evaluation of confluent cells by image-based orientation heterogeneity analysis10.1016/j.jbiosc.2015.06.012 ↗
48. Boumaraf, S., Liu, X., Wan, Y., Zheng, Z., Ferkous, C., Ma, X., Li, Z., and Bardou, D. (2021). Conventional machine learning versus deep learning for magnification Dependent histopathological breast cancer image classification: A comparative study with visual explanation. Diagnostics., 11.10.3390/diagnostics11030528 ↗
49. Shoeibi, A., Khodatars, M., Jafari, M., Moridian, P., Rezaei, M., Alizadehsani, R., Khozeimeh, F., Gorriz, J.M., Heras, J., and Panahiazar, M. (2021). Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review. Comput. Biol. Med., 136.10.1016/j.compbiomed.2021.104697 ↗
50. Van Valen, D.A., Kudo, T., Lane, K.M., Macklin, D.N., Quach, N.T., DeFelice, M.M., Maayan, I., Tanouchi, Y., Ashley, E.A., and Covert, M.W. (2016). Deep learning automates the quantitative analysis of individual cells in live-cell imaging experiments. PLoS Comput. Biol., 12.10.1371/journal.pcbi.1005177 ↗
51. Chang, Y.-H., Abe, K., Yokota, H., Sudo, K., Nakamura, Y., Lin, C.-T., and Tsai, M.-D. (2017, January 11–15). Human induced pluripotent stem cell region recognition in microscopy images using Convolutional Neural Networks. Proceedings of the 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Korea.10.1109/EMBC.2017.8037747 ↗
52. Hong, J., Park, B.-Y., and Park, H. (2017, January 11–15). Convolutional neural network classifier for distinguishing Barrett’s esophagus and neoplasia endomicroscopy images. Proceedings of the 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Korea.10.1109/EMBC.2017.8037461 ↗
53. A convolutional neural network uses microscopic images to differentiate between mouse and human cell lines and their radioresistant clones10.1158/0008-5472.CAN-18-0653 ↗
54. Guo, X., Wang, F., Teodoro, G., Farris, A.B., and Kong, J. (2019, January 8–11). Liver steatosis segmentation with deep learning methods. Proceedings of the 16th IEEE International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.10.1109/ISBI.2019.8759600 ↗
55. Deep learning-based quality control of cultured human-induced pluripotent stem cell-derived cardiomyocytes10.1016/j.jphs.2019.04.008 ↗
56. An enhancement of deep learning algorithm for brain tumor segmentation using Kernel based CNN with M-SVM10.1007/s10916-019-1223-7 ↗
57. Automatic detection and characterization of quantitative phase images of thalassemic red blood cells using a mask region-based convolutional neural network10.1117/1.JBO.25.11.116502 ↗
58. Combining DC-GAN with ResNet for blood cell image classification10.1007/s11517-020-02163-3 ↗
59. Generative adversarial network based data augmentation to improve cervical cell classification model10.3934/mbe.2021090 ↗
60. Intelligent image-activated cell sorting 2.010.1039/D0LC00080A ↗
61. Janocha, K., and Czarnecki, W.M. (2017). On loss functions for deep neural networks in classification. arXiv, Available online: https://arxiv.org/abs/1702.05659.10.4467/20838476SI.16.004.6185 ↗
62. Bradley, J. (1968). Distribution-Free Statistical Tests, Prentice-Hall.
63. Novel 3D Liquid Cell Culture Method for Anchorage-independent Cell Growth, Cell Imaging and Automated Drug Screening10.1038/s41598-018-21950-5 ↗
64. Yao, Z., Gholami, A., Arfeen, D., Liaw, R., Gonzalez, J., Keutzer, K., and Mahoney, M. (2018). Large batch size training of neural networks with adversarial training and second-order information. arXiv, Available online: https://arxiv.org/abs/1810.01021.
65. Perrone, M.P., Khan, H., Kim, C., Kyrillidis, A., Quinn, J., and Salapura, V. (2019). Optimal mini-batch size selection for fast gradient descent. arXiv, Available online: https://arxiv.org/abs/1911.06459.
66. Alfarra, M., Hanzely, S., Albasyoni, A., Ghanem, B., and Richtarik, P. (2005). Adaptive learning of the optimal mini-batch size of SGD. arXiv, Available online: https://arxiv.org/abs/2005.01097.
67. Qian, X., and Klabjan, D. (2004). The impact of the mini-batch size on the variance of gradients in stochastic gradient descent. arXiv, Available online: https://arxiv.org/abs/2004.13146.
68. Gao, F., and Zhong, H. (2012). Study on the large batch size training of neural networks based on the second order gradient. arXiv, Available online: https://arxiv.org/abs/2012.08795.
69. Lin, T., Kong, L., Stich, S.U., and Jaggi, M. (2006). Extrapolation for large-batch training in deep learning. arXiv, Available online: https://arxiv.org/abs/2006.05720.
70. Dimensionality reduction to maximize prediction generalization capability10.1038/s42256-021-00306-1 ↗
71. DeepDose: Towards a fast dose calculation engine for radiation therapy using deep learning10.1088/1361-6560/ab7630 ↗
72. A novel deep autoencoder based survival analysis approach for microarray dataset10.7717/peerj-cs.492 ↗
73. Faster mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking10.1016/j.media.2021.102048 ↗
74. fast GPU implementation of a scan-specific deep learning reconstruction for accelerated magnetic resonance imaging
75. Deep Learning in Medical Imaging: General Overview10.3348/kjr.2017.18.4.570 ↗
76. Salman, S., and Liu, X. (2019). Overfitting Mechanism and Avoidance in Deep Neural Networks. arXiv, Available online: https://arxiv.org/abs/1901.06566.
77. Rice, L., Wong, E., and Kolter, J.Z. (2002). Overfitting in adversarially robust deep learning. arXiv, Available online: https://arxiv.org/abs/2002.11569.
78. Zhang, C., Vinyals, O., Munos, R., and Bengio, S. (2018). A Study on Overfitting in Deep Reinforcement Learning. arXiv, Available online: https://arxiv.org/abs/1804.06893.
79. Arief, H.A., Indahl, U.G., Strand, G.-H., and Tveite, H. (2019). Addressing Overfitting on Pointcloud Classification using Atrous XCRF. arXiv, Available online: https://arxiv.org/abs/1902.03088.10.1016/j.isprsjprs.2019.07.002 ↗
80. Daee, P., Peltola, T., Vehtari, A., and Kaski, S. (2018). User Modelling for Avoiding Overfitting in Interactive Knowledge Elicitation for Prediction. arXiv, Available online: https://arxiv.org/abs/1710.04881.10.1145/3172944.3172989 ↗
81. Cogswell, M., Ahmed, F., Girshick, R., Zitnick, L., and Batra, D. (2016). Reducing Overfitting in Deep Networks by Decorrelating Representations. arXiv, Available online: https://arxiv.org/abs/1511.06068.
82. Ghojogh, B., and Crowley, M. (2019). The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial. arXiv, Available online: https://arxiv.org/abs/1905.12787.
83. Yilmaz, A., Demircali, A.A., Kocaman, S., and Uvet, H. (2009). Comparison of Deep Learning and Traditional Machine Learning Techniques for Classification of Pap Smear Images. arXiv, Available online: https://arxiv.org/abs/2009.06366.