{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:05:29Z","timestamp":1775581529335,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cambridge Vice Chancellor\u2019s Award Fund"},{"name":"Rosen Bioengineering Center Pilot Research Grant Award","award":["9900050"],"award-info":[{"award-number":["9900050"]}]},{"name":"Rosen Bioengineering Center Pilot Research Grant Award","award":["9900050"],"award-info":[{"award-number":["9900050"]}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["098287\/Z\/12\/Z"],"award-info":[{"award-number":["098287\/Z\/12\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","award":["RPG- 2018-085"],"award-info":[{"award-number":["RPG- 2018-085"]}],"id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Philanthropy\/Silicon Valley"},{"name":"Weston Havens Foundations"},{"name":"NIH R01","award":["HD100456-01A1"],"award-info":[{"award-number":["HD100456-01A1"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Polarization of the mammalian embryo at the right developmental time is critical for its development to term and would be valuable in assessing the potential of human embryos. However, tracking polarization requires invasive fluorescence staining, impermissible in the in vitro fertilization clinic. Here, we report the use of artificial intelligence to detect polarization from unstained time-lapse movies of mouse embryos. We assembled a dataset of bright-field movie frames from 8-cell-stage embryos, side-by-side with corresponding images of fluorescent markers of cell polarization. We then used an ensemble learning model to detect whether any bright-field frame showed an embryo before or after onset of polarization. Our resulting model has an accuracy of 85% for detecting polarization, significantly outperforming human volunteers trained on the same data (61% accuracy). We discovered that our self-learning model focuses upon the angle between cells as one known cue for compaction, which precedes polarization, but it outperforms the use of this cue alone. By compressing three-dimensional time-lapsed image data into two-dimensions, we are able to reduce data to an easily manageable size for deep learning processing. In conclusion, we describe a method for detecting a key developmental feature of embryo development that avoids clinically impermissible fluorescence staining.<\/jats:p>","DOI":"10.1038\/s41598-022-05990-6","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T11:16:32Z","timestamp":1644837392000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Stain-free detection of embryo polarization using deep learning"],"prefix":"10.1038","volume":"12","author":[{"given":"Cheng","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adiyant","family":"Lamba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ray","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Magdalena","family":"Zernicka-Goetz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhuei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,14]]},"reference":[{"key":"5990_CR1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0092-8674(81)90502-X","volume":"24","author":"MH Johnson","year":"1981","unstructured":"Johnson, M. H. & Ziomek, C. A. The foundation of two distinct cell lineages within the mouse morula. Cell 24, 71\u201380 (1981).","journal-title":"Cell"},{"key":"5990_CR2","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/0012-1606(86)90175-2","volume":"113","author":"TP Fleming","year":"1986","unstructured":"Fleming, T. P., Cannon, P. M. & Pickering, S. J. The cytoskeleton, endocytosis and cell polarity in the mouse preimplantation embryo. Dev. Biol. 113, 406\u2013419 (1986).","journal-title":"Dev. Biol."},{"key":"5990_CR3","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1038\/s41586-020-2759-x","volume":"587","author":"C Gerri","year":"2020","unstructured":"Gerri, C. et al. Initiation of a conserved trophectoderm program in human, cow and mouse embryos. Nature 587, 443\u2013447 (2020).","journal-title":"Nature"},{"key":"5990_CR4","doi-asserted-by":"crossref","unstructured":"Zhu, M. et al. Human embryo polarization requires PLC signaling to mediate trophectoderm specification. elife 10, e65068 (2021).","DOI":"10.7554\/eLife.65068"},{"key":"5990_CR5","doi-asserted-by":"publisher","first-page":"2813","DOI":"10.1242\/dev.107276","volume":"141","author":"S Anani","year":"2014","unstructured":"Anani, S., Bhat, S., Honma-Yamanaka, N., Krawchuk, D. & Yamanaka, Y. Initiation of Hippo signaling is linked to polarity rather than to cell position in the pre-implantation mouse embryo. Development 141, 2813\u20132824 (2014).","journal-title":"Development"},{"key":"5990_CR6","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1016\/j.devcel.2015.07.004","volume":"34","author":"CR Samarage","year":"2015","unstructured":"Samarage, C. R. et al. Cortical tension allocates the first inner cells of the mammalian embryo. Dev. Cell 34, 435\u2013447 (2015).","journal-title":"Dev. Cell"},{"key":"5990_CR7","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1146\/annurev-cellbio-022020-024900","volume":"36","author":"C Gerri","year":"2020","unstructured":"Gerri, C., Menchero, S., Mahadevaiah, S. K., Turner, J. M. & Niakan, K. K. Human embryogenesis: a comparative perspective. Annu. Rev. Cell Dev. Biol. 36, 411\u2013440 (2020).","journal-title":"Annu. Rev. Cell Dev. Biol."},{"key":"5990_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1083\/jcb.91.1.303","volume":"91","author":"MH Johnson","year":"1981","unstructured":"Johnson, M. H. & Ziomek, C. A. Induction of polarity in mouse 8-cell blastomeres: specificity, geometry, and stability. J. Cell Biol. 91, 303\u2013308 (1981).","journal-title":"J. Cell Biol."},{"key":"5990_CR9","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1006\/dbio.1996.0186","volume":"177","author":"S Louvet","year":"1996","unstructured":"Louvet, S., Aghion, J., Santa-Maria, A., Mangeat, P. & Maro, B. Ezrin becomes restricted to outer cells following asymmetrical division in the preimplantation mouse embryo. Dev. Biol. 177, 568\u2013579 (1996).","journal-title":"Dev. Biol."},{"key":"5990_CR10","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.ydbio.2005.03.001","volume":"282","author":"S Vinot","year":"2005","unstructured":"Vinot, S. et al. Asymmetric distribution of PAR proteins in the mouse embryo begins at the 8-cell stage during compaction. Dev. Biol. 282, 307\u2013319 (2005).","journal-title":"Dev. Biol."},{"key":"5990_CR11","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1242\/jcs.01666","volume":"118","author":"B Plusa","year":"2005","unstructured":"Plusa, B. et al. Downregulation of Par3 and aPKC function directs cells towards the ICM in the preimplantation mouse embryo. J. Cell Sci. 118, 505\u2013515 (2005).","journal-title":"J. Cell Sci."},{"key":"5990_CR12","doi-asserted-by":"crossref","unstructured":"Zhu, M. et al. Developmental clock and mechanism of de novo polarization of the mouse embryo. Science 370, eabd2703 (2020).","DOI":"10.1126\/science.abd2703"},{"key":"5990_CR13","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1095\/biolreprod.110.084400","volume":"83","author":"VB Alarcon","year":"2010","unstructured":"Alarcon, V. B. Cell polarity regulator PARD6B is essential for trophectoderm formation in the preimplantation mouse embryo. Biol. Reprod. 83, 347\u2013358 (2010).","journal-title":"Biol. Reprod."},{"key":"5990_CR14","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.devcel.2017.01.006","volume":"40","author":"E Korotkevich","year":"2017","unstructured":"Korotkevich, E. et al. The apical domain is required and sufficient for the first lineage segregation in the mouse embryo. Dev. Cell 40, 235\u2013247 (2017).","journal-title":"Dev. Cell"},{"key":"5990_CR15","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1016\/j.ydbio.2007.10.054","volume":"313","author":"A Ralston","year":"2008","unstructured":"Ralston, A. & Rossant, J. Cdx2 acts downstream of cell polarization to cell-autonomously promote trophectoderm fate in the early mouse embryo. Dev. Biol. 313, 614\u2013629 (2008).","journal-title":"Dev. Biol."},{"key":"5990_CR16","doi-asserted-by":"crossref","unstructured":"Khan, A., Gould, S. & Salzmann, M. Deep Convolutional Neural Networks for Human Embryonic Cell Counting. In European Conference on Computer Vision, Springer, Cham, 339\u2013348 (2016).","DOI":"10.1007\/978-3-319-46604-0_25"},{"key":"5990_CR17","doi-asserted-by":"crossref","unstructured":"Rad, R. M., Saeedi, P., Au, J. & Havelock, J. Blastomere cell counting and centroid localization in microscopic images of human embryo. In 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP), IEEE, 1\u20136 (2018).","DOI":"10.1109\/MMSP.2018.8547107"},{"key":"5990_CR18","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1142\/S2661318219500051","volume":"1","author":"TJ Chen","year":"2019","unstructured":"Chen, T. J. et al. Using deep learning with large dataset of microscope images to develop an automated embryo grading system. Fertil. Reprod. 1, 51\u201356 (2019).","journal-title":"Fertil. Reprod."},{"key":"5990_CR19","doi-asserted-by":"crossref","unstructured":"Bormann, C. L. et al. Performance of a deep learning based neural network in the selection of human blastocysts for implantation. eLife 9, e55301 (2020).","DOI":"10.7554\/eLife.55301"},{"key":"5990_CR20","doi-asserted-by":"crossref","unstructured":"Leahy, B. D. et al. Automated Measurements of Key Morphological Features of Human Embryos for IVF. In International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 25\u201335 (2020).","DOI":"10.1007\/978-3-030-59722-1_3"},{"key":"5990_CR21","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1093\/humrep\/dez064","volume":"34","author":"D Tran","year":"2019","unstructured":"Tran, D., Cooke, S., Illingworth, P. J. & Gardner, D. K. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum. Reprod. 34, 1011\u20131018 (2019).","journal-title":"Hum. Reprod."},{"key":"5990_CR22","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1006\/dbio.2001.0192","volume":"233","author":"N Dard","year":"2001","unstructured":"Dard, N. et al. In vivo functional analysis of ezrin during mouse blastocyst formation. Dev. Biol. 233, 161\u2013173 (2001).","journal-title":"Dev. Biol."},{"key":"5990_CR23","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1242\/dev.124.6.1133","volume":"124","author":"M Zernicka-Goetz","year":"1997","unstructured":"Zernicka-Goetz, M. et al. Following cell fate in the living mouse embryo. Development 124, 1133\u20131137 (1997).","journal-title":"Development"},{"key":"5990_CR24","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1016\/j.cell.2018.02.035","volume":"173","author":"J Zenker","year":"2018","unstructured":"Zenker, J. et al. Expanding actin rings zipper the mouse embryo for blastocyst formation. Cell 173, 776\u2013791 (2018).","journal-title":"Cell"},{"key":"5990_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3042064","volume":"50","author":"A Ioannidou","year":"2017","unstructured":"Ioannidou, A., Chatzilari, E., Nikolopoulos, S. & Kompatsiaris, I. Deep learning advances in computer vision with 3d data: A survey. ACM Comput. Surv. (CSUR) 50, 1\u201338 (2017).","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"5990_CR26","doi-asserted-by":"publisher","first-page":"5097","DOI":"10.3390\/s20185097","volume":"20","author":"SP Singh","year":"2020","unstructured":"Singh, S. P. et al. 3D deep learning on medical images: a review. Sensors 20, 5097 (2020).","journal-title":"Sensors"},{"key":"5990_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss, K., Khoshgoftaar, T. M. & Wang, D. A survey of transfer learning. J. Big Data 3, 1\u201340 (2016).","journal-title":"J. Big Data"},{"key":"5990_CR28","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1002\/jemt.20092","volume":"65","author":"B Forster","year":"2004","unstructured":"Forster, B., Van De Ville, D., Berent, J., Sage, D. & Unser, M. Complex wavelets for extended depth-of-field: A new method for the fusion of multichannel microscopy images. Microsc. Res. Tech. 65, 33\u201342 (2004).","journal-title":"Microsc. Res. Tech."},{"key":"5990_CR29","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. ImageNet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 248\u2013255 (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5990_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2921\u20132929 (2016).","DOI":"10.1109\/CVPR.2016.319"},{"key":"5990_CR31","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1242\/dev.62.1.351","volume":"62","author":"WJD Reeve","year":"1981","unstructured":"Reeve, W. J. D. Cytoplasmic polarity develops at compaction in rat and mouse embryos. Development 62, 351\u2013367 (1981).","journal-title":"Development"},{"key":"5990_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-017-00977-8","volume":"8","author":"M Zhu","year":"2017","unstructured":"Zhu, M., Leung, C. Y., Shahbazi, M. N. & Zernicka-Goetz, M. Actomyosin polarisation through PLC-PKC triggers symmetry breaking of the mouse embryo. Nat. Commun. 8, 1\u201316 (2017).","journal-title":"Nat. Commun."},{"key":"5990_CR33","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1016\/j.cell.2018.03.040","volume":"173","author":"EM Christiansen","year":"2018","unstructured":"Christiansen, E. M. et al. In silico labeling: Predicting fluorescent labels in unlabeled images. Cell 173, 792\u2013803 (2018).","journal-title":"Cell"},{"key":"5990_CR34","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1038\/s41592-018-0111-2","volume":"15","author":"C Ounkomol","year":"2018","unstructured":"Ounkomol, C., Seshamani, S., Maleckar, M. M., Collman, F. & Johnson, G. R. Label-free prediction of three-dimensional fluorescence images from transmitted-light microscopy. Nat. Methods 15, 917\u2013920 (2018).","journal-title":"Nat. Methods"},{"key":"5990_CR35","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158\u2013164 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"5990_CR36","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700\u20134708 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"5990_CR37","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L. & Sun, G. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132\u20137141 (2018).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"5990_CR38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-05990-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-05990-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-05990-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T22:35:31Z","timestamp":1669329331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-05990-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,14]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["5990"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-05990-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,14]]},"assertion":[{"value":"22 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2404"}}