{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T23:41:30Z","timestamp":1778715690818,"version":"3.51.4"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>The most common Assisted Reproductive Technology is <jats:italic>In-Vitro<\/jats:italic> Fertilization (IVF). During IVF, embryologists commonly perform a morphological assessment to evaluate embryo quality and choose the best embryo for transferring to the uterus. However, embryo selection through morphological assessment is subjective, so various embryologists obtain different conclusions. Furthermore, humans can consider only a limited number of visual parameters resulting in a poor IVF success rate. Artificial intelligence (AI) for embryo selection is objective and can include many parameters, leading to better IVF outcomes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>This study sought to use AI to (1) predict pregnancy results based on embryo images, (2) assess using more than one image of the embryo in the prediction of pregnancy but based on the current process in IVF labs, and (3) compare results of AI-Based methods and embryologist experts in predicting pregnancy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A data set including 252 Time-lapse Videos of embryos related to IVF performed between 2017 and 2020 was collected. Frames related to 19\u2009\u00b1\u20091, 43\u2009\u00b1\u20091, and 67\u2009\u00b1 1\u2009h post-insemination were extracted. Well-Known CNN architectures with transfer learning have been applied to these images. The results have been compared with an algorithm that only uses the final image of embryos. Furthermore, the results have been compared with five experienced embryologists.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>To predict the pregnancy outcome, we applied five well-known CNN architectures (AlexNet, ResNet18, ResNet34, Inception V3, and DenseNet121). DeepEmbryo, using three images, predicts pregnancy better than the algorithm that only uses one final image. It also can predict pregnancy better than all embryologists. Different well-known architectures can successfully predict pregnancy chances with up to 75.0% accuracy using Transfer Learning.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>We have developed DeepEmbryo, an AI-based tool that uses three static images to predict pregnancy. Additionally, DeepEmbryo uses images that can be obtained in the current IVF process in almost all IVF labs. AI-based tools have great potential for predicting pregnancy and can be used as a proper tool in the future.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1375474","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T12:11:43Z","timestamp":1717071103000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["An artificial intelligence algorithm to select most viable embryos considering current process in IVF labs"],"prefix":"10.3389","volume":"7","author":[{"given":"Mahdi-Reza","family":"Borna","sequence":"first","affiliation":[]},{"given":"Mohammad Mehdi","family":"Sepehri","sequence":"additional","affiliation":[]},{"given":"Behnam","family":"Maleki","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3431804","article-title":"A deep learning approach for COVID-19 8 viral pneumonia screening with X-ray images","volume":"2","author":"Ahmed","year":"2021","journal-title":"Digit. Gov. Res. Pract."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e372","DOI":"10.1016\/j.fertnstert.2018.07.1038","article-title":"High accuracy machine learning predictive model for embryo selection in IVF PGT cycles with single embryo transfers","volume":"110","author":"Barash","year":"2018","journal-title":"Fertil. Steril."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.1016\/j.fertnstert.2006.05.037","article-title":"Interobserver and intraobserver variation in day 3 embryo grading","volume":"86","author":"Baxter Bendus","year":"2006","journal-title":"Fertil. Steril."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1016\/j.ajog.2023.04.027","article-title":"Deep learning for embryo evaluation using time-lapse: a systematic review of diagnostic test accuracy","volume":"29","author":"Berman","year":"2023","journal-title":"Am. J. Obstet. Gynecol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e55301","DOI":"10.7554\/eLife.55301","article-title":"Performance of a deep learning based neural network in the selection of human blastocysts for implantation","volume":"9","author":"Bormann","year":"2020","journal-title":"eLife"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.fertnstert.2019.12.004","article-title":"Consistency and objectivity of automated embryo assessments using deep neural networks","volume":"113","author":"Bormann","year":"2020","journal-title":"Fertil. Steril."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"23","DOI":"10.22037\/nbm.v12i1.43214","article-title":"Predicting IVF pregnancy outcome and analyzing its cost factors: an artificial intelligence approach","volume":"12","author":"Borna","year":"2024","journal-title":"Nov. Biomed"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-61357-9","article-title":"Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning","volume":"10","author":"Chavez-Badiola","year":"2020","journal-title":"Sci. Rep."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1142\/S2661318219500051","article-title":"Using deep learning with large dataset of microscope images to develop an automated embryo grading system","volume":"1","author":"Chen","year":"2019","journal-title":"Fertil. Reprod."},{"key":"ref10","first-page":"248","author":"Deng","year":"2009"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1007\/s10815-017-0964-9","article-title":"National survey on use of time-lapse imaging systems in IVF laboratories","volume":"34","author":"Dolinko","year":"2017","journal-title":"J. Assist. Reprod. Genet."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e14623","DOI":"10.1111\/and.14623","article-title":"Microfluidic devices employing chemo- and thermotaxis for sperm selection can improve sperm parameters and function in patients with high DNA fragmentation","volume":"54","author":"Doostabadi","year":"2022","journal-title":"Andrologia"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1588","DOI":"10.1093\/humrep\/dew082","article-title":"International Committee for Monitoring Assisted Reproductive Technologies world report: assisted reproductive technology 2008, 2009 and 2010","volume":"31","author":"Dyer","year":"2016","journal-title":"Hum. Reprod."},{"key":"ref14","first-page":"242","article-title":"Culture systems for the human embryo","volume-title":"Textbook of assisted reproductive techniques","author":"Gardner","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-09356-w","article-title":"Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning","volume":"12","author":"Gourdeau","year":"2022","journal-title":"Sci. Rep."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1093\/humrep\/deab278","article-title":"Talking about possible IVF\/ICSI failure and need for multiple cycles in treatment planning: qualitative investigation of multi-cycle planning and its acceptability to patients and staff","volume":"37","author":"Harrison","year":"2022","journal-title":"Hum. Reprod."},{"key":"ref17","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s12884-021-04373-5","article-title":"Using deep learning to predict the outcome of live birth from more than 10,000 embryo data","volume":"22","author":"Huang","year":"2022","journal-title":"BMC Pregnancy Childbirth"},{"key":"ref19","first-page":"4700","volume-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1093\/humupd\/dmv016","article-title":"Infertility around the globe: new thinking on gender, reproductive technologies and global movements in the 21st century","volume":"21","author":"Inhorn","year":"2015","journal-title":"Hum. Reprod. Update"},{"key":"ref21","first-page":"142","article-title":"Progressively normalized self-attention network for video polyp segmentation","author":"Ji","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-019-0096-y","article-title":"Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization","volume":"2","author":"Khosravi","year":"2019","journal-title":"NPJ Digit. Med."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.fertnstert.2014.11.003","article-title":"Choosing the best embryo by time lapse versus standard morphology","volume":"103","author":"Kirkegaard","year":"2015","journal-title":"Fertil. Steril."},{"key":"ref24","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1007\/s10815-021-02228-8","article-title":"End-to-end deep learning for recognition of ploidy status using time-lapse videos","volume":"38","author":"Lee","year":"2021","journal-title":"J. Assist. Reprod. Genet."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42003-021-01937-1","article-title":"Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring","volume":"4","author":"Liao","year":"2021","journal-title":"Commun. Biol."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.rbmo.2012.10.021","article-title":"Morphological systems of human embryo assessment and clinical evidence","volume":"26","author":"Machtinger","year":"2013","journal-title":"Reprod. Biomed. Online"},{"key":"ref28","article-title":"Identification of empty follicles or oocyte-containing follicles by ultrasound images using K-means method and principal component analysis assessing several parameters with artificial intelligence","volume-title":"Human Reproduction","author":"Matsubayashi","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-03889-2","article-title":"DUNEScan: a web server for uncertainty estimation in skin cancer detection with deep neural networks","volume":"12","author":"Mazoure","year":"2022","journal-title":"Sci. Rep."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2245","DOI":"10.1093\/humrep\/dew183","article-title":"Correlation between aneuploidy, standard morphology evaluation and morphokinetic development in 1730 biopsied blastocysts: a consecutive case series study","volume":"31","author":"Minasi","year":"2016","journal-title":"Hum. Reprod."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1002\/rmb2.12267","article-title":"Feasibility of artificial intelligence for predicting live birth without aneuploidy from a blastocyst image","volume":"18","author":"Miyagi","year":"2019","journal-title":"Reprod. Med. Biol."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"101612","DOI":"10.1016\/j.media.2019.101612","article-title":"Trophectoderm segmentation in human embryo images via inceptioned U-net","volume":"62","author":"Rad","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref33","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"ref34","first-page":"225","article-title":"Evaluation of embryo quality analysis of morphology and physiology","volume-title":"Textbook of assisted reproductive techniques","author":"Sakkas","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1016\/j.rbmo.2021.05.002","article-title":"Evaluation of artificial intelligence using time-lapse images of IVF embryos to predict live birth","volume":"43","author":"Sawada","year":"2021","journal-title":"Reprod. Biomed. Online"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1101\/2024.03.04.583269","article-title":"Deep learning methods to forecasting human embryo development in time-lapse videos","volume":"54","author":"Sharma","year":"2024","journal-title":"bioRxiv"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1093\/humrep\/dew330","article-title":"Inter-observer and intra-observer agreement between embryologists during selection of a single day 5 embryo for transfer: a multicenter study","volume":"32","author":"Storr","year":"2017","journal-title":"Hum. Reprod. Oxf. Engl."},{"key":"ref38","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"355","DOI":"10.2147\/tcrm.2006.2.4.355","article-title":"In vitro fertilization (IVF): a review of 3 decades of clinical innovation and technological advancement","volume":"2","author":"Wang","year":"2006","journal-title":"Ther. Clin. Risk Manag."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1375474\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T12:11:48Z","timestamp":1717071108000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1375474\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":39,"alternative-id":["10.3389\/frai.2024.1375474"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1375474","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,30]]},"article-number":"1375474"}}