{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T20:16:02Z","timestamp":1789503362372,"version":"build-2803163510"},"reference-count":51,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"vor","delay-in-days":132,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Integrative Precision Agriculture","award":["2023-2644"],"award-info":[{"award-number":["2023-2644"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This study evaluated the suitability of applying supervised deep learning (DL) algorithms for early and real-time pregnancy diagnosis in beef cattle using luteal color Doppler (CD) ultrasonography recorded on days 20 (D20) and 22 (D22) after fixed-time artificial insemination (FTAI). CD ultrasound videos from 390 females were manually evaluated by trained personnel to perform the human-based pregnancy diagnosis (Human). Images were extracted at a rate of 5 frames per second from each video, resulting in 10,533 (D20) and 10,413 (D22) valid frames after applying a frame-filtering pipeline. Three convolutional neural network (CNN) architectures\u2014VGG19, Xception, and ResNet50\u2014along with their averaged inference (Combined), were evaluated using restricted 5-fold cross-validation, ensuring that images from the same animal did not appear in both training and validation sets. Final inferences for each animal were determined by averaging the network outputs across all video frames. Pregnancy status was confirmed on day 29 using conventional ultrasonography and treated as ground truth for assessing both Human and DL-based predictions. Accuracy levels were similar across methods, ranging from 0.84 (VGG19) to 0.87 (Human) for D20 and from 0.86 (VGG19) to 0.93 (Human) for D22. Based on Matthew\u2019s correlation coefficient, the Combined and Xception architectures demonstrated the best overall agreement with true pregnancy status among DL models. These architectures performed comparably to human diagnosis, with the Combined model achieving similar F1 scores (0.89 vs 0.91), higher specificity (0.72 vs 0.65), and slightly lower sensitivity (0.95 vs 1.00) on D20. Xception showed similar performance to human diagnosis on D22, with comparable accuracy (0.91 vs 0.93), specificity (0.79 vs 0.81), sensitivity (0.99 vs 1.00), and F1 score (0.93 vs 0.94). In conclusion, DL algorithms can effectively predict pregnancy status using CD ultrasonography earlier than industry-standard methods, with performance comparable to that of trained personnel.<\/jats:p>","DOI":"10.1093\/jas\/skaf166","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T07:38:44Z","timestamp":1746689924000},"source":"Crossref","is-referenced-by-count":4,"title":["Computer vision analysis of luteal color Doppler ultrasonography for early and automated pregnancy diagnosis in <i>Bos taurus<\/i> beef cows"],"prefix":"10.1093","volume":"103","author":[{"given":"Lucas Melo","family":"Gon\u00e7alves","sequence":"first","affiliation":[{"name":"Department of Animal and Dairy Science, University of Georgia , Athens, GA, 30602 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1369-5641","authenticated-orcid":false,"given":"Pedro Levy Piza","family":"Fontes","sequence":"additional","affiliation":[{"name":"Department of Animal and Dairy Science, University of Georgia , Athens, GA, 30602 ,","place":["USA"]},{"name":"Institute for Integrative Precision Agriculture \u2013 University of Georgia , Athens, GA 30602 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anderson Antonio Carvalho","family":"Alves","sequence":"additional","affiliation":[{"name":"Department of Animal and Dairy Science, University of Georgia , Athens, GA, 30602 ,","place":["USA"]},{"name":"Institute for Integrative Precision Agriculture \u2013 University of Georgia , Athens, GA 30602 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"2025092207411312000_CIT0001","article-title":"TensorFlow: A system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"2025092207411312000_CIT0002","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"NPJ Digit. Med"},{"key":"2025092207411312000_CIT0003","doi-asserted-by":"publisher","first-page":"100723","DOI":"10.1016\/j.imu.2021.100723","article-title":"An overview of deep learning in medical imaging","volume":"26","author":"Anaya-Isaza","year":"2021","journal-title":"Inf. Med. Unlocked"},{"key":"2025092207411312000_CIT0004","doi-asserted-by":"publisher","first-page":"107674","DOI":"10.1016\/j.compag.2023.107674","article-title":"Identifying pregnancy in cows using ovarian ultrasound images and convolutional neural networks - a proof-of-concept study","volume":"206","author":"Andrade","year":"2023","journal-title":"Comput. Electron. Agric"},{"key":"2025092207411312000_CIT0005","doi-asserted-by":"publisher","first-page":"106133","DOI":"10.1016\/j.compag.2021.106133","article-title":"Visual identification of individual Holstein-Friesian cattle via deep metric learning","volume":"185","author":"Andrew","year":"2021","journal-title":"Comput. Electron. Agric"},{"key":"2025092207411312000_CIT0006","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1016\/0093-691x(93)90234-v","article-title":"Corpus luteum size and plasma progesterone levels in cattle after cloprostenol-induced luteolysis","volume":"39","author":"Assey","year":"1993","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0007","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1016\/0093-691x(91)90362-h","article-title":"Factors influencing the accuracy of early pregnancy detection in cattle by real-time ultrasound scanning of the uterus","volume":"35","author":"Badtram","year":"1991","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0008","doi-asserted-by":"publisher","first-page":"924","DOI":"10.2527\/1992.703924x","article-title":"The use of ultrasound in monitoring reproductive physiology of beef cattle","volume":"70","author":"Beal","year":"1992","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0009","doi-asserted-by":"publisher","first-page":"4980","DOI":"10.3168\/jds.2020-18367","article-title":"Predicting pregnancy status from mid-infrared spectroscopy in dairy cow milk using deep learning","volume":"104","author":"Brand","year":"2021","journal-title":"J. Dairy Sci"},{"key":"2025092207411312000_CIT0010","doi-asserted-by":"publisher","first-page":"664","DOI":"10.3168\/jds.2022-22138","article-title":"Assessing optimal frequency for image acquisition in computer vision systems developed to monitor feeding behavior of group-housed Holstein heifers","volume":"106","author":"Bresolin","year":"2023","journal-title":"J. Dairy Sci"},{"key":"2025092207411312000_CIT0012","author":"Chollet","year":"2015"},{"key":"2025092207411312000_CIT0011","first-page":"1800","article-title":"Xception: Deep learning with depthwise separable convolutions","volume-title":"Proc. 2017 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Chollet","year":"2017"},{"key":"2025092207411312000_CIT0013","doi-asserted-by":"publisher","first-page":"103904","DOI":"10.1016\/j.livsci.2019.103904","article-title":"Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases","volume":"232","author":"Cominotte","year":"2020","journal-title":"Livest. Sci"},{"key":"2025092207411312000_CIT0014","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.2527\/jas.2013-6465","article-title":"Heifer calving date positively influences calf weaning weights through six parturitions1","volume":"91","author":"Cushman","year":"2013","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0015","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.theriogenology.2020.04.001","article-title":"Applied use of interferon-tau stimulated genes expression in polymorphonuclear cells to detect pregnancy compared to other early predictors in beef cattle","volume":"152","author":"Dalmaso de Melo","year":"2020","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0016","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"ImageNet: A large-scale hierarchical image database","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"2025092207411312000_CIT0017","doi-asserted-by":"publisher","first-page":"11418","DOI":"10.1038\/s41598-022-14993-2","article-title":"Deep learning in veterinary medicine, an approach based on CNN to detect pulmonary abnormalities from lateral thoracic radiographs in cats","volume":"12","author":"Dumortier","year":"2022","journal-title":"Sci. Rep"},{"key":"2025092207411312000_CIT0018","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.theriogenology.2024.05.006","article-title":"Accuracy of early pregnancy diagnosis and determining pregnancy loss using different biomarkers and machine learning applications in dairy cattle","volume":"224","author":"Ferraz","year":"2024","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0019","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1002\/bimj.200410135","article-title":"Estimation of the Youden Index and its associated cutoff point","volume":"47","author":"Fluss","year":"2005","journal-title":"Biom J"},{"key":"2025092207411312000_CIT0020","doi-asserted-by":"publisher","first-page":"912854","DOI":"10.3389\/fanim.2022.912854","article-title":"Applied use of doppler ultrasonography in bovine reproduction","volume":"3","author":"Fontes","year":"2022","journal-title":"Front. Anim. Sci"},{"key":"2025092207411312000_CIT0021","doi-asserted-by":"publisher","first-page":"5118","DOI":"10.2527\/jas.2012-5263","article-title":"Effect of calving distribution on beef cattle progeny performance","volume":"90","author":"Funston","year":"2012","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0022","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1186\/1746-6148-8-164","article-title":"Pregnancy detection and monitoring in cattle via combined foetus electrocardiogram and phonocardiogram signal processing","volume":"8","author":"Gargiulo","year":"2012","journal-title":"BMC Vet. Res"},{"key":"2025092207411312000_CIT0023","doi-asserted-by":"publisher","first-page":"104204H","DOI":"10.1117\/12.2281723","article-title":"Neural analysis of bovine ovaries ultrasound images in the identification process of the corpus luteum","author":"G\u00f3rna","year":"2017"},{"key":"2025092207411312000_CIT0024","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"2025092207411312000_CIT0025","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1016\/j.theriogenology.2009.11.016","article-title":"Luteal blood flow is a more appropriate indicator for luteal function during the bovine estrous cycle than luteal size","volume":"73","author":"Herzog","year":"2010","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0026","doi-asserted-by":"publisher","first-page":"skac335","DOI":"10.1093\/jas\/skac335","article-title":"Evaluating the use of luteal color Doppler ultrasonography and pregnancy-associated glycoproteins to diagnose pregnancy and predict pregnancy loss in Bos taurus beef replacement heifers","volume":"100","author":"Holton","year":"2022","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0027","doi-asserted-by":"publisher","first-page":"skac018","DOI":"10.1093\/jas\/skac018","article-title":"Luteal color doppler ultrasonography and pregnancy-associated glycoproteins as early pregnancy diagnostic tools and predictors of pregnancy loss in Bos taurus postpartum beef cows","volume":"100","author":"Holton","year":"2022","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0028","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1016\/0093-691x(90)90045-u","article-title":"Relationship between ultrasonic assessment of the corpus luteum and plasma progesterone concentration in heifers","volume":"33","author":"Kastelic","year":"1990","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0029","doi-asserted-by":"publisher","first-page":"3000","DOI":"10.2527\/jas.2006-220","article-title":"Synchronization of estrus and artificial insemination in replacement beef heifers using gonadotropin-releasing hormone, prostaglandin F2alpha, and progesterone","volume":"84","author":"Lamb","year":"2006","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0030","doi-asserted-by":"publisher","first-page":"162","DOI":"10.15232\/pas.2015-01455","article-title":"Invited Review: advantages of current and future reproductive technologies for beef cattle production1,2","volume":"32","author":"Lamb","year":"2016","journal-title":"Professional Anim. Scientist"},{"key":"2025092207411312000_CIT0031","doi-asserted-by":"publisher","first-page":"332","DOI":"10.2527\/2006.842332x","article-title":"Synchronization of estrus in suckled beef cows for detected estrus and artificial insemination and timed artificial insemination using gonadotropin-releasing hormone, prostaglandin F2\u03b1, and progesterone1","volume":"84","author":"Larson","year":"2006","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0032","doi-asserted-by":"publisher","author":"Lin","year":"2014","DOI":"10.48550\/arXiv.1312.4400"},{"key":"2025092207411312000_CIT0033","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1111\/j.1751-0813.2003.tb11435.x","article-title":"Accuracy of bovine pregnancy detection using transrectal ultrasonography at 28 to 35 days after insemination","volume":"81","author":"Nation","year":"2003","journal-title":"Aust. Vet. J"},{"key":"2025092207411312000_CIT0034"},{"key":"2025092207411312000_CIT0035","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/0093-691x(84)90435-7","article-title":"Ultrasonography for detection of pregnancy and study of embryonic development in heifers","volume":"22","author":"Pierson","year":"1984","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0036","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1016\/0093-691x(90)90547-7","article-title":"Early pregnancy diagnosis in cattle by means of linear-array real-time ultrasound scanning of the uterus and a qualitative and quantitative milk progesterone test","volume":"33","author":"Pieterse","year":"1990","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0038","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1095\/biolreprod.114.121525","article-title":"Conceptus-Induced changes in the gene expression of blood immune cells and the ultrasound-accessed luteal function in beef cattle: How early can we detect pregnancy?1","volume":"91","author":"Pugliesi","year":"2014","journal-title":"Biol. Reprod"},{"key":"2025092207411312000_CIT0037","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.theriogenology.2019.06.006","article-title":"Use of color-Doppler ultrasonography for selection of recipients in timed-embryo transfer programs in beef cattle","volume":"135","author":"Pugliesi","year":"2019","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0049","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1262\/jrd.45.13","article-title":"Bovine reproductive ultrasonography: a review","volume":"45","author":"Ribadu","year":"1999","journal-title":"J. Reprod. Dev"},{"key":"2025092207411312000_CIT0039","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.anireprosci.2018.12.003","article-title":"Ultrasonography-accessed luteal size endpoint that most closely associates with circulating progesterone during the estrous cycle and early pregnancy in beef cows","volume":"201","author":"Rocha","year":"2019","journal-title":"Anim. Reprod. Sci"},{"key":"2025092207411312000_CIT0040","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1016\/j.theriogenology.2006.02.044","article-title":"Early pregnancy diagnosis by transrectal ultrasonography in dairy cattle","volume":"66","author":"Romano","year":"2006","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0041","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.theriogenology.2023.07.039","article-title":"Conception rate and pregnancy loss in fixed-time cattle embryo transfer programs are related to the luteal blood perfusion but not to the corpus luteum size","volume":"210","author":"dos Santos","year":"2023","journal-title":"Theriogenology"},{"key":"2025092207411312000_CIT0042","doi-asserted-by":"publisher","author":"Simonyan","year":"2015","DOI":"10.48550\/arXiv.1409.1556"},{"key":"2025092207411312000_CIT0043","doi-asserted-by":"publisher","first-page":"6461","DOI":"10.3168\/jds.2013-6814","article-title":"Color Doppler flow imaging for the early detection of nonpregnant cattle at 20 days after timed artificial insemination","volume":"96","author":"Siqueira","year":"2013","journal-title":"J. Dairy Sci"},{"key":"2025092207411312000_CIT0044","doi-asserted-by":"publisher","first-page":"2111","DOI":"10.2527\/jas.2014-8391","article-title":"Progesterone status, parity, body condition, and days postpartum before estrus or ovulation synchronization in suckled beef cattle influence artificial insemination pregnancy outcomes1","volume":"93","author":"Stevenson","year":"2015","journal-title":"J. Anim. Sci"},{"key":"2025092207411312000_CIT0045","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.3168\/jds.2017-13647","article-title":"Diagnosing pregnancy status using infrared spectra and milk composition in dairy cows","volume":"101","author":"Toledo-Alvarado","year":"2018","journal-title":"J. Dairy Sci"},{"key":"2025092207411312000_CIT0046","volume-title":"The Python language reference manual","author":"Van Rossum","year":"2024"},{"key":"2025092207411312000_CIT0047","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"2025092207411312000_CIT0048","doi-asserted-by":"publisher","first-page":"txad085","DOI":"10.1093\/tas\/txad085","article-title":"Estimating body weight and body condition score of mature beef cows using depth images","volume":"7","author":"Xiong","year":"2023","journal-title":"Transl Anim Sci"},{"key":"2025092207411312000_CIT0050","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1002\/jum.16006","article-title":"Classification of thyroid nodules by using deep learning radiomics based on ultrasound dynamic video","volume":"41","author":"Zhang","year":"2022","journal-title":"J. Ultrasound Med"},{"key":"2025092207411312000_CIT0051","doi-asserted-by":"publisher","first-page":"110885","DOI":"10.1016\/j.ejrad.2023.110885","article-title":"Deep learning-based classification of breast lesions using dynamic ultrasound video","volume":"165","author":"Zhao","year":"2023","journal-title":"Eur. J. Radiol"}],"container-title":["Journal of Animal Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jas\/advance-article-pdf\/doi\/10.1093\/jas\/skaf166\/63158714\/skaf166.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skaf166\/63158714\/skaf166.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skaf166\/63158714\/skaf166.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T11:41:22Z","timestamp":1758541282000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jas\/article\/doi\/10.1093\/jas\/skaf166\/8129065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1093\/jas\/skaf166","relation":{},"ISSN":["0021-8812","1525-3163"],"issn-type":[{"value":"0021-8812","type":"print"},{"value":"1525-3163","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"skaf166"}}