{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:34:25Z","timestamp":1789029265897,"version":"build-2803163510"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"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. Vet. Sci."],"abstract":"<jats:p>\n                    Sperm viability analysis is directly related to fertility rates, and eosin\/nigrosin staining is one of the most essential methods for assessing sperm viability. Although this method is easy to apply, it is time-consuming and has a high error rate due to its high subjectivity. Flow cytometric analyses, an alternative to the eosin\/nigrosin method that is highly reliable, are not accessible due to the need for specialized personnel and high costs. Therefore, in this study, four different artificial intelligence models (YOLOv8, YOLOv12, Faster R-CNN, and YOLOv5\u202f+\u202fHRNet) were utilized to analyze eosin\/nigrosin-stained sperm samples with high reliability, and their performance was compared. For this purpose, 15 different frozen bull sperm samples were purchased, thawed in a water bath at 37\u202f\u00b0C, and smears were prepared using the eosin\/nigrosin method. A total of 3,068 photographs were taken from the prepared smears: 2140 for model training, 512 for validation, and 416 for testing. In the test set analysis, the YOLOv8 model demonstrated the highest overall performance (balanced accuracy: 97.1%; F1 score: 0.978), followed by YOLOv12 (balanced accuracy: 94.1%; F1 score: 0.958). While Faster R-CNN delivered mid-level performance, the YOLOv5\u202f+\u202fHRNet model showed a significant performance loss, particularly in dead sperm detection, due to low specificity. To measure the clinical usability of the trained models, another smear set was prepared and photographed. In the independent mock test, 281 spermatozoa from 36 images were evaluated by the trained models and compared with both the ground truth and an expert evaluator. The expert achieved a balanced accuracy of 98.8%, while YOLOv12 demonstrated the highest performance among the AI models (balanced accuracy: 91.3%, F1 score: 0.895). Statistical comparison using McNemar\u2019s test revealed no significant difference between YOLOv8, YOLOv12, Faster R-CNN, and the reference evaluation (\n                    <jats:italic>p<\/jats:italic>\n                    \u202f&amp;gt;\u202f0.05). On average, AI-based analysis was 16.7 times faster than manual counting. The results reinforce the possibility that artificial intelligence models, updated with future studies, could be used in sperm viability analysis.\n                  <\/jats:p>","DOI":"10.3389\/fvets.2026.1772252","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T06:37:14Z","timestamp":1773643034000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Performance comparison of YOLO, Faster R-CNN, and HRNet architectures for bull sperm viability assessment"],"prefix":"10.3389","volume":"13","author":[{"given":"Ali Erdem","family":"\u00d6zt\u00fcrk","sequence":"first","affiliation":[{"name":"Department of Reproduction and Artificial Insemination, Faculty of Veterinary Medicine, Erciyes University","place":["Kayseri, T\u00fcrkiye"]},{"name":"ReproFellas Research Group, ArGePark Research Center, Erciyes University","place":["Kayseri, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatih \u0130smail","family":"Bahar","sequence":"additional","affiliation":[{"name":"ReproFellas Research Group, ArGePark Research Center, Erciyes University","place":["Kayseri, T\u00fcrkiye"]},{"name":"Faculty of Veterinary Medicine, Erciyes University","place":["Kayseri, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunus Emre","family":"Atay","sequence":"additional","affiliation":[{"name":"ReproFellas Research Group, ArGePark Research Center, Erciyes University","place":["Kayseri, T\u00fcrkiye"]},{"name":"Department of Obstetrics and Gynecology, Faculty of Veterinary Medicine, Erciyes University","place":["Kayseri, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mustafa","family":"Bodu","sequence":"additional","affiliation":[{"name":"ReproFellas Research Group, ArGePark Research Center, Erciyes University","place":["Kayseri, T\u00fcrkiye"]},{"name":"Department of Reproduction and Artificial Insemination, Faculty of Veterinary Medicine, Sel\u00e7uk University","place":["Konya, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcven","family":"G\u00fcng\u00f6r","sequence":"additional","affiliation":[{"name":"Department of Veterinary Biostatistics, Faculty of Veterinary Medicine, Bing\u00f6l University","place":["Bingol, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/aja.2010.67","article-title":"Measurement and significance of sperm morphology","volume":"13","author":"Menkveld","year":"2010","journal-title":"Asian J Androl"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1093\/oxfordjournals.humrep.a137876","article-title":"Estimating fertility potential via semen analysis data","volume":"8","author":"Bartoov","year":"1993","journal-title":"Hum Reprod"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"3563","DOI":"10.3390\/ani11123563","article-title":"An exploration of current and perspective semen analysis and sperm selection for livestock artificial insemination","volume":"11","author":"Zuidema","year":"2021","journal-title":"Animals"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e13725","DOI":"10.1111\/and.13725","article-title":"Sperm selection strategies and their impact on assisted reproductive technology outcomes","volume":"53","author":"Pinto","year":"2021","journal-title":"Andrologia"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1016\/j.rbmo.2020.03.002","article-title":"A technical note on the assessment of human sperm vitality using eosin\u2013nigrosin staining","volume":"40","author":"Mortimer","year":"2020","journal-title":"Reprod Biomed Online"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"13","DOI":"10.32707\/ercivet.1557680","article-title":"The effects of mesoporous silica nanoparticles on spermatological parameters of merino ram","volume":"22","author":"\u00d6zt\u00fcrk","year":"2025","journal-title":"Erciyes \u00dcniversitesi Veteriner Fak\u00fcltesi Dergisi"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/S0015-0282(16)30126-1","article-title":"Study of sperm vitality with the aid of eosin-nigrosin stain","volume":"1","author":"Williams","year":"1950","journal-title":"Fertil Steril"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1017\/9781108878715.009","volume-title":"Manual of Sperm Function Testing in Human Assisted Reproduction","author":"Sharma","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e70132","DOI":"10.1111\/rda.70132","article-title":"Evaluation of Afp iii-conjugated Fe3o4 nanoparticles on bull sperm cryopreservation","volume":"60","author":"Ozturk","year":"2025","journal-title":"Reprod Domest Anim"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1002\/cyto.a.21044","article-title":"Cytometric solutions in veterinary andrology: developments, advantages, and limitations","volume":"79","author":"Petrunkina","year":"2011","journal-title":"Cytometry A"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"106838","DOI":"10.1016\/j.anireprosci.2021.106838","article-title":"Commercial application of flow cytometry for evaluating bull sperm","volume":"246","author":"DeJarnette","year":"2022","journal-title":"Anim Reprod Sci"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"16560","DOI":"10.1038\/s41598-023-43678-7","article-title":"Validation of the volumetric flow cytometry for bovine sperm concentration","volume":"13","author":"Gloria","year":"2023","journal-title":"Sci Rep"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1093\/humrep\/deg199","article-title":"Evaluation of the one-step eosin-Nigrosin staining technique for human sperm vitality assessment","volume":"18","author":"Bj\u00f6rndahl","year":"2003","journal-title":"Hum Reprod"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"395","DOI":"10.46309\/biodicon.2025.1630745","article-title":"Effects of different doses and sizes of Bsa nanoparticles on cryopreservation of angora buck semen: motility, functional membrane \u0131ntegrity and, viability","volume":"18","author":"\u00d6zt\u00fcrk","year":"2025","journal-title":"Biol Diver Conserv"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"117504","DOI":"10.1016\/j.theriogenology.2025.117504","article-title":"Evaluation of an artificial intelligence system for bull sperm morphology evaluation","volume":"245","author":"Urli","year":"2025","journal-title":"Theriogenology"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An overview of overfitting and its solutions","author":"Ying","year":"2019","journal-title":"J Phys Conf Ser"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2009"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.3390\/vetsci12101015","article-title":"Design and implementation of a deep learning system to analyze bovine sperm morphology","volume":"12","author":"Sevilla","year":"2025","journal-title":"Vet Sci"},{"key":"ref19","volume-title":"WHO Laboratory Manual for the Examination and Processing of Human Semen","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1186\/s12894-025-01946-w","article-title":"Deep learning-based approach for sperm morphology analysis","volume":"25","author":"Liang","year":"2025","journal-title":"BMC Urol"},{"key":"ref21","author":"Rezatofighi","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"21300","DOI":"10.1109\/ACCESS.2023.3249759","article-title":"Assessing inter-annotator agreement for medical image segmentation","volume":"11","author":"Yang","year":"2023","journal-title":"IEEE Access"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"60921","DOI":"10.1007\/s11042-023-17838-w","article-title":"An improved Yolov8 for foreign object debris detection with optimized architecture for small objects","volume":"83","author":"Farooq","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"ref26","author":"Tian","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-Cnn: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of Yolo architectures in computer vision: from Yolov1 to Yolov8 and Yolo-Nas","volume":"5","author":"Terven","year":"2023","journal-title":"Machine Learn Knowl Extract"},{"key":"ref29","author":"Sulistyaningrum","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"7318","DOI":"10.3390\/s24227318","article-title":"Coal and gangue detection networks with compact and high-performance design","volume":"24","author":"Cao","year":"2024","journal-title":"Sensors"},{"key":"ref31","author":"Sun","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1111\/mice.12387","article-title":"Road damage detection and classification using deep neural networks with smartphone images","volume":"33","author":"Maeda","year":"2018","journal-title":"Comput Aided Civ Infrastruct Eng"},{"key":"ref33","author":"Goyal","year":"2017"},{"key":"ref34","author":"Gotmare","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"94","DOI":"10.32707\/ercivet.1142552","article-title":"Buza\u011f\u0131 Hastal\u0131klar\u0131 \u00dczerine Etkili Fakt\u00f6rlerin S\u0131n\u0131fland\u0131r\u0131lmas\u0131nda Yapay Sinir A\u011flar\u0131, Rassal Orman Algoritmas\u0131 Ve Lojistik Regresyon Analizi Performanslar\u0131n\u0131n Kar\u015f\u0131la\u015ft\u0131r\u0131lmas\u0131","volume":"19","author":"G\u00fcng\u00f6r","year":"2022","journal-title":"Erciyes \u00dcniversitesi Veteriner Fak\u00fcltesi Dergisi"},{"key":"ref36","volume-title":"General Object Detection Algorithm Yolov5 Comparison and Improvement","author":"Du","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"2622","DOI":"10.3390\/ani13162622","article-title":"Deep learning-based precision analysis for acrosome reaction by modification of plasma membrane in boar sperm","volume":"13","author":"Park","year":"2023","journal-title":"Animals"},{"key":"ref38","author":"Wang","year":"2022"},{"key":"ref39","author":"Lin","year":"2017"},{"key":"ref40","author":"Bodla","year":"2017"}],"container-title":["Frontiers in Veterinary Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2026.1772252\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T06:37:15Z","timestamp":1773643035000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2026.1772252\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":40,"alternative-id":["10.3389\/fvets.2026.1772252"],"URL":"https:\/\/doi.org\/10.3389\/fvets.2026.1772252","relation":{},"ISSN":["2297-1769"],"issn-type":[{"value":"2297-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"article-number":"1772252"}}