{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:18:29Z","timestamp":1772093909014,"version":"3.50.1"},"reference-count":36,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001786","name":"University of Adelaide","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001786","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Australas J Ultrason Med"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Accurate diagnosis of pathology from ultrasound images is reliant upon images of a suitable diagnostic quality being acquired. This study aimed to create a novel machine learning model to automatically assess transvaginal ultrasound (TVUS) image quality for gynaecological ultrasound.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>Six imaging professionals (two sonographers, two gynaecological sonologists and two radiologists) assigned a quality score to 150 TVUS images from 50 cases (50 uterus images and 100 ovary images). Images were given a score of 1\u20134 (1\u2014reject\/image inaccurate, 2\u2014poor quality, 3\u2014suboptimal quality or 4\u2014optimal quality). As variation existed between the scores assigned by the labellers, we framed this problem as a multi\u2010annotator noisy label problem. To address this, a new machine learning architecture was developed, combining a weighted ensemble algorithm to estimate consensus labels and a multi\u2010axis vision transformer (MaxViT) to handle noisy labels, improving model accuracy in predicting image quality. Forty cases (120 images) were used for model training, while the remaining 10 cases (30 images) were reserved as a test set for model evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The novel machine learning architecture we created was able to successfully determine image quality with a validation accuracy of 80% and a macro average recall of 77%. This significantly improved upon the 57% accuracy of the baseline machine learning method (ResNet50). The MaxViTs were able to outperform human performance in most cases, with an accuracy of 80% surpassing four of the six human labellers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This novel machine learning model offers an automated method of assessing the quality of TVUS images. The tool has the potential to provide real\u2010time feedback to those performing TVUS, reduce the need for repeated imaging, and improve the diagnosis of gynaecological pathology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/ajum.70026","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T05:15:59Z","timestamp":1758604559000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Development of a Novel Machine Learning Model for Automatic Assessment of Quality of Transvaginal Ultrasound Images From Multi\u2010Annotator Labels"],"prefix":"10.1002","volume":"28","author":[{"given":"Alison","family":"Deslandes","sequence":"first","affiliation":[{"name":"Robinson Research Institute University of Adelaide  Adelaide Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Petashvili","sequence":"additional","affiliation":[{"name":"School of Computer and Mathematical Sciences University of Adelaide  Adelaide Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Wang","sequence":"additional","affiliation":[{"name":"Australian Institute of Machine Learning University of Adelaide  Adelaide Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustavo","family":"Carnerio","sequence":"additional","affiliation":[{"name":"University of Surrey  Guildford UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jodie","family":"Avery","sequence":"additional","affiliation":[{"name":"Robinson Research Institute University of Adelaide  Adelaide Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Condous","sequence":"additional","affiliation":[{"name":"Robinson Research Institute University of Adelaide  Adelaide Australia"},{"name":"Endometriosis Ultrasound &amp; Advanced Endosurgey Unit, Sydney Medical School Nepean University of Sydney, Nepean Hospital  Sydney New South Wales Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5538-6906","authenticated-orcid":false,"given":"Mathew","family":"Leonardi","sequence":"additional","affiliation":[{"name":"Robinson Research Institute University of Adelaide  Adelaide Australia"},{"name":"Department of Obstetrics and Gynecology McMaster University  Hamilton Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Louise","family":"Hull","sequence":"additional","affiliation":[{"name":"Robinson Research Institute University of Adelaide  Adelaide Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiang\u2010Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer and Mathematical Sciences University of Adelaide  Adelaide Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.22122"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.29178"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.19101"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.13376"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.37015\/AUDT.2021.210003"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.26661"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9938367"},{"key":"e_1_2_12_9_1","unstructured":"H.Luo H.Liu K.Li andB.Zhang \u201cAutomatic Quality Assessment for 2D Fetal Sonographic Standard Plane Based on Multi\u2010Task Learning [Internet] \u201darXiv(2019) http:\/\/arxiv.org\/abs\/1912.05260."},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000024427"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.119.009303"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.xjidi.2024.100285"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101759"},{"key":"e_1_2_12_14_1","unstructured":"H. W.Goh U.Tkachenko andJ.Mueller \u201cCROWDLAB: Supervised Learning to Infer Consensus Labels and Quality Scores for Data With Multiple Annotators [Internet] \u201darXiv(2023) http:\/\/arxiv.org\/abs\/2210.06812."},{"key":"e_1_2_12_15_1","article-title":"TRIPOD+AI Statement: Updated Guidance for Reporting Clinical Prediction Models That Use Regression or Machine Learning Methods","volume":"385","author":"Collins G. S.","year":"2024","journal-title":"BMJ (Clinical Research Ed.)"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"e_1_2_12_17_1","doi-asserted-by":"crossref","unstructured":"Z.Tu H.Talebi H.Zhang et\u00a0al. \u201cMaxViT: Multi\u2010Axis Vision Transformer [Internet] \u201darXiv(2022) http:\/\/arxiv.org\/abs\/2204.01697.","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_12_19_1","first-page":"1","volume-title":"IEEE International Symposium on Biomedical Imaging (ISBI)","author":"Petashvili D.","year":"2024"},{"key":"e_1_2_12_20_1","unstructured":"I.LoshchilovandF.Hutter \u201cDecoupled weight Decay Regularization \u201dInInternational Conference on Learning Representations 2019 https:\/\/doi.org\/10.48550\/arXiv.1711.05101."},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13063693"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959209"},{"key":"e_1_2_12_24_1","first-page":"40","article-title":"Artificial Intelligence in Diagnostic Ultrasonography","volume":"29","author":"Dicle O.","year":"2023","journal-title":"Diagnostic and Interventional Radiology"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.14366\/usg.21031"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020192224"},{"key":"e_1_2_12_27_1","first-page":"10520","volume-title":"Proceedings of the 26th International Conference on Artificial Intelligence and Statistics","author":"Mozannar H.","year":"2023"},{"key":"e_1_2_12_28_1","volume-title":"Advances in Neural Information Processing Systems","author":"Madras D.","year":"2018"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160435"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/sono.12305"},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2020.12.512"},{"key":"e_1_2_12_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101548"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-56476-6"},{"key":"e_1_2_12_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2690836"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.118.034338"},{"key":"e_1_2_12_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10554-020-02046-6"},{"key":"e_1_2_12_37_1","unstructured":"Food and Drug Administration \u201cFDA Authorizes Marketing of First Cardiac Ultrasound Software That Uses Artificial Intelligence to Guide User [Internet] \u201d 2020 https:\/\/www.fda.gov\/news\u2010events\/press\u2010announcements\/fda\u2010authorizes\u2010marketing\u2010first\u2010cardiacultrasound\u2010software\u2010uses\u2010artificial\u2010intelligence\u2010guide\u2010user."}],"container-title":["Australasian Journal of Ultrasound in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ajum.70026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T09:15:51Z","timestamp":1764234951000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ajum.70026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1002\/ajum.70026"],"URL":"https:\/\/doi.org\/10.1002\/ajum.70026","archive":["Portico"],"relation":{},"ISSN":["1836-6864","2205-0140"],"issn-type":[{"value":"1836-6864","type":"print"},{"value":"2205-0140","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"2025-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70026"}}