{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:15:16Z","timestamp":1783577716393,"version":"3.55.0"},"reference-count":16,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"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. Pediatr."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Congenital heart disease (CHD) is a clinically important fetal anomaly. Early-pregnancy fetal cardiac microflow imaging (FCMI) can show low-velocity intracardiac flow, but brief shunt-related, regurgitant, and outflow-tract disturbances remain difficult to recognize when image quality, fetal position, and gestational age vary across examinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate uFlowAM for fetus-level detection and visualization of abnormal intracardiac microflow patterns on early-pregnancy FCMI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This multicenter diagnostic accuracy study analyzed 650 early-pregnancy FCMI examinations from fetuses referred for suspected CHD or CHD risk assessment, including 500 examinations in the internal cohort and 150 in the external cohort. Standard four-chamber, left ventricular outflow tract (LVOT), and right ventricular outflow tract (RVOT) clips were processed by microflow extraction, cardiac-cycle alignment, signal normalization, and 16-frame windowing. uFlowAM used self-supervised training to learn a 256-dimensional representation of control fetal microflow from temporal-order discrimination and masked-frame reconstruction. Model training used no pixel-level or lesion-level labels. Control embeddings were grouped by view and cardiac phase to build a normal microflow template library, and an abnormality index (AbI) was calculated from latent-space Mahalanobis distances. The operating threshold was calibrated in internal validation and then kept fixed for external testing. Clinical utility was assessed in a 9-reader, 240-case multi-reader multi-case (MRMC) study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Using the fixed operating threshold (\n                      <jats:italic>\u03c4<\/jats:italic>\n                      *\u2009=\u20092.15), uFlowAM achieved an area under the receiver operating characteristic curve (AUC) of 0.94 (95% CI, 0.92\u20130.96), sensitivity of 0.92, and specificity of 0.88 in the internal cohort. In the external cohort, AUC was 0.92 (95% CI, 0.88\u20130.95), with sensitivity of 0.90 and specificity of 0.86. Median reader-level AUC increased from 0.85 to 0.92 with uFlowAM assistance, weighted kappa for subtype agreement increased from 0.62 to 0.78, visibility scores increased from 2.8\u2009\u00b1\u20090.6 to 4.3\u2009\u00b1\u20090.5, and median reading time decreased from 78 s to 59 s. Mean inference time was 6.8\u2009\u00b1\u20091.3 s per case.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In this CHD-enriched referral\/risk-assessment cohort, uFlowAM detected abnormal early-pregnancy fetal cardiac microflow patterns and improved reader consistency and efficiency on selected fetal cardiac microflow views. The framework should be considered an assistive second-reader tool for early fetal CHD assessment. It should not be used as a substitute for a complete fetal echocardiographic examination.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fped.2026.1888687","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:34:17Z","timestamp":1783575257000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["uFlowAM: an unsupervised framework for detection and visualization of abnormal intracardiac microflow on early-pregnancy fetal cardiac microflow imaging"],"prefix":"10.3389","volume":"14","author":[{"given":"Yan","family":"Xia","sequence":"first","affiliation":[{"name":"Department of Ultrasound Medicine, Peking University First Hospital Ningxia Women and Children\u2019s Hospital (Ningxia Hui Autonomous Region Maternal and Child Health Hospital)","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]},{"name":"The Third Clinical College, Ningxia Medical University","place":["Yinchuan, Ningxia, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yarui","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Peking University First Hospital Ningxia Women and Children\u2019s Hospital (Ningxia Hui Autonomous Region Maternal and Child Health Hospital)","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanru","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Ultrasonography, Ningxia Guyuan Maternal and Child Health Hospital","place":["Guyuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Peking University First Hospital Ningxia Women and Children\u2019s Hospital (Ningxia Hui Autonomous Region Maternal and Child Health Hospital)","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, Beijing Genertec Aerospace Hospital","place":["Beijing, China"]},{"name":"School of Automation and Intelligence, Beijing Jiaotong University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqin","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Peking University First Hospital Ningxia Women and Children\u2019s Hospital (Ningxia Hui Autonomous Region Maternal and Child Health Hospital)","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1016\/j.jacc.2011.08.025","article-title":"Birth prevalence of congenital heart disease worldwide: a systematic review and meta-analysis","volume":"58","author":"van der Linde","year":"2011","journal-title":"J Am Coll Cardiol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/S2352-4642(19)30402-X","article-title":"Global, regional, and national burden of congenital heart disease, 1990\u20132017: a systematic analysis for the global burden of disease study 2017","volume":"4","year":"2020","journal-title":"Lancet Child Adolesc Health"},{"key":"B3","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s12968-015-0174-5","article-title":"4D Flow cardiovascular magnetic resonance consensus statement","volume":"17","author":"Dyverfeldt","year":"2015","journal-title":"J Cardiovasc Magn Reson"},{"key":"B4","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1186\/s12968-023-00942-z","article-title":"4D Flow cardiovascular resonance consensus statement: 2023 update","volume":"25","author":"Bissell","year":"2023","journal-title":"J Cardiovasc Magn Reson"},{"key":"B5","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1148\/rg.2019180091","article-title":"Four-dimensional flow MRI: principles and cardiovascular applications","volume":"39","author":"Azarine","year":"2019","journal-title":"Radiographics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1017\/S1047951112002028","article-title":"Computational fluid dynamics in congenital heart disease","volume":"22","author":"DeCampli","year":"2012","journal-title":"Cardiol Young"},{"key":"B7","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1177\/0218492320957163","article-title":"Computational fluid dynamics: a primer for congenital heart disease clinicians","volume":"28","author":"Gerrah","year":"2020","journal-title":"Asian Cardiovasc Thorac Ann"},{"key":"B8","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","article-title":"Video-based AI for beat-to-beat assessment of cardiac function","volume":"580","author":"Ouyang","year":"2020","journal-title":"Nature"},{"key":"B9","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","article-title":"f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks","volume":"54","author":"Schlegl","year":"2019","journal-title":"Med Image Anal"},{"key":"B10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s12859-020-03936-1","article-title":"MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction","volume":"22","author":"Han","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"B11","doi-asserted-by":"publisher","first-page":"101952","DOI":"10.1016\/j.media.2020.101952","article-title":"Autoencoders for unsupervised anomaly segmentation in brain MR images: a comparative study","volume":"69","author":"Baur","year":"2021","journal-title":"Med Image Anal"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2436","DOI":"10.1038\/s41467-023-38125-0","article-title":"Cross-modal autoencoder framework learns holistic representations of cardiovascular state","volume":"14","author":"Radhakrishnan","year":"2023","journal-title":"Nat Commun"},{"key":"B13","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1148\/radiol.2015151516","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies","volume":"277","author":"Bossuyt","year":"2015","journal-title":"Radiology"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers","volume":"2","author":"Mongan","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2026.3695309","article-title":"Semi-Supervised medical image segmentation with dual-view differential feature reinjection","author":"Qiao","year":"2026","journal-title":"IEEE J Biomed Health Inform"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2026.3668775","article-title":"Liquid-Sequencer: a lightweight liquid neural network for real-time fetal congenital heart disease diagnosis","author":"Qiao","year":"2026","journal-title":"IEEE J Biomed Health Inform"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1888687\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:34:17Z","timestamp":1783575257000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1888687\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":16,"alternative-id":["10.3389\/fped.2026.1888687"],"URL":"https:\/\/doi.org\/10.3389\/fped.2026.1888687","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"article-number":"1888687"}}