{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T04:39:43Z","timestamp":1773808783716,"version":"3.50.1"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"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. Digit. Health"],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Extraction of Doppler-based measurements from feto-placental Doppler images is crucial in identifying vulnerable new-borns prenatally. However, this process is time-consuming, operator dependent, and prone to errors.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address this, our study introduces an artificial intelligence (AI) enabled workflow for automating feto-placental Doppler measurements from four sites (i.e., Umbilical Artery (UA), Middle Cerebral Artery (MCA), Aortic Isthmus (AoI) and Left Ventricular Inflow and Outflow (LVIO)), involving classification and waveform delineation tasks. Derived from data from a low- and middle-income country, our approach's versatility was tested and validated using a dataset from a high-income country, showcasing its potential for standardized and accurate analysis across varied healthcare settings.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The classification of Doppler views was approached through three distinct blocks: (i) a Doppler velocity amplitude-based model with an accuracy of 94%, (ii) two Convolutional Neural Networks (CNN) with accuracies of 89.2% and 67.3%, and (iii) Doppler view- and dataset-dependent confidence models to detect misclassifications with an accuracy higher than 85%. The extraction of Doppler indices utilized Doppler-view dependent CNNs coupled with post-processing techniques. Results yielded a mean absolute percentage error of 6.1\u2009\u00b1\u20094.9% (<jats:italic>n<\/jats:italic>\u2009=\u2009682), 1.8\u2009\u00b1\u20091.5% (<jats:italic>n<\/jats:italic>\u2009=\u20091,480), 4.7\u2009\u00b1\u20094.0% (<jats:italic>n<\/jats:italic>\u2009=\u2009717), 3.5\u2009\u00b1\u20093.1% (<jats:italic>n<\/jats:italic>\u2009=\u20091,318) for the magnitude location of the systolic peak in LVIO, UA, AoI and MCA views, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The developed models proved to be highly accurate in classifying Doppler views and extracting essential measurements from Doppler images. The integration of this AI-enabled workflow holds significant promise in reducing the manual workload and enhancing the efficiency of feto-placental Doppler image analysis, even for non-trained readers.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdgth.2024.1455767","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T05:12:35Z","timestamp":1729055555000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["AI-enabled workflow for automated classification and analysis of feto-placental Doppler images"],"prefix":"10.3389","volume":"6","author":[{"given":"Ainhoa M.","family":"Aguado","sequence":"first","affiliation":[]},{"given":"Guillermo","family":"Jimenez-Perez","sequence":"additional","affiliation":[]},{"given":"Devyani","family":"Chowdhury","sequence":"additional","affiliation":[]},{"given":"Josa","family":"Prats-Valero","sequence":"additional","affiliation":[]},{"given":"Sergio","family":"S\u00e1nchez-Mart\u00ednez","sequence":"additional","affiliation":[]},{"given":"Zahra","family":"Hoodbhoy","sequence":"additional","affiliation":[]},{"given":"Shazia","family":"Mohsin","sequence":"additional","affiliation":[]},{"given":"Roberta","family":"Castellani","sequence":"additional","affiliation":[]},{"given":"Lea","family":"Testa","sequence":"additional","affiliation":[]},{"given":"F\u00e0tima","family":"Crispi","sequence":"additional","affiliation":[]},{"given":"Bart","family":"Bijnens","sequence":"additional","affiliation":[]},{"given":"Babar","family":"Hasan","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Bernardino","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1007\/s11517-023-02814-1","article-title":"Performance evaluation of computer-aided automated master frame selection techniques for fetal echocardiography","volume":"61","author":"Sriraam","year":"2023","journal-title":"Med Biol Eng Comput"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1016\/j.jacc.2010.11.002","article-title":"ACCF\/ASE\/AHA\/ASNC\/HFSA\/HRS\/SCAI\/SCCM\/SCCT\/SCMR 2011 appropriate use criteria for echocardiography","volume":"57","author":"Douglas","year":"2011","journal-title":"J Am Soc Echocardiogr"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fcvm.2024.1426593","article-title":"Advanced magnetic resonance imaging in human placenta: insights into fetal growth restriction and congenital heart disease","volume":"11","author":"Sadiku","year":"2024","journal-title":"Front Cardiovasc Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3259","DOI":"10.1113\/JP279725","article-title":"Normal human and sheep fetal vessel oxygen saturations by T2 magnetic resonance imaging","volume":"598","author":"Saini","year":"2020","journal-title":"J Physiol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.12688\/gatesopenres.12796.1","article-title":"Machine learning from fetal flow waveforms to predict adverse perinatal outcomes: a study protocol","volume":"2","author":"Hoodbhoy","year":"2018","journal-title":"Gates Open Res"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s43055-022-00814-z","article-title":"Role of prenatal fetal echocardiography in the assessment of intrauterine growth restriction","volume":"53","author":"Ali","year":"2022","journal-title":"Egypt J Radiol Nucl. Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1002\/uog.23698","article-title":"ISUOG practice guidelines (updated): use of Doppler velocimetry in obstetrics","volume":"58","author":"Bhide","year":"2021","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2079","DOI":"10.1109\/TUFFC.2013.2798","article-title":"Finding the peak velocity in a flow from its Doppler spectrum","volume":"60","author":"Vilkomerson","year":"2013","journal-title":"IEEE Trans Ultrason Ferroelectr Freq Control"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.1016\/j.jcmg.2019.06.009","article-title":"State-of-the-art deep learning in cardiovascular image analysis","volume":"12","author":"Litjens","year":"2019","journal-title":"JACC Cardiovasc Imaging"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-67076-5","article-title":"Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes","volume":"10","author":"Burgos-Artizzu","year":"2020","journal-title":"Sci Rep"},{"key":"B11","first-page":"1569","article-title":"Automatic classification of cardiac views in echocardiogram using histogram and statistical features","volume-title":"Procedia Computer Science","author":"Balaji","year":"2015"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2113","DOI":"10.1109\/JBHI.2020.3029392","article-title":"User-intended Doppler measurement type prediction combining CNNs with smart post-processing","volume":"25","author":"Gilbert","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-44689-0","article-title":"Transfer learning for accurate fetal organ classification from ultrasound images: a potential tool for maternal healthcare providers","volume":"13","author":"Ghabri","year":"2023","journal-title":"Sci Rep"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","article-title":"Fully automated echocardiogram interpretation in clinical practice","volume":"138","author":"Zhang","year":"2018","journal-title":"Circulation"},{"key":"B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ULTSYM.2017.8092797","article-title":"A fully automatic and multi-structural segmentation of the left ventricle and the myocardium on highly heterogeneous 2D echocardiographic data","volume-title":"2017 IEEE International Ultrasonics Symposium (IUS); Washington, DC, USA","author":"Leclerc","year":"2017"},{"key":"B16","first-page":"2019","article-title":"ResDUnet: residual dilated UNet for left ventricle segmentation from echocardiographic images","author":"Amer","year":"2020"},{"key":"B17","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/ULTSYM.2019.8926017","article-title":"Segmentation of apical long axis, four- and two-chamber views using deep neural networks","volume-title":"2019 IEEE International Ultrasonics Symposium (IUS): Glasgow, Scotland","author":"Smistad","year":"2019"},{"key":"B18","doi-asserted-by":"publisher","first-page":"108192","DOI":"10.1016\/j.compbiomed.2024.108192","article-title":"Automated mitral inflow Doppler peak velocity measurement using deep learning","volume":"171","author":"Jevsikov","year":"2024","journal-title":"Comput Biol Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.media.2022.102438","article-title":"Real-time echocardiography image analysis and quantification of cardiac indices","volume":"80","author":"Zamzmi","year":"2022","journal-title":"Med Image Anal"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/JBHI.2013.2286155","article-title":"Automated estimation of fetal cardiac timing events from Doppler ultrasound signal using hybrid models","volume":"18","author":"Marzbanrad","year":"2014","journal-title":"IEEE J Biomed Health Inform"},{"key":"B21","doi-asserted-by":"publisher","first-page":"105336","DOI":"10.1016\/j.cmpb.2020.105336","article-title":"Automatic detection of complete and measurable cardiac cycles in antenatal pulsed-wave Doppler signals","volume":"190","author":"Sulas","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1109\/TMI.2014.2303782","article-title":"Automated aortic Doppler flow tracing for reproducible research and clinical measurements","volume":"33","author":"Zolgharni","year":"2014","journal-title":"IEEE Trans Med Imaging"},{"key":"B23","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3389\/fphys.2019.00237","article-title":"In silico optimization of left atrial appendage occluder implantation using interactive and modeling tools","volume":"10","author":"Aguado","year":"2019","journal-title":"Front Physiol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cmpb.2020.105682","article-title":"EView: an electric field visualization web platform for electroporation-based therapies","volume":"197","author":"Perera-Bel","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"B25","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B26","first-page":"1","article-title":"Pneumonia detection using CNN based feature extraction","author":"Varshni","year":"2019"},{"key":"B27","volume-title":"APTOS 2019 Blindness Detection","author":"Maggie","year":"2019"},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","volume-title":"XGBoost: A Scalable Tree Boosting System","author":"Chen","year":"2016"},{"key":"B29","doi-asserted-by":"publisher","first-page":"80437","DOI":"10.1109\/ACCESS.2020.2984630","article-title":"Convolutional-neural-network-based approach for segmentation of apical four-chamber view from fetal echocardiography","volume":"8","author":"Xu","year":"2020","journal-title":"IEEE Access"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.08506","article-title":"W-net: a deep model for fully unsupervised image segmentation","author":"Xia","year":"2017","journal-title":"ArXiv"},{"key":"B31","doi-asserted-by":"publisher","first-page":"101690","DOI":"10.1016\/j.compmedimag.2019.101690","article-title":"DW-net: a cascaded convolutional neural network for apical four-chamber view segmentation in fetal echocardiography","volume":"80","author":"Xu","year":"2020","journal-title":"Comput Med Imaging Graph"},{"key":"B32","first-page":"1","volume-title":"Going Deeper with Convolutions","author":"Szegedy","year":"2015"},{"key":"B33","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-44521-7_2","volume-title":"An Automatic Guidance and Quality Assessment System for Doppler Imaging of Umbilical Artery","author":"Wong","year":"2023"},{"key":"B34","first-page":"8024","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"},{"key":"B35","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/jcm12216833","article-title":"Evolving the era of 5D ultrasound? A systematic literature review on the applications for artificial intelligence ultrasound imaging in obstetrics and gynecology","volume":"12","author":"Jost","year":"2023","journal-title":"J Clin Med"},{"key":"B37","doi-asserted-by":"publisher","first-page":"102165","DOI":"10.1016\/j.artmed.2021.102165","article-title":"Artificial intelligence applied to support medical decisions for the automatic analysis of echocardiogram images: a systematic review","volume":"120","author":"de Siqueira","year":"2021","journal-title":"Artif Intell Med"},{"key":"B38","first-page":"1","article-title":"Medical imaging multimodality annotating framework","volume-title":"PhD Open Days 2020","author":"Calisto","year":"2020"},{"key":"B39","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1145\/3359178","article-title":"Understanding expert disagreement in medical data analysis through structured adjudication","volume":"3","author":"Schaekermann","year":"2019","journal-title":"Proc ACM Hum-Comput Interact"},{"key":"B40","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.ejogrb.2024.02.002","article-title":"Assessment of the cerebroplacental ratio and uterine arteries in low-risk pregnancies in early labour for the prediction of obstetric and neonatal outcomes","volume":"295","author":"Dall'Asta","year":"2024","journal-title":"Eur J Obstet Gynecol Reprod Biol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.1007\/s00521-022-07953-4","article-title":"A survey on deep learning applied to medical images: from simple artificial neural networks to generative models","volume":"35","author":"Celard","year":"2023","journal-title":"Neural Comput. Appl"},{"key":"B42","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow","year":"2014"},{"key":"B43","volume-title":"External Validation of a Deep Learning Model for Breast Density Classification","author":"Abrantes","year":"2023"},{"key":"B44","doi-asserted-by":"publisher","first-page":"AIpc2400545","DOI":"10.1056\/AIpc2400545","article-title":"The regulation of clinical artificial intelligence","volume":"1","author":"Blumenthal","year":"2024","journal-title":"NEJM AI"},{"key":"B45","doi-asserted-by":"publisher","first-page":"345","DOI":"10.54648\/COLA2024025","article-title":"Sustainable AI regulation","author":"Hacker","year":"2024","journal-title":"Common Mark Law Rev"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1609\/aies.v7i1.31633","article-title":"An FDA for AI? pitfalls and plausibility of approval regulation for frontier artificial intelligence","volume-title":"arXiv","author":"Carpenter","year":"2024"},{"key":"B47","doi-asserted-by":"publisher","first-page":"21501319241255576","DOI":"10.1177\/21501319241255576","article-title":"A clinician\u2019s guide to the implementation of point-of-care ultrasound (POCUS) in the outpatient practice","volume":"15","author":"Overgaard","year":"2024","journal-title":"J Prim Care Community Health"},{"key":"B48","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1053\/j.jvca.2019.06.018","article-title":"Automated spectral Doppler profile tracing","volume":"34","author":"Gosling","year":"2020","journal-title":"J Cardiothorac Vasc Anesth"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fcvm.2021.765693","article-title":"Machine learning for clinical decision-making: challenges and opportunities in cardiovascular imaging","volume":"8","author":"Sanchez-Martinez","year":"2021","journal-title":"Front Cardiovasc Med"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2024.1455767\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T18:34:56Z","timestamp":1732905296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2024.1455767\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":49,"alternative-id":["10.3389\/fdgth.2024.1455767"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2024.1455767","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"article-number":"1455767"}}