{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T22:55:28Z","timestamp":1790895328137,"version":"4.1.0"},"reference-count":67,"publisher":"SPIE-Intl Soc Optical Eng","issue":"01","funder":[{"name":"National Institutes of Health","award":["RO1 H11097"],"award-info":[{"award-number":["RO1 H11097"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Med. Imag."],"published-print":{"date-parts":[[2017,1,24]]},"abstract":"<jats:p>Coarctation of aorta (CoA) is a critical congenital heart defect (CCHD) that requires accurate and immediate diagnosis and treatment. Current newborn screening methods to detect CoA lack both in sensitivity and specificity, and when suspected in a newborn, it must be confirmed using specialized imaging and expert diagnosis, both of which are usually unavailable at tertiary birthing centers. We explore the feasibility of applying machine learning methods to reliably determine the presence of this difficult-to-diagnose cardiac abnormality from ultrasound image data. We propose a framework that uses deep learning-based machine learning methods for fully automated detection of CoA from two-dimensional ultrasound clinical data acquired in the parasternal long axis view, the apical four chamber view, and the suprasternal notch view. On a validation set consisting of 26\u00a0CoA and 64 normal patients our algorithm achieved a total error rate of 12.9% (11.5% false-negative error and 13.6% false-positive error) when combining decisions of classifiers over three standard echocardiographic view planes. This compares favorably with published results that combine clinical assessments with pulse oximetry to detect CoA (71% sensitivity).<\/jats:p>","DOI":"10.1117\/1.jmi.4.1.014502","type":"journal-article","created":{"date-parts":[[2017,1,24]],"date-time":"2017-01-24T12:32:00Z","timestamp":1485261120000},"page":"1-13","source":"Crossref","is-referenced-by-count":30,"title":["Automated detection of coarctation of aorta in neonates from two-dimensional echocardiograms"],"prefix":"10.1117","volume":"4","author":[{"given":"Franklin","family":"Pereira","sequence":"first","affiliation":[{"name":"Philips Ultrasound, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandra","family":"Bueno","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Douglas","family":"Perrin","sequence":"additional","affiliation":[{"name":"Boston Children\u2019s Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerald","family":"Marx","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Cardinale","sequence":"additional","affiliation":[{"name":"Philips Ultrasound, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Salgo","sequence":"additional","affiliation":[{"name":"Philips Ultrasound, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro","family":"del Nido","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2005-0397"},{"key":"r2","first-page":"31","article-title":"Congenital heart disease: prevalence at livebirth. The Baltimore-Washington infant study","author":"Ferencz","year":"1985"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1111\/apa.2011.100.issue-8"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2012-302543"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2008.05.059"},{"key":"r6","doi-asserted-by":"publisher","DOI":"10.1007\/s00431-011-1525-3"},{"key":"r7","doi-asserted-by":"publisher","DOI":"10.1542\/peds.103.4.743"},{"key":"r8","doi-asserted-by":"publisher","DOI":"10.1002\/bdra.v97.10"},{"key":"r9","first-page":"59","article-title":"Strategies for implementing screening for critical congenital heart disease","author":"Kemper","year":"2011"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2011-3211"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1007\/s00431-010-1160-4"},{"key":"r12","first-page":"e6041","article-title":"Factors associated with late detection of critical congenital heart disease in newborns","author":"Dawson","year":"2013"},{"key":"r13","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2014-3662"},{"key":"r14","author":"Armstrong","year":"2010"},{"key":"r15","author":"Lai","year":"2009"},{"key":"r16","article-title":"Digital imaging and communications in medicine (DICOM) standard","year":"2012"},{"key":"r17","first-page":"447","article-title":"Random forest classification for automatic delineation of myocardium in real-time 3D echocardiography","author":"Lempitsky","year":"2009"},{"key":"r18","first-page":"1","article-title":"Machine learning in computer-aided diagnosis, medical imaging intelligence and analysis","author":"Suzuki","year":"2012"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.842457"},{"key":"r20","article-title":"Automated detection of local fetal brain structures in ultrasound images","author":"Yaqub","year":"2012"},{"key":"r21","author":"Zheng","year":"2014"},{"key":"r22","first-page":"187","article-title":"Automatic view recognition for cardiac ultrasound images","author":"Otey","year":"2006"},{"key":"r23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2169273"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1117\/12.911734"},{"key":"r25","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2011.06.004"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2008.2004421"},{"key":"r27","first-page":"1","article-title":"LIBSVM: a library for support vector machines","author":"Chang","year":"2011"},{"key":"r28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2011.01.006"},{"key":"r29","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-013-1128-4"},{"key":"r30","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2235438"},{"key":"r31","author":"Bishop","year":"2007"},{"key":"r32","author":"Duda","year":"2001"},{"key":"r33","first-page":"511","article-title":"Rapid object detection using a boosted cascade of simple features","author":"Viola","year":"2001"},{"key":"r34","first-page":"1","article-title":"Automatic cardiac view classification of echocardiogram","author":"Park","year":"2007"},{"key":"r35","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"r36","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"r37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"r38","first-page":"411","article-title":"Mitosis detection in breast cancer histology images using deep neural networks","author":"Ciresan","year":"2013"},{"key":"r39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.023"},{"key":"r40","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"r41","first-page":"1096","article-title":"Extracting and composing robust features with denoising autoencoders","author":"Vincent","year":"2008"},{"key":"r42","first-page":"3371","article-title":"Stacked denoising autoencoders: learning useful representations in a deep network with local denoising criterion","author":"Vincent","year":"2010"},{"key":"r43","author":"Nadas","year":"1972"},{"key":"r44","author":"Keith","year":"1978"},{"key":"r45","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(14)60198-7"},{"key":"r46","article-title":"Coarctation of aorta","author":"Patnana","year":"2012"},{"key":"r47","author":"Sonka","year":"2008"},{"key":"r48","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/31\/9\/002"},{"key":"r49","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"Coates","year":"2011"},{"key":"r50","article-title":"Ask the locals: multi-way pooling for image recognition","author":"Boureau","year":"2010"},{"key":"r51","first-page":"144","article-title":"A training algorithm for optimal margin classifiers","author":"Boser","year":"1992"},{"key":"r52","article-title":"Deep learning using linear support vector machines","author":"Tang","year":"2013"},{"key":"r53","article-title":"Feature representation in convolutional neural networks","author":"Athiwaratkun","year":"2015"},{"key":"r54","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"r55","article-title":"ADADELTA: an adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"r56","first-page":"9","article-title":"Efficient backprop","author":"LeCun","year":"2005"},{"key":"r57","first-page":"281","article-title":"Random search for hyper\u2013parameter optimization","author":"Bergstra","year":"2012"},{"key":"r58","author":"Efron","year":"1993"},{"key":"r59","first-page":"330","article-title":"Shrinking the tube: a new support vector regression algorithm","author":"Scholkopf","year":"1999"},{"key":"r60","doi-asserted-by":"crossref","DOI":"10.1186\/1758-2946-6-10","article-title":"Cross-validation pitfalls when selecting and assessing regression and classification models","author":"Krstajic","year":"2014"},{"key":"r61","first-page":"101","article-title":"Interval estimation for a binomial proportion","author":"Brown","year":"2001"},{"key":"r62","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/26.4.404"},{"key":"r63","first-page":"99","author":"Corder","year":"2009"},{"key":"r64","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177706374"},{"key":"r65","first-page":"1322","article-title":"Learning visual motion in recurrent neural networks","author":"Pachitariu","year":"2012"},{"key":"r66","first-page":"190","article-title":"Training and analyzing deep recurrent neural networks","author":"Hermans","year":"2013"},{"key":"r67","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.a3037"}],"container-title":["Journal of Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-4\/issue-01\/014502\/Automated-detection-of-coarctation-of-aorta-in-neonates-from-two\/10.1117\/1.JMI.4.1.014502.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T22:11:16Z","timestamp":1790892676000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-4\/issue-01\/014502\/Automated-detection-of-coarctation-of-aorta-in-neonates-from-two\/10.1117\/1.JMI.4.1.014502.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,24]]},"references-count":67,"journal-issue":{"issue":"01"},"URL":"https:\/\/doi.org\/10.1117\/1.jmi.4.1.014502","relation":{},"ISSN":["2329-4302","2329-4310"],"issn-type":[{"value":"2329-4302","type":"print"},{"value":"2329-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,24]]}}}