{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:16:16Z","timestamp":1779927376453,"version":"3.53.1"},"reference-count":35,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T00:00:00Z","timestamp":1632355200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100009633","name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["U01 HD087180"],"award-info":[{"award-number":["U01 HD087180"]}],"id":[{"id":"10.13039\/100009633","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["F32 HL119010"],"award-info":[{"award-number":["F32 HL119010"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 EB017255"],"award-info":[{"award-number":["R01 EB017255"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 NS094456"],"award-info":[{"award-number":["R01 NS094456"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J of Ultrasound Medicine"],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:sec><jats:title>Objectives<\/jats:title><jats:p>Early placental volume (PV) has been associated with small\u2010for\u2010gestational\u2010age infants born under the 10th\/5th centiles (SGA10\/SGA5). Manual or semiautomated PV quantification from 3D ultrasound (3DUS) is time intensive, limiting its incorporation into clinical care. We devised a novel convolutional neural network (CNN) pipeline for fully automated placenta segmentation from 3DUS images, exploring the association between the calculated PV and SGA.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Volumes of 3DUS obtained from singleton pregnancies at 11\u201314\u2009weeks' gestation were automatically segmented by our CNN pipeline trained and tested on 99\/25 images, combining two 2D and one 3D models with downsampling\/upsampling architecture. The PVs derived from the automated segmentations (PV<jats:sub>CNN<\/jats:sub>) were used to train multivariable logistic\u2010regression classifiers for SGA10\/SGA5. The test performance for predicting SGA was compared to PVs obtained via the semiautomated VOCAL (GE\u2010Healthcare) method (PV<jats:sub>VOCAL<\/jats:sub>).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We included 442 subjects with 37 (8.4%) and 18 (4.1%) SGA10\/SGA5 infants, respectively. Our segmentation pipeline achieved a mean Dice score of 0.88 on an independent test\u2010set. Adjusted models including PV<jats:sub>CNN<\/jats:sub>or PV<jats:sub>VOCAL<\/jats:sub>were similarly predictive of SGA10 (area under curve [AUC]: PV<jats:sub>CNN<\/jats:sub>\u00a0=\u00a00.780, PV<jats:sub>VOCAL<\/jats:sub>\u00a0=\u00a00.768). The addition of PV<jats:sub>CNN<\/jats:sub>to a clinical model without any PV included (AUC\u00a0=\u00a00.725) yielded statistically significant improvement in AUC (<jats:italic>P<\/jats:italic>\u2009&lt;\u2009.05); whereas PV<jats:sub>VOCAL<\/jats:sub>did not (<jats:italic>P<\/jats:italic>\u00a0=\u00a0.105). Moreover, when predicting SGA5, including the PV<jats:sub>CNN<\/jats:sub>(0.897) brought statistically significant improvement over both the clinical model (0.839,<jats:italic>P<\/jats:italic>\u00a0=\u00a0.015) and the PV<jats:sub>VOCAL<\/jats:sub>model (0.870,<jats:italic>P<\/jats:italic>\u00a0=\u00a0.039).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>First trimester PV measurements derived from our CNN segmentation pipeline are significantly associated with future SGA. This fully automated tool enables the incorporation of including placental volumetric biometry into the bedside clinical evaluation as part of a multivariable prediction model for risk stratification and patient counseling.<\/jats:p><\/jats:sec>","DOI":"10.1002\/jum.15835","type":"journal-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T14:48:57Z","timestamp":1632408537000},"page":"1509-1524","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Fully Automated Placental Volume Quantification From<scp>3D<\/scp>Ultrasound for Prediction of Small\u2010for\u2010Gestational\u2010Age Infants"],"prefix":"10.1002","volume":"41","author":[{"given":"Nadav","family":"Schwartz","sequence":"first","affiliation":[{"name":"Maternal and Child Health Research Program, Department of OBGYN University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ipek","family":"Oguz","sequence":"additional","affiliation":[{"name":"Department of EECS Vanderbilt University Nashville TN USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiancong","family":"Wang","sequence":"additional","affiliation":[{"name":"Penn Image Computing and Science Laboratory (PICSL), Department of Radiology University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alison","family":"Pouch","sequence":"additional","affiliation":[{"name":"Penn Image Computing and Science Laboratory (PICSL), Department of Radiology University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalie","family":"Yushkevich","sequence":"additional","affiliation":[{"name":"Penn Image Computing and Science Laboratory (PICSL), Department of Radiology University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shobhana","family":"Parameshwaran","sequence":"additional","affiliation":[{"name":"Maternal and Child Health Research Program, Department of OBGYN University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Gee","sequence":"additional","affiliation":[{"name":"Penn Image Computing and Science Laboratory (PICSL), Department of Radiology University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Yushkevich","sequence":"additional","affiliation":[{"name":"Penn Image Computing and Science Laboratory (PICSL), Department of Radiology University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-0100","authenticated-orcid":false,"given":"Baris","family":"Oguz","sequence":"additional","affiliation":[{"name":"Penn Image Computing and Science Laboratory (PICSL), Department of Radiology University of Pennsylvania Philadelphia PA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,9,23]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/14767050802415728"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.301.6746.259"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.earlhumdev.2007.09.017"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.11136"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.placenta.2010.06.011"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1469-0705.2002.00655.x"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2009.10.381"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.placenta.2014.06.373"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2014.02.033"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2012.09.003"},{"key":"e_1_2_6_12_1","doi-asserted-by":"crossref","unstructured":"LooneyP StevensonGN NicolaidesKH et al.Automatic 3D ultrasound segmentation of the first trimester placenta using deep learning. Paper presented at: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017); 2017:279\u2013282.","DOI":"10.1109\/ISBI.2017.7950519"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1172\/jci.insight.120178"},{"key":"e_1_2_6_14_1","unstructured":"OguzI PouchA YushkevichN et al.Fully automated placenta segmentation from 3D ultrasound images. Paper presented at: Perinatal Preterm and Paediatric Image Analysis PIPPI Workshop MICCAI 2016."},{"key":"e_1_2_6_15_1","doi-asserted-by":"crossref","unstructured":"OguzBU WangJ YushkevichN et al.Combining deep learning and multi\u2010atlas label fusion for automated placenta segmentation from 3DUS. Paper presented at: Data Driven Treatment Response Assessment and Preterm Perinatal and Paediatric Image Analysis; 2018; Springer Cham Switzerland:138\u2013148.","DOI":"10.1007\/978-3-030-00807-9_14"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.7.1.014004"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2015.07.021"},{"key":"e_1_2_6_18_1","doi-asserted-by":"crossref","unstructured":"YangX YuL LiS et al.Towards automatic semantic segmentation in volumetric ultrasound. Paper presented at: International Conference on Medical Image Computing and Computer\u2010Assisted Intervention;2017; Springer Cham Switzerland:711\u2013719.","DOI":"10.1007\/978-3-319-66182-7_81"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/0029-7844(95)00386-X"},{"key":"e_1_2_6_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1974.10489157"},{"key":"e_1_2_6_21_1","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.2517-6161.1974.tb00994.x","article-title":"Cross validatory choice and assessment of statistical predictions","volume":"36","author":"Stone M","year":"1974","journal-title":"J R Stat Soc B Methodol"},{"key":"e_1_2_6_22_1","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1111\/j.2517-6161.1977.tb01603.x","article-title":"An asymptotic equivalence of choice of model by cross validation and Akaike's criterion","volume":"39","author":"Stone M","year":"1977","journal-title":"J R Stat Soc B Methodol"},{"key":"e_1_2_6_23_1","doi-asserted-by":"crossref","unstructured":"BlumA KalaiA LangfordJ.Beating the hold\u2010out: Bounds for k\u2010fold and progressive cross\u2010validation. Paper presented at: Proceedings of the twelfth annual conference on Computational learning theory;1999:203\u2013208.","DOI":"10.1145\/307400.307439"},{"key":"e_1_2_6_24_1","unstructured":"KohaviR.A study of cross\u2010validation and bootstrap for accuracy estimation and model selection. Paper presented at: IJCAI'95: Proceedings of the 14th international joint conference on Artificial intelligence;1995:1137\u20131145."},{"key":"e_1_2_6_25_1","doi-asserted-by":"crossref","unstructured":"deBelT HermsenM SmeetsB HilbrandsL van derLaakJ LitjensG.Automatic segmentation of histopathological slides of renal tissue using deep learning. Paper presented at: Medical Imaging 2018: Digital Pathology International Society for Optics and Photonics;2018; 10581:1058112.","DOI":"10.1117\/12.2293717"},{"key":"e_1_2_6_26_1","doi-asserted-by":"crossref","unstructured":"MortaziA BurtJ BagciU.Multi\u2010planar deep segmentation networks for cardiac substructures from MRI and CT. Paper presented at: International Workshop on Statistical Atlases and Computational Models of the Heart;2017; Springer Cham Switzerland:199\u2013206.","DOI":"10.1007\/978-3-319-75541-0_21"},{"key":"e_1_2_6_27_1","doi-asserted-by":"crossref","unstructured":"RothHR LuL FaragA et al.Deeporgan: multi\u2010level deep convolutional networks for automated pancreas segmentation. Paper presented at: International Conference on Medical Image Computing and Computer\u2010assisted Intervention;2015; Springer Cham Switzerland:556\u2013564.","DOI":"10.1007\/978-3-319-24553-9_68"},{"key":"e_1_2_6_28_1","doi-asserted-by":"crossref","unstructured":"DietterichTG.Ensemble methods in machine learning. Paper presented at: International Workshop on Multiple Classifier Systems;2000; Springer Berlin Heidelberg:1\u201315.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1289"},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.614"},{"key":"e_1_2_6_31_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation. Paper presented at: International Conference on Medical Image Computing and Computer\u2010assisted Intervention;2015; Springer Cham Switzerland:234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_6_32_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_6_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.232073"},{"key":"e_1_2_6_34_1","doi-asserted-by":"publisher","DOI":"10.1387\/ijdb.082760db"},{"key":"e_1_2_6_35_1","doi-asserted-by":"publisher","DOI":"10.1136\/adc.66.11.1291"},{"key":"e_1_2_6_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.12421"}],"container-title":["Journal of Ultrasound in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jum.15835","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jum.15835","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jum.15835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T19:06:49Z","timestamp":1725822409000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jum.15835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,23]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10.1002\/jum.15835"],"URL":"https:\/\/doi.org\/10.1002\/jum.15835","archive":["Portico"],"relation":{},"ISSN":["0278-4297","1550-9613"],"issn-type":[{"value":"0278-4297","type":"print"},{"value":"1550-9613","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,23]]},"assertion":[{"value":"2021-03-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}