{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T09:14:40Z","timestamp":1790414080995,"version":"4.1.0"},"reference-count":55,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T00:00:00Z","timestamp":1642032000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Human Brain Mapping"],"published-print":{"date-parts":[[2022,4,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Post\u2010hemorrhagic hydrocephalus (PHH) is a severe complication of intraventricular hemorrhage (IVH) in very preterm infants. PHH monitoring and treatment decisions rely heavily on manual and subjective two\u2010dimensional measurements of the ventricles. Automatic and reliable three\u2010dimensional (3D) measurements of the ventricles may provide a more accurate assessment of PHH, and lead to improved monitoring and treatment decisions. To accurately and efficiently obtain these 3D measurements, automatic segmentation of the ventricles can be explored. However, this segmentation is challenging due to the large ventricular anatomical shape variability in preterm infants diagnosed with PHH. This study aims to (a) propose a Bayesian U\u2010Net method using 3D spatial concrete dropout for automatic brain segmentation (with uncertainty assessment) of preterm infants with PHH; and (b) compare the Bayesian method to three reference methods: DenseNet, U\u2010Net, and ensemble learning using DenseNets and U\u2010Nets. A total of 41 T<jats:sub>2<\/jats:sub>\u2010weighted MRIs from 27 preterm infants were manually segmented into lateral ventricles, external CSF, white and cortical gray matter, brainstem, and cerebellum. These segmentations were used as ground truth for model evaluation. All methods were trained and evaluated using 4\u2010fold cross\u2010validation and segmentation endpoints, with additional uncertainty endpoints for the Bayesian method. In the lateral ventricles, segmentation endpoint values for the DenseNet, U\u2010Net, ensemble learning, and Bayesian U\u2010Net methods were mean Dice score\u00a0=\u00a00.814\u2009\u00b1\u20090.213, 0.944\u2009\u00b1\u20090.041, 0.942\u2009\u00b1\u20090.042, and 0.948\u2009\u00b1\u20090.034 respectively. Uncertainty endpoint values for the Bayesian U\u2010Net were mean recall\u00a0=\u00a00.953\u2009\u00b1\u20090.037, mean\u00a0 negative predictive value =\u00a00.998\u2009\u00b1\u20090.005, mean accuracy\u00a0=\u00a00.906\u2009\u00b1\u20090.032, and mean AUC\u00a0=\u00a00.949\u2009\u00b1\u20090.031. To conclude, the Bayesian U\u2010Net showed the best segmentation results across all methods and provided accurate uncertainty maps. This method may be used in clinical practice for automatic brain segmentation of preterm infants with PHH, and lead to better PHH monitoring and more informed treatment decisions.<\/jats:p>","DOI":"10.1002\/hbm.25762","type":"journal-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T08:46:52Z","timestamp":1642063612000},"page":"1895-1916","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Automatic brain segmentation in preterm infants with <scp>post\u2010hemorrhagic<\/scp> hydrocephalus using <scp>3D<\/scp> Bayesian <scp>U\u2010Net<\/scp>"],"prefix":"10.1002","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0336-6350","authenticated-orcid":false,"given":"Axel","family":"Largent","sequence":"first","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josepheen","family":"De Asis\u2010Cruz","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kushal","family":"Kapse","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott D.","family":"Barnett","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Murnick","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudeepta","family":"Basu","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Andersen","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie","family":"Norman","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nickie","family":"Andescavage","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"},{"name":"Department of Neonatology Children's National Hospital  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine","family":"Limperopoulos","sequence":"additional","affiliation":[{"name":"Developing Brain Institute, Department of Diagnostic Imaging and Radiology Children's National Hospital  Washington District of Columbia USA"},{"name":"Departments of Radiology and Pediatrics George Washington University  Washington District of Columbia USA"},{"name":"Neurology School of Medicine and Health Sciences George Washington University  Washington District of Columbia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1227\/01.NEU.0000370939.30003.D1"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14387"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.07.027"},{"key":"e_1_2_9_5_1","first-page":"1479","article-title":"Increased intracranial volume: A clue to the etiology of idiopathic Normal\u2010pressure hydrocephalus?","volume":"25","author":"Bradley W. G.","year":"2004","journal-title":"American Journal of Neuroradiology"},{"key":"e_1_2_9_6_1","unstructured":"Bui T. D. Shin J. &Moon T.(2017).3D densely convolutional networks for volumetric segmentation. arXiv:170903199 [cs]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1709.03199."},{"key":"e_1_2_9_7_1","unstructured":"Chollet F.(2015).Keras."},{"key":"e_1_2_9_8_1","unstructured":"DeVries T. &Taylor G. W.(2018):Leveraging uncertainty estimates for predicting segmentation Quality arXiv:180700502 [Cs]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1807.00502."},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-9091(98)80032-6"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2020.07.079"},{"key":"e_1_2_9_11_1","unstructured":"Gal Y. &Ghahramani Z.(2016).Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In:Proceedings of the 33rd International Conference on Machine Learning(ICML\u201916) Vol. 48 JMLR.org New York NY. pp.1050\u20131059."},{"key":"e_1_2_9_12_1","unstructured":"Gal Y. Hron J. &Kendall A.(2017).Concrete dropout. arXiv:170507832 [stat]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1705.07832."},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12887-018-1249-x"},{"key":"e_1_2_9_14_1","first-page":"1604","article-title":"Magnetic resonance imaging of the fetal brain and spine: An increasingly important tool in prenatal diagnosis, part 1","volume":"27","author":"Glenn O. A.","year":"2006","journal-title":"American Journal of Neuroradiology"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-80783-3"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_81"},{"key":"e_1_2_9_17_1","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman M. D.","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2019.102031"},{"key":"e_1_2_9_19_1","unstructured":"Jang E. Gu S. &Poole B.(2017).Categorical reparameterization with Gumbel\u2010Softmax. arXiv:161101144 [cs stat]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1611.01144."},{"key":"e_1_2_9_20_1","unstructured":"Jungo A. Meier R. Ermis E. Herrmann E. &Reyes M.(2018):Uncertainty\u2010driven sanity check: Application to postoperative brain tumor cavity segmentation. arXiv:180603106 [cs]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1806.03106."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2415453"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00345-018-2292-9"},{"key":"e_1_2_9_23_1","unstructured":"Kingma D. P. &Ba J.(2014).Adam: A method for stochastic optimization arXiv:14126980 [Cs]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1412.6980."},{"key":"e_1_2_9_24_1","unstructured":"Kingma D. P. Salimans T. &Welling M.. (2015).Variational dropout and the local reparameterization trick. In:Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS\u201915) Vol. 2. MIT Press Cambridge MA. pp.2575\u20132583."},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.2.026001"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.08.049"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27649"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.canrad.2020.01.008"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_9_30_1","doi-asserted-by":"crossref","unstructured":"LeCun Y. Kavukcuoglu K. &Farabet C.(2010).Convolutional networks and applications in vision. In:Proceedings of 2010 IEEE International Symposium on Circuits and Systemspp.253\u2013256.","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"L\u00fctjens B. Everett M. &How J. P.(2019).Safe reinforcement learning with model uncertainty estimates. In2019 International Conference on Robotics and Automation (ICRA). pp.8662\u20138668.","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"e_1_2_9_33_1","unstructured":"Maddison C. J. Mnih A. &Teh Y. W.(2017).The concrete distribution: A continuous relaxation of discrete random variables. arXiv:161100712 [Cs Stat]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1611.00712."},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1136\/fn.87.3.F185"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"McAllister R. Gal Y. Kendall A. Van Der Wilk M. Shah A. Cipolla R. &Weller A.(2017).Concrete problems for autonomous vehicle safety: Advantages of Bayesian deep learning. InProceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI\u201917). AAAI Press Melbourne Australia. pp.4745\u20134753.","DOI":"10.24963\/ijcai.2017\/661"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"Michelmore R. Wicker M. Laurenti L. Cardelli L. Gal Y. &Kwiatkowska M.(2020).Uncertainty quantification with statistical guarantees in end\u2010to\u2010end autonomous driving control. In:2020 IEEE International Conference on Robotics and Automation (ICRA)pp.7344\u20137350.","DOI":"10.1109\/ICRA40945.2020.9196844"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"Miok K. Nguyen\u2010Doan D. Zaharie D. &Robnik\u2010\u0160ikonja M.(2019).Generating data using Monte Carlo dropout. In2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP). pp.509\u2013515.","DOI":"10.1109\/ICCP48234.2019.8959787"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-84854-x"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.025"},{"key":"e_1_2_9_40_1","unstructured":"Okada M. &Taniguchi T.(2020).Variational inference MPC for Bayesian model\u2010based reinforcement learning. InConference on Robot Learning PMLR. pp.258\u2013272. Retrieved fromhttp:\/\/proceedings.mlr.press\/v100\/okada20a.html."},{"key":"e_1_2_9_41_1","unstructured":"Paisley J. Blei D. &Jordan M.(2012).Variational Bayesian inference with stochastic search. arXiv:12066430 [cs stat]. Retrieved fromhttp:\/\/arxiv.org\/abs\/1206.6430."},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106236"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.06.038"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.05.099"},{"key":"e_1_2_9_45_1","unstructured":"Rezende D. J. Mohamed S. &Wierstra D.(2014).Stochastic backpropagation and approximate inference in deep generative models. InInternational Conference on Machine Learning PMLR. pp.1278\u20131286. Retrieved fromhttp:\/\/proceedings.mlr.press\/v32\/rezende14.html."},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.10.038"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.3171\/2011.12.PEDS11136"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_75"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.03.042"},{"key":"e_1_2_9_51_1","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_52_1","doi-asserted-by":"crossref","unstructured":"Tabrizi P. R. Obeid R. Cerrolaza J. J. Penn A. Mansoor A. &Linguraru M. G.(2018).Automatic segmentation of neonatal ventricles from cranial ultrasound for prediction of intraventricular hemorrhage outcome. In2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)pp.3136\u20133139.","DOI":"10.1109\/EMBC.2018.8513097"},{"key":"e_1_2_9_53_1","unstructured":"Titsias M. &L\u00e1zaro\u2010Gredilla M.(2014).Doubly stochastic variational Bayes for non\u2010conjugate inference. InInternational Conference on Machine Learning (PMLR). pp.1971\u20131979. Retrieved fromhttp:\/\/proceedings.mlr.press\/v32\/titsias14.html."},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2901712"},{"key":"e_1_2_9_56_1","doi-asserted-by":"crossref","unstructured":"W\u0119gli\u00f1ski T. &Fabija\u00f1ska A.(2012).Min\u2010Cut\/max\u2010flow segmentation of hydrocephalus in children from CT datasets. In:2012 International Conference on Signals and Electronic Systems(ICSES)pp.1\u20136.","DOI":"10.1109\/ICSES.2012.6382217"}],"container-title":["Human Brain Mapping"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hbm.25762","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/hbm.25762","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hbm.25762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T03:40:04Z","timestamp":1693107604000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hbm.25762"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,13]]},"references-count":55,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,4,15]]}},"alternative-id":["10.1002\/hbm.25762"],"URL":"https:\/\/doi.org\/10.1002\/hbm.25762","archive":["Portico"],"relation":{},"ISSN":["1065-9471","1097-0193"],"issn-type":[{"value":"1065-9471","type":"print"},{"value":"1097-0193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,13]]},"assertion":[{"value":"2021-06-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}