دورية أكاديمية
أعرض في EDS

Fetal Cortical Plate Segmentation Using Fully Convolutional Networks With Multiple Plane Aggregation.

التفاصيل البيبلوغرافية
العنوان: Fetal Cortical Plate Segmentation Using Fully Convolutional Networks With Multiple Plane Aggregation.
المؤلفون: Hong J; Department of Electronic Engineering, Hanyang University, Seoul, South Korea.; Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States., Yun HJ; Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States.; Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States., Park G; Department of Biomedical Engineering, Hanyang University, Seoul, South Korea., Kim S; Department of Electronic Engineering, Hanyang University, Seoul, South Korea., Laurentys CT; Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States., Siqueira LC; Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States., Tarui T; Mother Infant Research Institute, Tufts Medical Center, Tufts University School of Medicine, Boston, MA, United States.; Department of Pediatrics, Tufts Medical Center, Tufts University School of Medicine, Boston, MA, United States., Rollins CK; Department of Neurology, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States., Ortinau CM; Department of Pediatrics, Washington University in St. Louis, St. Louis, MO, United States., Grant PE; Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States.; Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States., Lee JM; Department of Biomedical Engineering, Hanyang University, Seoul, South Korea., Im K; Fetal-Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States.; Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States.
المصدر: Frontiers in neuroscience [Front Neurosci] 2020 Dec 02; Vol. 14, pp. 591683. Date of Electronic Publication: 2020 Dec 02 (Print Publication: 2020).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Frontiers Research Foundation Country of Publication: Switzerland NLM ID: 101478481 Publication Model: eCollection Cited Medium: Print ISSN: 1662-4548 (Print) Linking ISSN: 1662453X NLM ISO Abbreviation: Front Neurosci Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: Lausanne : Frontiers Research Foundation
مستخلص: Fetal magnetic resonance imaging (MRI) has the potential to advance our understanding of human brain development by providing quantitative information of cortical plate (CP) development in vivo . However, for a reliable quantitative analysis of cortical volume and sulcal folding, accurate and automated segmentation of the CP is crucial. In this study, we propose a fully convolutional neural network for the automatic segmentation of the CP. We developed a novel hybrid loss function to improve the segmentation accuracy and adopted multi-view (axial, coronal, and sagittal) aggregation with a test-time augmentation method to reduce errors using three-dimensional (3D) information and multiple predictions. We evaluated our proposed method using the ten-fold cross-validation of 52 fetal brain MR images (22.9-31.4 weeks of gestation). The proposed method obtained Dice coefficients of 0.907 ± 0.027 and 0.906 ± 0.031 as well as a mean surface distance error of 0.182 ± 0.058 mm and 0.185 ± 0.069 mm for the left and right, respectively. In addition, the left and right CP volumes, surface area, and global mean curvature generated by automatic segmentation showed a high correlation with the values generated by manual segmentation ( R 2 > 0.941). We also demonstrated that the proposed hybrid loss function and the combination of multi-view aggregation and test-time augmentation significantly improved the CP segmentation accuracy. Our proposed segmentation method will be useful for the automatic and reliable quantification of the cortical structure in the fetal brain.
Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
(Copyright © 2020 Hong, Yun, Park, Kim, Laurentys, Siqueira, Tarui, Rollins, Ortinau, Grant, Lee and Im.)
References: Cereb Cortex. 2019 Jul 22;29(8):3605-3616. (PMID: 30272144)
Med Image Anal. 2012 Dec;16(8):1550-64. (PMID: 22939612)
Hum Brain Mapp. 2010 Sep;31(9):1348-58. (PMID: 20108226)
Neuroimage. 2019 Mar;188:473-482. (PMID: 30553042)
Neuroimage. 2019 Feb 1;186:713-727. (PMID: 30502445)
Neurocomputing (Amst). 2019 Sep 3;335:34-45. (PMID: 31595105)
Brain Struct Funct. 2012 Jan;217(1):127-39. (PMID: 21562906)
Magn Reson Imaging. 2019 Dec;64:77-89. (PMID: 31181246)
Neuroimage. 2018 Apr 15;170:434-445. (PMID: 28223187)
Neuroimage. 2002 Oct;17(2):825-41. (PMID: 12377157)
J Med Imaging (Bellingham). 2019 Jan;6(1):014006. (PMID: 30944843)
Cereb Cortex. 2021 Jan 5;31(2):757-767. (PMID: 32940649)
AJNR Am J Neuroradiol. 2017 Jul;38(7):1449-1455. (PMID: 28522661)
Neuroimage. 2018 Apr 15;170:446-455. (PMID: 28445774)
Int J Dev Neurosci. 2011 Aug;29(5):529-36. (PMID: 21530634)
IEEE Trans Med Imaging. 2020 Feb;39(2):499-513. (PMID: 31329113)
IEEE Trans Med Imaging. 2021 Apr;40(4):1123-1133. (PMID: 33351755)
Neuroimage. 2016 Apr 1;129:460-469. (PMID: 26808333)
Med Phys. 2018 May;45(5):2097-2107. (PMID: 29500816)
Cereb Cortex. 2013 Dec;23(12):3007-15. (PMID: 22989584)
Cereb Cortex. 2020 Jun 1;30(7):4257-4268. (PMID: 32219376)
Magn Reson Med. 2020 Apr;83(4):1471-1483. (PMID: 31631409)
Neuroimage. 2015 Mar;108:214-24. (PMID: 25562829)
Sci Rep. 2017 Jul 11;7(1):5110. (PMID: 28698556)
Neuroimage. 2014 May 1;91:21-32. (PMID: 24473102)
Cereb Cortex. 2018 Sep 1;28(9):3192-3203. (PMID: 30124828)
Med Image Anal. 2018 Aug;48:177-186. (PMID: 29935442)
معلومات مُعتمدة: R01 NS114087 United States NS NINDS NIH HHS; R01 HD100009 United States HD NICHD NIH HHS; K23 HL141602 United States HL NHLBI NIH HHS; R01 EB017337 United States EB NIBIB NIH HHS; U01 HD087211 United States HD NICHD NIH HHS; T32 DK060445 United States DK NIDDK NIH HHS; R21 HD094130 United States HD NICHD NIH HHS; K23 HD079605 United States HD NICHD NIH HHS; K23 NS101120 United States NS NINDS NIH HHS
فهرسة مساهمة: Keywords: MRI; cortical plate; deep learning; fetal brain; hybrid loss; segmentation
تواريخ الأحداث: Date Created: 20201221 Latest Revision: 20240330
رمز التحديث: 20240330
مُعرف محوري في PubMed: PMC7738480
DOI: 10.3389/fnins.2020.591683
PMID: 33343286
قاعدة البيانات: MEDLINE
الوصف
تدمد:1662-4548
DOI:10.3389/fnins.2020.591683