Histograms of Oriented 3D Gradients for Fully Automated Fetal Brain Localization and Robust Motion Correction in 3 T Magnetic Resonance Images.

Fetal brain magnetic resonance imaging (MRI) is a rapidly emerging diagnostic imaging tool. However, automated fetal brain localization is one of the biggest obstacles in expediting and fully automating large-scale fetal MRI processing. We propose a method for automatic localization of fetal brain i...

Descripción completa

Detalles Bibliográficos
Publicado en:BioMed Research International Vol. 2017; pp. 1 - 9
Autores principales: Serag, Ahmed, Macnaught, Gillian, Denison, Fiona C., Reynolds, Rebecca M., Semple, Scott I., Boardman, James P.
Formato: algorithm diagnostic images equations & formulas research tables/charts Journal Article
Publicado: Wiley-Blackwell 1/30/2017
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=121015446&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 121015446
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        23146133
        FT2T
      jtl: BioMed Research International
      issn: 23146133
      maglogo: N
    pubinfo:
      dt: 1/30/2017
      vid: 2017
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        121015446
        121015446
        121015446
        10.1155/2017/3956363
        121015446
      ppf: 1
      ppct: 8
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Histograms of Oriented 3D Gradients for Fully Automated Fetal Brain Localization and Robust Motion Correction in 3 T Magnetic Resonance Images.
      aug:
        au:
          Serag, Ahmed
          Macnaught, Gillian
          Denison, Fiona C.
          Reynolds, Rebecca M.
          Semple, Scott I.
          Boardman, James P.
        affil: MRC Centre for Reproductive Health, University of Edinburgh, Edinburgh, UK
      sug:
        subj:
          Magnetic Resonance Imaging Methods
          Brain Embryology
          Fetal Development
          Automation
          Magnetic Resonance Imaging Evaluation
          Prenatal Diagnosis
          Human
          Fetus
          Algorithms
          Validity
          Descriptive Statistics
          Regression
          Gestational Age
          Funding Source
          Fetus, conception to birth
      ab: Fetal brain magnetic resonance imaging (MRI) is a rapidly emerging diagnostic imaging tool. However, automated fetal brain localization is one of the biggest obstacles in expediting and fully automating large-scale fetal MRI processing. We propose a method for automatic localization of fetal brain in 3 T MRI when the images are acquired as a stack of 2D slices that are misaligned due to fetal motion. First, the Histogram of Oriented Gradients (HOG) feature descriptor is extended from 2D to 3D images. Then, a sliding window is used to assign a score to all possible windows in an image, depending on the likelihood of it containing a brain, and the window with the highest score is selected. In our evaluation experiments using a leave-one-out cross-validation strategy, we achieved 96% of complete brain localization using a database of 104 MRI scans at gestational ages between 34 and 38 weeks. We carried out comparisons against template matching and random forest based regression methods and the proposed method showed superior performance. We also showed the application of the proposed method in the optimization of fetal motion correction and how it is essential for the reconstruction process. The method is robust and does not rely on any prior knowledge of fetal brain development.
      pubtype: Academic Journal
      doctype:
        algorithm
        diagnostic images
        equations & formulas
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N