Artificial intelligence using neural network architecture for radiology (AINNAR): classification of MR imaging sequences.

Purpose: The confusion of MRI sequence names could be solved if MR images were automatically identified after image data acquisition. We revealed the ability of deep learning to classify head MRI sequences.Materials and Methods: Seventy-eight patients with mild cognitive impairment (MCI) having appa...

Descripción completa

Detalles Bibliográficos
Publicado en:Japanese Journal of Radiology Vol. 36; no. 12; pp. 691 - 698
Autores principales: Noguchi, Tomoyuki, Higa, Daichi, Asada, Takashi, Kawata, Yusuke, Machitori, Akihiro, Shida, Yoshitaka, Okafuji, Takashi, Yokoyama, Kota, Uchiyama, Fumiya, Tajima, Tsuyoshi
Formato: diagnostic images pictorial research tables/charts Journal Article
Publicado: Springer Nature Dec2018
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=133160232&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 133160232
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        18671071
        AUCM
      jtl: Japanese Journal of Radiology
      issn: 18671071
      maglogo: N
    pubinfo:
      dt: Dec2018
      vid: 36
      iid: 12
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        133160232
        133160232
        NLM30232585
        133160232
        10.1007/s11604-018-0779-3
        NLM30232585
        133160232
      ppf: 691
      ppct: 7
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Artificial intelligence using neural network architecture for radiology (AINNAR): classification of MR imaging sequences.
      aug:
        au:
          Noguchi, Tomoyuki
          Higa, Daichi
          Asada, Takashi
          Kawata, Yusuke
          Machitori, Akihiro
          Shida, Yoshitaka
          Okafuji, Takashi
          Yokoyama, Kota
          Uchiyama, Fumiya
          Tajima, Tsuyoshi
        affil: Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, 162-8655, Tokyo, Japan
      sug:
        subj:
          Neural Networks (Computer)
          Magnetic Resonance Imaging Methods
          Brain
          Brain Physiopathology
          Artificial Intelligence
          Middle Age
          Aged
          Aged, 80 and Over
          Reproducibility of Results
          Magnetic Resonance Angiography
          Magnetic Resonance Imaging
          Female
          Male
          Retrospective Design
          Middle Aged: 45-64 years
          Aged: 65+ years
          Aged, 80 & over
          Female
          Male
      ab: Purpose: The confusion of MRI sequence names could be solved if MR images were automatically identified after image data acquisition. We revealed the ability of deep learning to classify head MRI sequences.Materials and Methods: Seventy-eight patients with mild cognitive impairment (MCI) having apparently normal head MR images and 78 intracranial hemorrhage (ICH) patients with morphologically deformed head MR images were enrolled. Six imaging protocols were selected to be performed: T2-weighted imaging, fluid attenuated inversion recovery imaging, T2-star-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient mapping, and source images of time-of-flight magnetic resonance angiography. The proximal first image slices and middle image slices having ambiguous and distinctive contrast patterns, respectively, were classified by two deep learning imaging classifiers, AlexNet and GoogLeNet.Results: AlexNet had accuracies of 73.3%, 73.6%, 73.1%, and 60.7% in the middle slices of MCI group, middle slices of ICH group, first slices of MCI group, and first slices of ICH group, while GoogLeNet had accuracies of 100%, 98.1%, 93.1%, and 94.8%, respectively. AlexNet significantly had lower classification ability than GoogLeNet for all datasets.Conclusions: GoogLeNet could judge the types of head MRI sequences with a small amount of training data, irrespective of morphological or contrast conditions.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N