Generative Adversarial Networks for Brain MRI Synthesis: Impact of Training Set Size on Clinical Application.

We evaluated the impact of training set size on generative adversarial networks (GANs) to synthesize brain MRI sequences. We compared three sets of GANs trained to generate pre-contrast T1 (gT1) from post-contrast T1 and FLAIR (gFLAIR) from T2. The baseline models were trained on 135 cases; for this...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Digital Imaging Vol. 37; no. 3; pp. 1228 - 1239
Autores principales: Zoghby, MM, Erickson, BJ, Conte, GM
Formato: diagnostic images research tables/charts Journal Article
Publicado: Springer Nature Jun2024
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=178678181&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 178678181
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        08971889
        DOQ
      jtl: Journal of Digital Imaging
      issn: 08971889
      maglogo: N
    pubinfo:
      dt: Jun2024
      vid: 37
      iid: 3
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        178678181
        178678181
        178678181
        10.1007/s10278-024-00976-4
        178678181
      ppf: 1228
      ppct: 11
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Generative Adversarial Networks for Brain MRI Synthesis: Impact of Training Set Size on Clinical Application.
      aug:
        au:
          Zoghby, MM
          Erickson, BJ
          Conte, GM
        affil: https://ror.org/02qp3tb03 Department of Radiology, Mayo Clinic, Rochester, MN, USA
      sug:
        subj:
          Brain Physiology
          Magnetic Resonance Imaging Methods
          Generative Adversarial Networks Evaluation
          Image Interpretation, Computer Assisted
          Education, Clinical
          Learning Methods
          Models, Theoretical
          Human
          Prospective Studies
          Glioma
          Comparative Studies
          Descriptive Statistics
          Diagnostic Errors
          Artificial Intelligence, Generative
          Data Analysis Software
          Mann-Whitney U Test
          Image Enhancement
          Coefficient alpha
          Funding Source
      ab: We evaluated the impact of training set size on generative adversarial networks (GANs) to synthesize brain MRI sequences. We compared three sets of GANs trained to generate pre-contrast T1 (gT1) from post-contrast T1 and FLAIR (gFLAIR) from T2. The baseline models were trained on 135 cases; for this study, we used the same model architecture but a larger cohort of 1251 cases and two stopping rules, an early checkpoint (early models) and one after 50 epochs (late models). We tested all models on an independent dataset of 485 newly diagnosed gliomas. We compared the generated MRIs with the original ones using the structural similarity index (SSI) and mean squared error (MSE). We simulated scenarios where either the original T1, FLAIR, or both were missing and used their synthesized version as inputs for a segmentation model with the original post-contrast T1 and T2. We compared the segmentations using the dice similarity coefficient (DSC) for the contrast-enhancing area, non-enhancing area, and the whole lesion. For the baseline, early, and late models on the test set, for the gT1, median SSI was.957,.918, and.947; median MSE was.006,.014, and.008. For the gFLAIR, median SSI was.924,.908, and.915; median MSE was.016,.016, and.019. The range DSC was.625–.955,.420–.952, and.610–.954. Overall, GANs trained on a relatively small cohort performed similarly to those trained on a cohort ten times larger, making them a viable option for rare diseases or institutions with limited resources.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N