• AJNR Am J Neuroradiol · Feb 2019

    Improving the Quality of Synthetic FLAIR Images with Deep Learning Using a Conditional Generative Adversarial Network for Pixel-by-Pixel Image Translation.

    • A Hagiwara, Y Otsuka, M Hori, Y Tachibana, K Yokoyama, S Fujita, C Andica, K Kamagata, R Irie, S Koshino, T Maekawa, L Chougar, A Wada, M Y Takemura, N Hattori, and S Aoki.
    • From the Departments of Radiology (A.H., Y.O., M.H., Y.T., S.F., C.A., K.K., R.I., S.K., T.M., L.C., A.W., M.Y.T., S.A.) a-hagiwara@juntendo.ac.jp.
    • AJNR Am J Neuroradiol. 2019 Feb 1; 40 (2): 224-230.

    Background And PurposeSynthetic FLAIR images are of lower quality than conventional FLAIR images. Here, we aimed to improve the synthetic FLAIR image quality using deep learning with pixel-by-pixel translation through conditional generative adversarial network training.Materials And MethodsForty patients with MS were prospectively included and scanned (3T) to acquire synthetic MR imaging and conventional FLAIR images. Synthetic FLAIR images were created with the SyMRI software. Acquired data were divided into 30 training and 10 test datasets. A conditional generative adversarial network was trained to generate improved FLAIR images from raw synthetic MR imaging data using conventional FLAIR images as targets. The peak signal-to-noise ratio, normalized root mean square error, and the Dice index of MS lesion maps were calculated for synthetic and deep learning FLAIR images against conventional FLAIR images, respectively. Lesion conspicuity and the existence of artifacts were visually assessed.ResultsThe peak signal-to-noise ratio and normalized root mean square error were significantly higher and lower, respectively, in generated-versus-synthetic FLAIR images in aggregate intracranial tissues and all tissue segments (all P < .001). The Dice index of lesion maps and visual lesion conspicuity were comparable between generated and synthetic FLAIR images (P = 1 and .59, respectively). Generated FLAIR images showed fewer granular artifacts (P = .003) and swelling artifacts (in all cases) than synthetic FLAIR images.ConclusionsUsing deep learning, we improved the synthetic FLAIR image quality by generating FLAIR images that have contrast closer to that of conventional FLAIR images and fewer granular and swelling artifacts, while preserving the lesion contrast.© 2019 by American Journal of Neuroradiology.

      Pubmed     Free full text   Copy Citation     Plaintext  

      Add institutional full text...

    Notes

     
    Knowledge, pearl, summary or comment to share?
    300 characters remaining
    help        
    You can also include formatting, links, images and footnotes in your notes
    • Simple formatting can be added to notes, such as *italics*, _underline_ or **bold**.
    • Superscript can be denoted by <sup>text</sup> and subscript <sub>text</sub>.
    • Numbered or bulleted lists can be created using either numbered lines 1. 2. 3., hyphens - or asterisks *.
    • Links can be included with: [my link to pubmed](http://pubmed.com)
    • Images can be included with: ![alt text](https://bestmedicaljournal.com/study_graph.jpg "Image Title Text")
    • For footnotes use [^1](This is a footnote.) inline.
    • Or use an inline reference [^1] to refer to a longer footnote elseweher in the document [^1]: This is a long footnote..

    hide…