Virtual Interpolation Images of Tumor Development and Growth on Breast Ultrasound Image Synthesis With Deep Convolutional Generative Adversarial Networks

DOI Web Site Web Site Web Site 被引用文献1件
  • Tomoyuki Fujioka
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Kazunori Kubota
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Mio Mori
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Leona Katsuta
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Yuka Kikuchi
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Koichiro Kimura
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Mizuki Kimura
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Mio Adachi
    Department of Surgery, Division of Breast Surgery Tokyo Medical and Dental University Tokyo Japan
  • Goshi Oda
    Department of Surgery, Division of Breast Surgery Tokyo Medical and Dental University Tokyo Japan
  • Tsuyoshi Nakagawa
    Department of Surgery, Division of Breast Surgery Tokyo Medical and Dental University Tokyo Japan
  • Yoshio Kitazume
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan
  • Ukihide Tateishi
    Department of Diagnostic Radiology Tokyo Medical and Dental University Tokyo Japan

説明

<jats:sec><jats:title>Objectives</jats:title><jats:p>We sought to generate realistic synthetic breast ultrasound images and express virtual interpolation images of tumors using a deep convolutional generative adversarial network (DCGAN).</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>After retrospective selection of breast ultrasound images of 528 benign masses, 529 malignant masses, and 583 normal breasts, 20 synthesized images of each were generated by the DCGAN. Fifteen virtual interpolation images of tumors were generated by changing the value of the input vector. A total of 60 synthesized images and 20 virtual interpolation images were evaluated by 2 readers, who scored them on a 5‐point scale (1, very good; to 5, very poor) and then answered whether the synthesized image was benign, malignant, or normal.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The mean score of overall quality for synthesized images was 3.05, and that of the reality of virtual interpolation images was 2.53. The readers classified the generated images with a correct answer rate of 92.5%.</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>A DCGAN can generate high‐quality synthetic breast ultrasound images of each pathologic tissue and has the potential to create realistic virtual interpolation images of tumor development.</jats:p></jats:sec>

収録刊行物

被引用文献 (1)*注記

もっと見る

問題の指摘

ページトップへ