Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists' interpretations at various levels.

Journal: Japanese journal of radiology
Published Date: Apr 18, 2023

Abstract

PURPOSE: To evaluate the diagnostic performance of deep learning using the Residual Networks 50 (ResNet50) neural network constructed from different segmentations for distinguishing malignant and benign non-mass enhancement (NME) on breast magnetic resonance imaging (MRI) and conduct a comparison with radiologists with various levels of experience.

Authors

  • Mariko Goto
    Radiology.
  • Koji Sakai
    Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho, Kawaramachi Hirokoji Agaru, Kamigyo-ku, Kyoto, Kyoto, 602-8566, Japan. sakai3@koto.kpu-m.ac.jp.
  • Yasuchiyo Toyama
    Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, 465 Kajiicho, Kawaramachi Hirokoji, Kamigyoku, Kyoto, 602-8566, Japan.
  • Yoshitomo Nakai
    Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, 465 Kajiicho, Kawaramachi Hirokoji, Kamigyoku, Kyoto, 602-8566, Japan.
  • Kei Yamada
    Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho, Kawaramachi Hirokoji Agaru, Kamigyo-ku, Kyoto, Kyoto, 602-8566, Japan.

Keywords

External Resources

Popular Topics
Recent Journals