Deep learning-based detection of parathyroid adenoma by Tc-MIBI scintigraphy in patients with primary hyperparathyroidism.

Journal: Annals of nuclear medicine
PMID: 35182328

Abstract

OBJECTIVE: It is important to detect parathyroid adenomas by parathyroid scintigraphy with 99m-technetium sestamibi (Tc-MIBI) before surgery. This study aimed to develop and validate deep learning (DL)-based models to detect parathyroid adenoma in patients with primary hyperparathyroidism, from parathyroid scintigrams with Tc-MIBI.

Authors

  • Atsushi Yoshida
    Department of Nuclear Medicine, Graduate School of Medicine, Osaka City University, Osaka, Japan.
  • Daiju Ueda
    Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, 1-4-3 Asahi-machi, Abeno-ku, Osaka, 545-8585, Japan. ai.labo.ocu@gmail.com.
  • Shigeaki Higashiyama
    Department of Nuclear Medicine, Graduate School of Medicine, Osaka City University, Osaka, Japan.
  • Yutaka Katayama
    From the Department of Diagnostic and Interventional Radiology (D.U., A.Y., T.S., S.D., A.S., Y.M.) and Department of Premier Preventive Medicine (S.F.), Osaka City University Graduate School of Medicine, 1-4-3 Asahi-machi, Abeno-ku, Osaka 545-8585, Japan; LPixel, Tokyo, Japan (M.N., A.C., Y.S.); and Department of Radiology, Osaka City University Hospital, Osaka, Japan (Y.K.).
  • Toshimasa Matsumoto
    Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka City University, 1-4-3, Asahimachi, Abeno-ku, Osaka, 545-8585, Japan.
  • Takashi Yamanaga
    Department of Radiology, Osaka City University Hospital, 1-5-7, Asahimachi, Abeno-ku, Osaka, 545-8586, Japan.
  • Yukio Miki
    Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, 1-4-3 Asahi-machi, Abeno-ku, Osaka, 545-8585, Japan.
  • Joji Kawabe
    Department of Nuclear Medicine, Graduate School of Medicine, Osaka City University, Osaka, Japan.

Keywords

External Resources

Popular Topics
Recent Journals