講演抄録/キーワード |
講演名 |
2019-02-20 13:00
3D residual networkに基づくPET/CT画像を用いた悪性腫瘍候補の自動検出 ○李 宗曜・藤後 廉・小川貴弘・平田健司・真鍋 治・志賀 哲・長谷山美紀(北大) |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
In this paper, we propose a malignant tumor candidate detection method with FDG-PET/CT images. We design our network based on the residual architecture. The network can learn from the metabolic information provided by PET images and the anatomical information provided by CT images simultaneously. Our method achieved a sensitivity of 0.993 at a false positive rate of 20. The performance is acceptable for the preliminary candidate detection. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Medical image analysis / Tumor detection / PET/CT / Deep learning / / / / |
文献情報 |
映情学技報, vol. 43, no. 5, ME2019-58, pp. 311-314, 2019年2月. |
資料番号 |
ME2019-58 |
発行日 |
2019-02-12 (MMS, HI, ME, AIT) |
ISSN |
Print edition: ISSN 1342-6893 Online edition: ISSN 2424-1970 |
PDFダウンロード |
|