機械学習を用いたフォトンカウンティング型X線CTにおけるスペクトル歪み補正の基礎的研究

DOI 機関リポジトリ (HANDLE)

書誌事項

タイトル別名
  • FUNDAMENTAL STUDY OF SPECTRAL DISTORTIONS CORRECTION USING MACHINE LEARNING TECHNIQUES IN PHOTON-COUNTING X-RAY CT

この論文をさがす

説明

Owing to the spectral capabilities, a photon counting CT system has generated considerable recent research interest. It can distinguish materials of target objects and enables us to perform a K-edge imaging. However, the photon-counting CT has a critical issue; spectral distortion mainly due to a pulse-pileup effect. In this work, we focus on the capability of nonlinear regression of machine learning and propose a neural network-based method to correct the spectral distortion. The aim of this study is to develop a neural-network based correction method of spectral distortion due to pulse-pileup effects for a photon-counting CT. We investigated the feasibility of our method with a simulation.

収録刊行物

キーワード

詳細情報 詳細情報について

  • CRID
    1390009225532480128
  • NII論文ID
    120007119605
  • NII書誌ID
    AA12677220
  • DOI
    10.15002/00023970
  • HANDLE
    10114/00023970
  • ISSN
    21879923
  • 本文言語コード
    ja
  • 資料種別
    departmental bulletin paper
  • データソース種別
    • JaLC
    • IRDB
    • CiNii Articles
  • 抄録ライセンスフラグ
    使用可

問題の指摘

ページトップへ