• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Novel pharmacokinetic analysis for PET molecular imaging based on neural network approach

Research Project

Project/Area Number 18K12073
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 90110:Biomedical engineering-related
Research InstitutionHokkaido Information University (2019-2021)
National Cardiovascular Center Research Institute (2018)

Principal Investigator

Koshino Kazuhiro  北海道情報大学, 経営情報学部, 教授 (90393206)

Co-Investigator(Kenkyū-buntansha) 平野 祥之  名古屋大学, 医学系研究科(保健), 准教授 (00423129)
Project Period (FY) 2018-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
KeywordsPET / ニューラルネットワーク / ノイズ除去 / 動態解析 / PETイメージング / 薬物動態解析 / 分子イメージング / 機械学習
Outline of Final Research Achievements

The purpose of this study is to realize a new pharmacokinetic analysis that is robust and accurate against noise using machine learning based on neural network structures. Processes were divided into two parts: (1) denoising of projection data and (2) estimation of pharmacokinetic parameters for noisy data. The performance of the neural networks prepared for each process was evaluated. For denoising of the projection data, a peak signal-to-noise ratio of 38.0 ± 0.5 dB was achieved while reducing discontinuities in the body axis direction using a neural network with a three-dimensional convolutional layer and residual connections. For the estimation of pharmacokinetic parameters, an estimation error of -0.3±12.4% was achieved for blood flow estimation.

Academic Significance and Societal Importance of the Research Achievements

ガウスノイズを対象としたノイズ除去研究は数多いが、投影データに含まれるポアソンノイズをニューラルネットワークによって除去可能であること、およびニューラルネットワークに基づく手法が既存手法より正確に血流量を推定可能であることを示したことは、本研究成果の意義である。正確な定量の実現は、齧歯類からヒトまで同じ放射性薬剤と測定方法を使用できるPETイメージングの高精度化を通して、新薬のスクリーニングや臨床試験、疾患診断、治療評価、細胞質の機能解明に貢献する。さらに、ヒトでは正確な画像診断に必要な放射能量の低減、つまり被ばく量の低減につながるため、放射線防護の観点から有用である。

Report

(5 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (2 results)

All 2021 2019

All Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (1 results) (of which Invited: 1 results)

  • [Journal Article] Narrative review of generative adversarial networks in medical and molecular imaging2021

    • Author(s)
      Kazuhiro Koshino, Rudolf A. Werner, Martin G. Pomper, Ralph A. Bundschuh, Fujio Toriumi, Takahiro Higuchi, Steven P. Rowe
    • Journal Title

      Annals of Translational Medicine

      Volume: -

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] Generative adversarial networks in molecular imaging2019

    • Author(s)
      Kazuhiro Koshino
    • Organizer
      PET Seminar in Tohoku 2019
    • Related Report
      2019 Research-status Report
    • Invited

URL: 

Published: 2018-04-23   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi