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

Elimination of motion artifacts from DSA images using deep learning

Research Project

Project/Area Number 20K16769
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 52040:Radiological sciences-related
Research InstitutionOsaka Metropolitan University (2022-2023)
Osaka City University (2020-2021)

Principal Investigator

Ueda Daiju  大阪公立大学, 大学院医学研究科, 研究員 (90779480)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2023: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2022: ¥130,000 (Direct Cost: ¥100,000、Indirect Cost: ¥30,000)
Fiscal Year 2021: ¥130,000 (Direct Cost: ¥100,000、Indirect Cost: ¥30,000)
Fiscal Year 2020: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Keywords人工知能 / AI / 深層学習 / Deep learning / 画像変換 / GAN / 敵対的学習 / DSA / インターベンショナルラジオロジー / IVR / Deepl earning / Interventional radiology / Interventional Radiology
Outline of Research at the Start

血管造影検査において欠くことのできない重要な技術の一つがdigital subtraction angiography (DSA)である。ライブ画像からマスク画像をサブトラクションすることで造影された血管のみを描出する技術で、病変までの血管走行の確認から病変の診断にまで広く用いられる。だがDSAは臨床的には患者の動きのある症例や腸管などに対しては適応が困難である。本研究ではディープラーニングの技術でアーチファクトから開放されたDSA画像を作成することを目的とする。

Outline of Final Research Achievements

In this study, we developed a deep learning model to reduce misregistration artifacts in DSA images. Validation using cerebral and abdominal angiograms showed that the images generated by deep learning were quantitatively and qualitatively equivalent to or better than conventional DSA images. This model allows for less artifactual vascular images even in cases with body motion, which is expected to enable smoother examinations and treatments.

Academic Significance and Societal Importance of the Research Achievements

本研究で開発したディープラーニングモデルは、従来のDSA画像に伴うミスレジストレーションアーチファクトを大幅に低減し、体動のある症例においても鮮明な血管像を提供できる。これにより、血管造影検査・治療の精度向上や時間短縮が期待でき、患者への負担軽減にもつながる。本モデルは、世界に先駆けて開発された革新的技術であり、国内外の医療現場への普及が期待される。

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (9 results)

All 2023 2022 2021

All Journal Article (2 results) (of which Peer Reviewed: 2 results,  Open Access: 2 results) Presentation (7 results) (of which Int'l Joint Research: 6 results,  Invited: 6 results)

  • [Journal Article] Mask-less Two-dimensional Digital Subtraction Angiography Generation Model for Abdominal Vasculature using Deep Learning2022

    • Author(s)
      Yonezawa Hiroki、Ueda Daiju、Yamamoto Akira、Kageyama Ken、Walston Shannon Leigh、Nota Takehito、Murai Kazuki、Ogawa Satoyuki、Sohgawa Etsuji、Jogo Atsushi、Kabata Daijiro、Miki Yukio
    • Journal Title

      Journal of Vascular and Interventional Radiology

      Volume: S1051-0443 Issue: 7 Pages: 00123-3

    • DOI

      10.1016/j.jvir.2022.03.010

    • Related Report
      2022 Research-status Report 2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Deep Learning?based Angiogram Generation Model for Cerebral Angiography without Misregistration Artifacts2021

    • Author(s)
      Ueda Daiju、Katayama Yutaka、Yamamoto Akira、Ichinose Tsutomu、Arima Hironori、Watanabe Yusuke、Walston Shannon L.、Tatekawa Hiroyuki、Takita Hirotaka、Honjo Takashi、Shimazaki Akitoshi、Kabata Daijiro、Ichida Takao、Goto Takeo、Miki Yukio
    • Journal Title

      Radiology

      Volume: Online Issue: 3 Pages: 203692-203692

    • DOI

      10.1148/radiol.2021203692

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Young Leaders Roundtable: What to expect for AI Reading Room 20432023

    • Author(s)
      Daiju Ueda, Rennie Chen, Arunnit Boonrod, Tan Min On
    • Organizer
      The Asian-Oceanian Congress of Neuroradiology 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Generation of synthetic subtraction angiograms in abdominal region using deep learning2022

    • Author(s)
      Hiroki Yonezawa, Daiju Ueda, Akira Yamamoto, Ken Kageyama, Shannon Walston, Takehito Nota;, Kazuki Murai, Satoyuki Ogawa, Etsuji Sohgawa, Atsushi Jogo, Daijiro Kabata, Yukio Miki
    • Organizer
      The Cardiovascular and Interventional Radiological Society of Europe
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] AI applications to aneurysms2021

    • Author(s)
      Daiju Ueda
    • Organizer
      The 13th Asian-Oceanian Congress of Neuroradiology
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep Learning for Cerebral Aneurysms Diagnosis and Treatment2021

    • Author(s)
      Daiju Ueda
    • Organizer
      The 59th Annual Meeting of the American Society of Neuroradiology
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] AI Applications to cerebrovascular imaging2021

    • Author(s)
      Daiju Ueda
    • Organizer
      Society for Imaging Informatics in Medicine 2021 Annual Meeting
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] AI applications to neuroradiology2021

    • Author(s)
      Daiju Ueda
    • Organizer
      The 3rd Annual Scientific Meeting of Asian Society of Magnetic Resonance in Medicine
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] AIによるMRAからの脳動脈瘤検出とDSAのミスレジストレーションからの開放2021

    • Author(s)
      植田大樹
    • Organizer
      神経放射線学会
    • Related Report
      2020 Research-status Report
    • Invited

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi