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

Active clinical application of image generation and analysis using deep learning approach in radiation therapy

Research Project

Project/Area Number 20H04278
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 62010:Life, health and medical informatics-related
Research InstitutionThe University of Tokyo

Principal Investigator

Nakagawa Keiichi  東京大学, 医学部附属病院, 特任教授 (80188896)

Co-Investigator(Kenkyū-buntansha) 名和 要武  東京大学, 医学部附属病院, 助教 (00456914)
鍛冶 静雄  九州大学, マス・フォア・インダストリ研究所, 教授 (00509656)
野沢 勇樹  東京大学, 医学部附属病院, 特任助教 (00836918)
仲本 宗泰  北海道大学, 保健科学研究院, 助教 (10808877)
太田 岳史  東京大学, 医学部附属病院, 特任助教 (20727408)
尾崎 翔  弘前大学, 理工学研究科, 助教 (60615326)
山下 英臣  東京大学, 医学部附属病院, 准教授 (70447407)
今江 禄一  東京大学, 医学部附属病院, 副診療放射線技師長 (80420222)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥16,900,000 (Direct Cost: ¥13,000,000、Indirect Cost: ¥3,900,000)
Fiscal Year 2022: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2021: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2020: ¥7,540,000 (Direct Cost: ¥5,800,000、Indirect Cost: ¥1,740,000)
Keywords放射線治療 / 深層学習 / 画像生成 / 画像解析 / 臨床適用 / 生成解析
Outline of Research at the Start

近年の情報処理技術の発展に伴い,医用画像に対して深層学習を用いた画像生成や解析(以下,深層画像処理)が適用され始めており,従来困難であったモダリティ間の画像変換や高画質化など,様々な応用が期待されている.本研究では,放射線治療における医用画像に対して深層画像処理を施した上で,生成画像や解析結果を放射線治療の様々な状況において安全かつ有効に利用する方法を確立することを目的とする. 研究期間内には,①深層画像処理法の構築,さらに深層画像処理の適用として②放射線治療前,③治療期間内,④治療後の医用画像を対象として有効性を明確にする.

Outline of Final Research Achievements

The purpose of this study is to apply deep learning and machine learning to medical images obtained by radiation therapy, and to propose safe usage methods for generated images and analysis results. We created a grade prediction and prognosis prediction model for glioma and primary non-small cell lung cancer using a machine learning approach. In addition, we proposed an image quality improvement method, optimization of the number of learning data, and organ segmentation using a deep learning approach.

Academic Significance and Societal Importance of the Research Achievements

本研究では,放射線治療で得られる医用画像に対する機械学習や深層学習の適用について,安定,かつ,安全な臨床利用を念頭に置いたデータ解析法や画質改善法,また,適切な学習データ数に関する提案を行った.医用画像に対する深層学習の適用範囲は広く,本研究の成果は放射線治療で得られる医用画像に対する深層学習の適用方法のいくつかを示したことであり,研究の実施によって得られた知見は学会発表や論文投稿を通して公表した.

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • Research Products

    (14 results)

All 2022 2021 2020 Other

All Journal Article (5 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 4 results,  Open Access: 4 results) Presentation (7 results) (of which Int'l Joint Research: 2 results,  Invited: 1 results) Remarks (2 results)

  • [Journal Article] Establishment of a Prediction Model for Overall Survival after Stereotactic Body Radiation Therapy for Primary Non-Small Cell Lung Cancer Using Radiomics Analysis2022

    • Author(s)
      Subaru Sawayanagi, Hideomi Yamashita, Yuki Nozawa, Ryosuke Takenaka, Yosuke Miki, Kosuke Morishima, Hiroyuki Ueno, Takeshi Ohta, Atsuto Katano.
    • Journal Title

      Cancers (Basel)

      Volume: 14 Issue: 16 Pages: 3859-3859

    • DOI

      10.3390/cancers14163859

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Training of deep cross‐modality conversion models with a small dataset, and their application in megavoltage CT to kilovoltage CT conversion2022

    • Author(s)
      Ozaki S, Kaji S, Nawa K, Imae T, Aoki A, Nakamoto T, Ohta T, Nozawa Y, Yamashita H, Haga A, Nakagawa K
    • Journal Title

      Medical Physics

      Volume: - Issue: 6 Pages: 1-14

    • DOI

      10.1002/mp.15626

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Retrospective dose reconstruction of prostate stereotactic body radiotherapy using cone-beam CT and a log file during VMAT delivery with flattening-filter-free mode2020

    • Author(s)
      Imae Toshikazu,Haga Akihiro,Watanabe Yuichi,Takenaka Shigeharu,Shiraki Takashi,Nawa Kanabu,Ogita Mami,Takahashi Wataru,Yamashita Hideomi,Nakagawa Keiichi,Abe Osamu.
    • Journal Title

      Radiological Physics and Technology

      Volume: 13 Issue: 3 Pages: 238-248

    • DOI

      10.1007/s12194-020-00574-3

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Improvement in Image Quality of CBCT during Treatment by Cycle Generative Adversarial Network2020

    • Author(s)
      今江 禄一, 鍛冶 静雄, 木田 智士, 松田 佳奈子, 竹中 重治, 青木 淳, 仲本 宗泰, 尾崎 翔, 名和 要武, 山下 英臣, 中川 恵一, 阿部 修.
    • Journal Title

      Japanese Journal of Radiological Technology

      Volume: 76 Issue: 11 Pages: 1173-1184

    • DOI

      10.6009/jjrt.2020_JSRT_76.11.1173

    • NAID

      130007941322

    • ISSN
      0369-4305, 1881-4883
    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Recent Review Articles in Radiological Physics and Technology2020

    • Author(s)
      鍛冶 静雄, 木田 智士, 藤田 広志
    • Journal Title

      Japanese Journal of Radiological Technology

      Volume: 76 Issue: 11 Pages: 1207-1210

    • DOI

      10.6009/jjrt.2020_JSRT_76.11.1207

    • NAID

      130007941354

    • ISSN
      0369-4305, 1881-4883
    • Related Report
      2020 Annual Research Report
  • [Presentation] 深層学習によるCT画像変換2022

    • Author(s)
      鍛冶静雄
    • Organizer
      第3回 京大―ハイデルベルク大―理研 ワークショップ 「医学と数理」
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Denoising and Contrast Enhancement of MVCT Using Deep Learning-based Methods2021

    • Author(s)
      Ozaki S, Kaji S, Nawa K, Imae T, Aoki A, Nakamoto T, Ohta T, Nozawa Y, Haga A, Nakagawa K
    • Organizer
      第121回日本医学物理学会学術大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] Training modality conversion models with small data and its application to MVCT to kVCT conversion2021

    • Author(s)
      Ozaki S, Kaji S, Nawa K, Imae T, Aoki A, Nakamoto T, Ohta T, Nozawa Y, Haga A, Nakagawa K
    • Organizer
      ESTRO 2021 Annual Meeting
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 深層学習を用いて画質改善した位置合わせ用CBCT上における線量分布の再構築2021

    • Author(s)
      今江禄一,青木淳,竹中重治,松田佳奈子,三枝茂輝,鍛冶静雄,岩永秀幸,阿部修
    • Organizer
      第49回日本放射線技術学会秋季学術大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 医用画像処理における深層学習ベースの画像変換2021

    • Author(s)
      鍛治 静雄
    • Organizer
      バイオフィジオロジー研究会特別企画Webカンファレンス2021
    • Related Report
      2020 Annual Research Report
  • [Presentation] Imaging biomarker analysis for grading malignant gliomas based on a few conventional magnetic resonance imaging sequences2020

    • Author(s)
      Nakamoto T, Takahashi W, Haga A, Takahashi S, Kiryu S, Nawa K, Ohta T, Ozaki S, Nozawa Y, Tanaka S, Mukasa A, Nakagawa K.
    • Organizer
      2020 Joint AAPM COMP Meeting
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Radiomic-based prediction of malignant glioma grades using preoperative contrast-enhanced T1WIs and T2WIs2020

    • Author(s)
      Nakamoto T, Takahashi W, Haga A, Takahashi S, Kiryu S, Nawa K, Ohta T, Ozaki S, Nozawa Y, Nakagawa K
    • Organizer
      第119回日本医学物理学会学術大会
    • Related Report
      2020 Annual Research Report
  • [Remarks] 東京大学医学部附属病院 放射線科 放射線治療部門 > 研究・業績

    • URL

      http://u-tokyo-rad.jp/works/index.html

    • Related Report
      2022 Annual Research Report 2020 Annual Research Report
  • [Remarks] 東京大学医学部附属病院 放射線科 放射線治療部門 > 研究・業績

    • URL

      http://u-tokyo-rad.jp/works/index.html

    • Related Report
      2021 Annual Research Report

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi