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

Synthetic breath-hold CT generation from free-breathing CT to predict cardiac dose reduction in deep-inspiration breath-hold radiotherapy

Research Project

Project/Area Number 20K16402
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 50020:Tumor diagnostics and therapeutics-related
Research InstitutionAichi Cancer Center Research Institute

Principal Investigator

Koide Yutaro  愛知県がんセンター(研究所), 分子腫瘍学分野, 研究員 (20813067)

Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2022: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2021: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords乳癌 / 放射線治療 / 深吸気息止め照射 / 心臓 / 線量予測 / Predictive assay / 機械学習 / Synthetic CT / 深層学習 / 人工知能
Outline of Research at the Start

左乳癌の深吸気息止め照射は、息止めにより心臓を照射野から離すことで、従来の自由呼吸照射より心臓線量を減らすことができる。しかしどれくらい低減できるかは患者間の差が大きく、予測ができない。申請者のこれまでの研究では、60%の患者は自由呼吸照射でも心臓線量が十分に低く、息止め照射の必要性が低いことがわかった。
本研究では深層学習を用いて、既存のCTから仮想的な深吸気CTを構築し、心臓線量を予測することを目的とする。予測により息止め照射が不要な患者を早期に判別することができればその患者は息止めCTの撮影を省略でき、息止めをする身体的負担がなくなり、さらに治療時間の短縮や医療費の削減が見込める。

Outline of Final Research Achievements

This study aimed to predict the reduction of cardiac dose in left-sided breast cancer patients using deep inspiration breath-hold radiotherapy (DIBH-RT) compared to conventional free-breathing radiotherapy (FB-RT) by utilizing deep learning-based virtual CT. The virtual CT model demonstrated higher accuracy in predicting cardiac dose than existing linear prediction models and also provided good results for lung dose. Furthermore, we identified preoperative lung function, BMI, and chest X-ray images as related parameters and showed that a deep learning chest X-ray prediction model allows for both accuracy and early prediction.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果は、心臓線量の低減効果を事前に予測することで、不要な検査被曝や治療時間の短縮が期待できる点で、学術的意義が大きいと言えます。また、胸部X線画像を用いた深層学習モデルによる早期予測が可能であることが示され、乳癌放射線治療の計画線量予測とその応用に関する多施設研究が進行しており、今後の疾患への応用が期待されています。

Report

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

    (12 results)

All 2023 2022 2021

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 3 results) Presentation (7 results) (of which Int'l Joint Research: 4 results)

  • [Journal Article] Recent trends of characteristics and treatments in adults with newly diagnosed brain metastases2023

    • Author(s)
      Koide Yutaro、Nagai Naoya、Miyauchi Risei、Kitagawa Tomoki、Aoyama Takahiro、Shimizu Hidetoshi、Hashimoto Shingo、Tachibana Hiroyuki、Kodaira Takeshi
    • Journal Title

      Japanese Journal of Clinical Oncology

      Volume: hyad026 Issue: 7 Pages: 572-580

    • DOI

      10.1093/jjco/hyad026

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Preoperative spirometry and BMI in deep inspiration breath-hold radiotherapy: the early detection of cardiac and lung dose predictors without radiation exposure2022

    • Author(s)
      Koide Yutaro、Shimizu Hidetoshi、Aoyama Takahiro、Kitagawa Tomoki、Miyauchi Risei、Watanabe Yui、Tachibana Hiroyuki、Kodaira Takeshi
    • Journal Title

      Radiation Oncology

      Volume: 17 Issue: 1 Pages: 35-35

    • DOI

      10.1186/s13014-022-02002-9

    • Related Report
      2022 Annual Research Report 2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Development of deep learning chest X-ray model for cardiac dose prediction in left-sided breast cancer radiotherapy2022

    • Author(s)
      Koide Yutaro、Aoyama Takahiro、Shimizu Hidetoshi、Kitagawa Tomoki、Miyauchi Risei、Tachibana Hiroyuki、Kodaira Takeshi
    • Journal Title

      Scientific Reports

      Volume: 12 Issue: 1 Pages: 13706-13706

    • DOI

      10.1038/s41598-022-16583-8

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Radiotherapy or systemic therapy versus combined therapy in patients with brain metastases: a propensity-score matched study2022

    • Author(s)
      Koide Yutaro、Nagai Naoya、Miyauchi Risei、Kitagawa Tomoki、Aoyama Takahiro、Shimizu Hidetoshi、Tachibana Hiroyuki、Kodaira Takeshi
    • Journal Title

      Journal of Neuro-Oncology

      Volume: 160 Issue: 1 Pages: 191-200

    • DOI

      10.1007/s11060-022-04132-2

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Synthetic breath-hold CT generation from free-breathing CT: a novel deep learning approach to predict cardiac dose reduction in deep-inspiration breath-hold radiotherapy2021

    • Author(s)
      Koide Yutaro、Shimizu Hidetoshi、Wakabayashi Kohei、Kitagawa Tomoki、Aoyama Takahiro、Miyauchi Risei、Tachibana Hiroyuki、Kodaira Takeshi
    • Journal Title

      Journal of Radiation Research

      Volume: 6 Pages: 1065-1075

    • DOI

      10.1093/jrr/rrab075

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Retrospective non-inferiority study of stereotactic radiosurgery for more than ten brain metastases2023

    • Author(s)
      小出雄太郎
    • Organizer
      欧州放射線腫瘍学会 ESTRO2023
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Fully automated rigid image registration versus human registration in postoperative spine SBRT2022

    • Author(s)
      小出雄太郎
    • Organizer
      欧州放射線腫瘍学会 ESTRO2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Development of deep learning chest X-ray model for cardiac dose prediction in left-sided breast cancer radiotherapy2022

    • Author(s)
      小出雄太郎
    • Organizer
      米国放射線腫瘍学会 ASTRO2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Preoperative spirometry and BMI are early predictive factors of the cardiac and lung dose in deep inspiration breath-hold radiotherapy2022

    • Author(s)
      小出雄太郎
    • Organizer
      米国放射線腫瘍学会 ASTRO2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 最近5年間に診断された転移性脳腫瘍患者の背景因子と治療選択の特徴2022

    • Author(s)
      小出雄太郎
    • Organizer
      日本放射線腫瘍学会 JASTRO2022
    • Related Report
      2022 Annual Research Report
  • [Presentation] 術後脊椎定位放射線治療における全自動剛体画像レジストレーションと手動レジストレーションの比較2022

    • Author(s)
      小出雄太郎
    • Organizer
      第35回高精度放射線外部照射部会学術大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] U-Netを用いた仮想CT生成による左乳癌深吸気息止め照射の心臓線量予測2021

    • Author(s)
      小出 雄太郎、 清水 秀年、北川 智基、青山 貴洋、宮内 理世、立花 弘之、古平 毅
    • Organizer
      日本放射線腫瘍学会第34回学術大会
    • Related Report
      2021 Research-status 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