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

Prediction of radiation pneumonitis with machine learning using dose-volume and dose-function features

Research Project

Project/Area Number 20K16815
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 52040:Radiological sciences-related
Research InstitutionTohoku University

Principal Investigator

Katsuta Yoshiyuki  東北大学, 大学病院, 助教 (90848326)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2023: ¥130,000 (Direct Cost: ¥100,000、Indirect Cost: ¥30,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2020: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords放射線治療 / 肺炎 / 機械学習 / 人工知能 / 放射線誘発性肺炎 / 肺がん / 放射線肺臓炎
Outline of Research at the Start

肺癌の放射線治療において、実際に投与された線量を基にした形態の線量評価と肺機能を基にした機能の線量評価を融合させた新たな放射線肺臓炎予測モデルを構築する。モデルの構築では線量評価と副作用の関係を機械学習によって導き出す。本研究で構築したモデルによって治療計画の段階で正確に放射線肺臓炎を予測できれば、有事事象を未然に予防しつつ安全な投与線量の増加が可能となる。このことにより、肺癌の放射線治療における治療成績の改善が期待できる。

Outline of Final Research Achievements

A predictive model was developed using support vector machine and random forest. Both models were able to build predictive abilities that exceeded existing methods including V20Gy, V5Gy, and mean lung dose. In order to improve predictive ability, we started (1) applying differential histograms and (2) creating a new dose-function feature. The model that added the differential dose-volume-histogram had superior predictive ability compared to the model constructed only from the integral dose-volume-histogram. Next, we created a dose-function specialized for machine learning that avoids multicollinearity. After adding new cases and investigating the benefits of our dose-function features, we obtained predictive performance from the LASSO and support vector machine methods that is expected for clinical use.

Academic Significance and Societal Importance of the Research Achievements

進行非小細胞肺がんの治療計画では、放射線誘発性肺炎を回避する目的で肺機能画像上に抽出した高機能肺領域の被ばくを選択的に低減する方法が試みられている。治療の安全性や成績は改善されつつあるが、一定数の症例で致死性を伴う肺炎が発生している。また、近年では免疫療法の普及によって治療成績の改善が可能となったが、投与は肺炎がGrade2未満の症例に限定されており、肺炎の抑制は重要である。このように、肺炎発生の回避は進行肺がん治療の安全性と治療効果の双方に恩恵をもたらすと考えられ、早急な手立てが熱望されている。

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

    (8 results)

All 2023 2022 2021 2020

All Journal Article (3 results) (of which Peer Reviewed: 3 results,  Open Access: 2 results) Presentation (4 results) (of which Int'l Joint Research: 1 results) Patent(Industrial Property Rights) (1 results)

  • [Journal Article] Radiation pneumonitis prediction model with integrating multiple dose-function features on 4DCT ventilation images2023

    • Author(s)
      Yoshiyuki Katsuta et al.
    • Journal Title

      Physica Medica

      Volume: 105 Pages: 102505-102505

    • DOI

      10.1016/j.ejmp.2022.11.009

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Feasibility of Differential Dose Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence2022

    • Author(s)
      Yoshiyuki Katsuta et al.
    • Journal Title

      Diagnostics

      Volume: 12 Issue: 6 Pages: 1354-1354

    • DOI

      10.3390/diagnostics12061354

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Prediction of radiation pneumonitis with machine learning using 4D-CT based dose-function features2021

    • Author(s)
      Katsuta Yoshiyuki、Kadoya Noriyuki、Mouri Shina、Tanaka Shohei、Kanai Takayuki、Takeda Kazuya、Yamamoto Takaya、Ito Kengo、Kajikawa Tomohiro、Nakajima Yujiro、Jingu Keiichi
    • Journal Title

      Journal of Radiation Research

      Volume: 63 Issue: 1 Pages: 71-79

    • DOI

      10.1093/jrr/rrab097

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Presentation] Evaluation of machine learning-based prediction model with combination of conventional and functional dosimetric parameters for radiation pneumonitis in NSCLC patients2021

    • Author(s)
      Mouri S, Kadoya N, Katsuta Y et al.
    • Organizer
      日本医学物理学会第121回学術大会
    • Related Report
      2021 Research-status Report
  • [Presentation] 複数の放射線生物影響数理モデルによる放射線肺臓炎の予測2021

    • Author(s)
      勝田義之 他
    • Organizer
      日本放射線腫瘍学会第34回学術大会
    • Related Report
      2021 Research-status Report
  • [Presentation] Development of machine learning-based radiation pneumonitis prediction model with combination of conventional, functional dosimetric parameters and clinical factors in NSCLC patients2021

    • Author(s)
      Mouri S, Kadoya N, Katsuta Y et al.
    • Organizer
      日本医学物理学会第122回学術大会
    • Related Report
      2021 Research-status Report
  • [Presentation] Evaluation of machine learning-based prediction model for radiation pneumonitis in NSCLC patients2020

    • Author(s)
      Mouri S, Kadoya N, Katsuta Y, Kanai T, Nakajima Y, Tanabe S, Sugai Y, Umeda M, Dobashi S, Takeda K, Jingu K
    • Organizer
      20th Asia-Oceania Congress of Medical Physics
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Patent(Industrial Property Rights)] 放射線誘発性肺炎を誘発する肺組織を抽出する技術2023

    • Inventor(s)
      勝田義之
    • Industrial Property Rights Holder
      東北大学
    • Industrial Property Rights Type
      特許
    • Filing Date
      2023
    • Related Report
      2023 Annual Research Report

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi