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

Development and clinical application of a deep-learning model to predict hemodynamic parameters from chest radiographs

Research Project

Project/Area Number 20KK0375
Research Category

Fund for the Promotion of Joint International Research (Fostering Joint International Research (A))

Allocation TypeMulti-year Fund
Review Section Basic Section 53020:Cardiology-related
Research InstitutionMie University

Principal Investigator

Toba Shuhei  三重大学, 医学部附属病院, 助教 (20806111)

Project Period (FY) 2021 – 2023
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥14,040,000 (Direct Cost: ¥10,800,000、Indirect Cost: ¥3,240,000)
Keywords胸部レントゲン写真 / 小児循環器学 / 先天性心疾患 / 人工知能 / フォンタン手術 / 国際共同研究 / 胸部X線写真 / 手術適応予測 / 血行動態予測 / 血行動態
Outline of Research at the Start

胸部X線写真には循環器に関する情報が豊富に含まれているが、その評価法は従来、医師による定性的な読影のみであった。研究代表者は基課題において胸部X線写真から肺体血流比を定量的に予測する人工知能を開発し、胸部X線写真には医師が認識していない膨大な情報が眠っている可能性があることを示した(Toba et al. JAMA Cardiology. 2020)。本国際共同研究では、胸部X線写真から血行動態を定量的に評価する人工知能を様々な血行動態指標へ応用し、その臨床応用を目指す。

Outline of Final Research Achievements

To improve the performance of artificial intelligence in quantitatively predicting hemodynamic parameters from chest radiograms, we developed a grayscale image-specific deep learning-based model pre-trained using large public datasets, and compared its performance with existing models. The comparison used a public dataset related to pediatric pneumonia diagnosis. In terms of both training time and diagnostic capability, the newly developed model showed improvements over the existing models.

Additionally, using data from Boston Children's Hospital, we developed a deep learning-based model to predict the condition of pulmonary vessels from chest radiograms in preoperative patients undergoing Fontan operation, demonstrating the ability of an artificial intelligence model for quantitative prediction.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果により、胸部X線写真から血行動態指標を定量評価するための高性能な人工知能の基盤モデルが得られた。本モデルを応用することで、胸部X線写真からの低侵襲かつ安価な血行動態指標評価手法の開発が加速し、循環器診療における新たな検査手法の確立が期待される。
また胸部X線写真からFontan型手術の予後を予測することが可能となり、今後より正確な手術適応の判断が可能になり、先天性心疾患手術の治療成績が向上することが期待される。

Report

(3 results)
  • 2023 Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (10 results)

All 2022 2021

All Journal Article (1 results) Presentation (8 results) (of which Int'l Joint Research: 1 results,  Invited: 1 results) Book (1 results)

  • [Journal Article] 先天性心疾患と人工知能-医師を代替するAI,超えるAI-2022

    • Author(s)
      鳥羽修平, 三谷義英
    • Journal Title

      循環器内科

      Volume: 91 Pages: 434-439

    • Related Report
      2022 Research-status Report
  • [Presentation] Development of base model for deep learning of chest radiographs.2022

    • Author(s)
      Sato A, Toba S, Tsuji S, Sugitani R
    • Organizer
      The 4th Annual Meeting of Japanese Association for Medical Artificial Intelligence
    • Related Report
      2022 Research-status Report
  • [Presentation] Quantitative analysis of hemodynamics from chest radiographs using deep learning.2022

    • Author(s)
      Tsuji S, Toba S, Sato A, Sugitani R
    • Organizer
      The 4th Annual Meeting of;Japanese;Association for;Medical Artificial Intelligence
    • Related Report
      2022 Research-status Report
  • [Presentation] 人工知能による胸部X線写真からの定量的血行動態予測2022

    • Author(s)
      辻 清龍, 鳥羽 修平, 藤本 直紀, 佐藤 綾音, 土肥 薫
    • Organizer
      第70回日本心臓病学会学術集会
    • Related Report
      2022 Research-status Report
  • [Presentation] Perioperative Changes of Pulmonary to Systemic Flow Ratio Predicted by Deep Learning-Based Analysis of Chest Radiographs in Patients with Atrial Septal Defect2022

    • Author(s)
      Yusuke Sugitani, Shuhei Toba, Keishin Hattori, Umezu Kentaro, Yoshihide Mitani, Hirofumi Sawada, Hiroyuki Ohashi, Noriko Yodoya, Kazunobu Ohya, Naoki Tsuboya, Hisato Itoh, Yu Shomura, Masahiro Hirayama, Motoshi Takao
    • Organizer
      第87回日本循環器学会学術集会
    • Related Report
      2022 Research-status Report
  • [Presentation] Application of Deep Learning in Pediatric Cardiology2022

    • Author(s)
      Shuhei Toba
    • Organizer
      AHA & JSPCCS joint webinar (Artificial Intelligence and 3D Imaging in Pediatric Cardiology)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep Learning-based Analysis of 12-lead Electrocardiogram for Pediatric Cardiac Disease Mass Screening in School-age Children2021

    • Author(s)
      Shuhei Toba, Yoshihide Mitani, et al.
    • Organizer
      日本循環器学会学術総会 プレナリーセッション
    • Related Report
      2021 Research-status Report
  • [Presentation] 学校心臓検診心電図における人工知能の応用2021

    • Author(s)
      鳥羽修平、三谷義英、et al.
    • Organizer
      日本小児心電図学会学術総会 シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] 学校心臓検診心電図を自動判読する人工知能の開発2021

    • Author(s)
      鳥羽修平,三谷義英、杉谷侑亮、大橋啓之,澤田博文,淀谷典子,大槻祥一郎、山崎誉斗,梅津健太郎
    • Organizer
      日本小児循環器学会学術総会 パネルディスカッション
    • Related Report
      2021 Research-status Report
  • [Book] 「先天性心疾患と人工知能ー医師を代替するAI、超えるAIー」循環器内科, 91(4): 434-4392022

    • Author(s)
      鳥羽修平、三谷義英
    • Total Pages
      510
    • Publisher
      科学評論社
    • Related Report
      2021 Research-status Report

URL: 

Published: 2021-03-19   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi