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

Automated grading system for the retinal arteriolosclerosis in a cardiology risk screening

Research Project

Project/Area Number 19K10662
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 58030:Hygiene and public health-related: excluding laboratory approach
Research InstitutionOsaka University

Principal Investigator

Kawasaki Ryo  大阪大学, 医学系研究科, 特任教授(常勤) (70301067)

Co-Investigator(Kenkyū-buntansha) 大久保 孝義  帝京大学, 医学部, 教授 (60344652)
中島 悠太  大阪大学, データビリティフロンティア機構, 准教授 (70633551)
Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
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)
Fiscal Year 2019: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Keywords眼底写真 / 人工知能 / 健康診断 / 動脈硬化 / 網膜血管 / 循環器検診 / 深層学習 / 検診 / 予防医学 / 危険因子 / 循環器疾患 / 眼底検診 / 高血圧 / 循環器リスク
Outline of Research at the Start

眼底は網膜血管を直接観察できるため「全身の窓」とも呼ばれる。循環器疾患のリスク評価における眼底所見には「網膜細動脈径の狭細」と「網膜細動脈硬化所見」があり、我が国で広く用いられてきた。
「網膜細動脈径の狭細」は現代の大規模疫学研究で再評価が進み、大規模疫学研究による知見が蓄積しつつある一方、「網膜細動脈硬化所見」の評価法は主観的で過去80年間変わっていない。本研究では健診において深層学習等を用いた自動判定システムの開発を目指す。新しい手法で革新的な眼底評価方法を確立することはさらに循環器疾患のリスク評価の精度を高め、我が国の循環器疾患予防に貢献できる可能性がある。

Outline of Final Research Achievements

"The eye is the window to the entire body," and fundus findings have long been used in medical examinations to assess the risk of cardiovascular disease. The evaluation method for "retinal arteriolosclerosis findings" (Scheie: S findings) has relied on visual inspection. In this study, we developed a system to evaluate retinal arteriolosclerosis findings. Using a pipeline consisting of multiple deep learning models, we obtained a precision of 98.1% and a recall of 89.7% for the extraction of crossings through the extraction of blood vessels from fundus images. The estimated severity of retinal artery crossing phenomenon was 0.61 in Kappa value and 0.77 in agreement. Through this study, we were able to construct an automatic determination system while reproducing the process of a physician's determination of fundus photographs.

Academic Significance and Societal Importance of the Research Achievements

特定健康診査において循環器リスク評価のための眼底検査の潜在的な対象人数は約2600万人にも上る。このような対象者に、迅速かつ再現性の高い眼底評価方法で循環器病リスク評価に貢献する眼底指標を提供することは我が国の循環器病予防に貢献する可能性がある。

Report

(4 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (16 results)

All 2022 2021 2020 2019

All Journal Article (6 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 6 results,  Open Access: 3 results) Presentation (8 results) (of which Int'l Joint Research: 7 results,  Invited: 1 results) Book (2 results)

  • [Journal Article] MTUNet: Few-Shot Image Classification With Visual Explanations2021

    • Author(s)
      Bowen Wang, Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
    • Journal Title

      Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops

      Volume: - Pages: 2294-2298

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] SCOUTER: Slot attention-based classifier for explainable image recognition2021

    • Author(s)
      Liangzhi Li, Bowen Wang, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
    • Journal Title

      Proceedings of the IEEE/CVF International Conference on Computer Vision

      Volume: - Pages: 1046-1055

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation2021

    • Author(s)
      Wang Bowen、Li Liangzhi、Nakashima Yuta、Kawasaki Ryo、Nagahara Hajime、Yagi Yasushi
    • Journal Title

      IEEE Access

      Volume: 9 Pages: 46810-46820

    • DOI

      10.1109/access.2021.3067928

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Joint learning of vessel segmentation and artery/vein classification with post-processing2020

    • Author(s)
      Li L, Verma M, Nakashima Y, Kawasaki R, Nagahara H.
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: 121 Pages: 440-453

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Retinal neovascularization-simulating retinal capillary reperfusion in branch retinal vein occlusion, imaged by wide-field optical coherence tomography angiography.2020

    • Author(s)
      Sakimoto S, Kawasaki R, Nishida K.
    • Journal Title

      JAMA Ophthalmology

      Volume: 138 Issue: 2 Pages: 216-218

    • DOI

      10.1001/jamaophthalmol.2019.5018

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Improving the current diabetic macular oedema screening programme.2019

    • Author(s)
      Wong I, Wong R, Gangwani R, Chong V, Kawasaki R.
    • Journal Title

      Hong Kong Med J.

      Volume: 25 Pages: 8-11

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Cardiovascular Disease Risk Prediction using Retinal Images via Explainable-AI based models with Traditional CVD risk factor estimation2022

    • Author(s)
      Ryo Kawasaki, Yiming Qian, Liangzhi Li, Kohji Nishida, Yuta Nakashima, Hajime Nagahara
    • Organizer
      ARVO
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] SCOUTER: Slot attention-based classifier for explainable image recognition2021

    • Author(s)
      Liangzhi Li, Bowen Wang, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
    • Organizer
      IEEE/CVF International Conference on Computer Vision
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] MTUNet: Few-Shot Image Classification With Visual Explanations2021

    • Author(s)
      Bowen Wang, Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
    • Organizer
      IEEE/CVF International Conference on Computer Vision
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A fully automated grading system for the retinal arteriovenous crossing signs using deep neural network based pipeline.2020

    • Author(s)
      Ryo Kawasaki, LIangzhi Li, Yuta Nakashima, Hajime Nagahara, Takayoshi Ohkubo
    • Organizer
      日本網膜硝子体学会
    • Related Report
      2020 Research-status Report
  • [Presentation] IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks2020

    • Author(s)
      Li L, Verma M, Nakajima Y, Nagahara H, Kawasaki R
    • Organizer
      WACV 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing2020

    • Author(s)
      Li L, Verma M, Nakashima Y, Kawasaki R, Nagahara H.
    • Organizer
      MIDL 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks2020

    • Author(s)
      Liangzhi Li, Manisha Verma, Yuta Nakashima, Hajime Nagahara, Ryo Kawasaki
    • Organizer
      The IEEE Winter Conference on Applications of Computer Vision
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Epidemiology of eye diseases: a framework to connect the dots.2019

    • Author(s)
      Kawasaki R
    • Organizer
      The 121th Korean Ophthalmological Society
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research / Invited
  • [Book] Computational Retinal Image Analysis2019

    • Author(s)
      Kawasaki R & Graulsund J.
    • Total Pages
      502
    • Publisher
      Elsevier
    • ISBN
      9780081028162
    • Related Report
      2019 Research-status Report
  • [Book] Innovative Approaches in the Delivery of Primary and Secondary Eye Care2019

    • Author(s)
      Kawasaki R & Kawasaki Y
    • Total Pages
      194
    • Publisher
      Springer
    • ISBN
      9783319980133
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi