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

2021 Fiscal Year Final Research Report

Prediction of FFR from coronary MRA using deep learning

Research Project

  • PDF
Project/Area Number 18K07749
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 52040:Radiological sciences-related
Research InstitutionMie University

Principal Investigator

Sakuma Hajime  三重大学, 医学系研究科, 教授 (60205797)

Co-Investigator(Kenkyū-buntansha) 石田 正樹  三重大学, 医学部附属病院, 講師 (10456741)
中山 良平  立命館大学, 理工学部, 教授 (20402688)
Project Period (FY) 2018-04-01 – 2022-03-31
Keywords冠動脈疾患 / 冠動脈MRA / 人工知能
Outline of Final Research Achievements

In this study, the authors optimized a speedup technique for coronary MRA imaging in healthy volunteers and achieve high image quality of coronary MRA using convolutional neural network (CNN) -based image processing techniques. The artificial intelligence-based image processing techniques for diagnosing the stenosis on coronary MRA was investigated using invasive coronary angiography (ICA) as a reference. Preliminary tests showed high diagnostic performance, but there is room for optimization and further research is planned.

Free Research Field

心臓MRI

Academic Significance and Societal Importance of the Research Achievements

本研究では、冠動脈MRAの撮影高速化および高画質化が達成されたが、これは、非侵襲的冠動脈MRA検査の質の向上に寄与し、診断能向上に貢献できることが期待される。また、侵襲的冠動脈造影検査(ICA)で計測される冠動脈狭窄度を、放射線被曝や負荷薬剤投与を必要としない冠動脈MRA画像データから画像処理技術を用い非侵襲的に予測するアルゴリズムの最適化を検討したが、高い診断能を得るまでもう一歩のところまで到達しており、開発が完了すれば医療への波及効果は非常に高いと考えられる。

URL: 

Published: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi