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

2023 Fiscal Year Final Research Report

Examination of Misrecognition in Diagnostic Support Algorithms Using Deep Learning

Research Project

  • PDF
Project/Area Number 20K16734
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 52040:Radiological sciences-related
Research InstitutionOsaka Metropolitan University (2022-2023)
Osaka City University (2020-2021)

Principal Investigator

Honjo Takashi  大阪公立大学, 大学院医学研究科, 研究員 (30779492)

Project Period (FY) 2020-04-01 – 2024-03-31
Keywords人工知能 / AI / 深層学習 / Deep learning
Outline of Final Research Achievements

In this study, initial research focused on misrecognition was conducted, but due to the failure to achieve ideal performance, we pivoted to developing deep learning-based super-resolution technology aimed at improving the visibility of microcalcifications in mammography images. By using AI, it became possible to more clearly depict microcalcifications, potentially contributing to the early detection of breast cancer. The evaluation was conducted using a perception-based image quality evaluation (PIQE) and visual assessment by radiologists, with AI-enhanced images receiving higher ratings than the original images.

Free Research Field

放射線診断学・IVR学

Academic Significance and Societal Importance of the Research Achievements

本研究によって開発された超解像技術は、乳がんの早期発見に直接貢献することが期待される。特に、従来のマンモグラフィでは見逃されがちな微小石灰化の視認性が向上し、乳がん診断の精度が向上する可能性が示された。学術的には、ディープラーニングを応用した画像処理技術の進展を示し、放射線画像診断分野における新たな基準を設けることに貢献している。社会的には、この技術が実用化されれば、乳がんによる死亡率の低減に寄与すると同時に、医療現場での診断支援ツールとしての役割を果たす。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi