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

2023 Fiscal Year Final Research Report

Development of a general-purpose computer-aided diagnosis system using VAE that can be used for a small number of cases

Research Project

  • PDF
Project/Area Number 21H03840
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 90130:Medical systems-related
Research InstitutionOsaka University

Principal Investigator

KIDO SHOJI  大阪大学, 大学院医学系研究科, 特任教授(常勤) (90314814)

Co-Investigator(Kenkyū-buntansha) 梁川 雅弘  大阪大学, 大学院医学系研究科, 准教授 (00546872)
鈴木 裕紀  大阪大学, 大学院医学系研究科, 特任助教(常勤) (20845599)
富山 憲幸  大阪大学, 大学院医学系研究科, 教授 (50294070)
間普 真吾  山口大学, 大学院創成科学研究科, 教授 (70434321)
神谷 亨  九州工業大学, 大学院工学研究院, 教授 (80295005)
平野 靖  山口大学, 医学部附属病院, 准教授 (90324459)
Project Period (FY) 2021-04-01 – 2024-03-31
Keywords画像診断 / 人工知能 / 深層学習 / 異常検知 / 自然言語処理
Outline of Final Research Achievements

In this study, a database of 80,000 PET/CT DICOM images and their findings reports obtained from MI Clinic, an affiliated hospital, has already been created.
Using these cases, Kido (automatic site-specific classification of findings reports using natural language processing and lesion detection using Vision Transformer from PET/CT images), Mabu and Hirano (classification of findings reports focusing on the thesaurus using natural language processing), Kamiya (radiomics analysis of lung cancer (analysis of radiomics of lung cancer using linguistic information), Nakayama (development of unsupervised abnormality detection AI using chest CT images), Teramoto (semantic segmentation of abdominal organs), etc., and many papers were accepted for presentation at conferences including international conferences.

Free Research Field

人工知能画像診断学

Academic Significance and Societal Importance of the Research Achievements

本研究は、8万例のPET/CT画像と所見レポートのデータベース化を通じて、医用画像解析と自然言語処理の分野で重要な成果を上げました。病変検出、読影所見分類、肺癌解析、異常検知AI、臓器セグメンテーションなどの研究成果において、多岐にわたる研究が国際学会や論文で評価された。これにより、診断精度の向上、医療現場の効率化、医療費の削減が期待され、全体的な医療サービスの質向上に貢献することが期待される。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi