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

2023 Fiscal Year Final Research Report

The integration of non-invasive imaging of tumor characteristics with deep learning analysis for personalized decision making in patients with head and neck cancer

Research Project

  • PDF
Project/Area Number 21K07558
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 InstitutionHokkaido University

Principal Investigator

Fujima Noriyuki  北海道大学, 大学病院, 講師 (80431360)

Co-Investigator(Kenkyū-buntansha) 本間 明宏  北海道大学, 医学研究院, 教授 (30312359)
Project Period (FY) 2021-04-01 – 2024-03-31
KeywordsMRI / 人工知能 / 頭頸部癌
Outline of Final Research Achievements

Our investigation tried to non-invasively achieve the imaging of functional information in head and neck cancers using MRI. Specifically, we developed imaging methods to visualize protein metabolism within the tumor and to image the microstructure and microarchitecture within the tumor. For these imaging processes, deep learning-based image reconstruction was utilized to obtain higher resolution information within the imaging durations feasible in routine clinical practice. Furthermore, using machine learning-based methods, we elucidated the association between the imaged information and prognostic factors for patients. Based on these findings, we constructed a model to use the imaging information as a prognostic factor clinically, preparing it for future clinical use.

Free Research Field

放射線医学

Academic Significance and Societal Importance of the Research Achievements

頭頸部癌は病理組織学的に同一の組織型であっても生物学的性状が異なる場合が多く、根治治療を達成するためにそれらに応じた個別化医療が求められる。本研究にて得られた画像撮像法により腫瘍の生物学的性状の一部の画像化が達成されたため、腫瘍のより詳細な細分化が可能となった。また、これらの画像情報を機械学習による解析にて、予後予測因子と深く関連することが示唆され、治療反応性の予測を介した個別化医療に向けたバイオマーカーのひとつとなりえると考えられる。これらを今後、臨床的に活用することで、患者予後の改善、および必要ないし不要な治療の判別などで医療費抑制にも有効であることが予想される。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi