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

2020 Fiscal Year Final Research Report

Diagnosis of extra nodal extension based on multimodality imaging and machine learning in patients with head and neck cancer.

Research Project

  • PDF
Project/Area Number 18K07758
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 InstitutionKumamoto University

Principal Investigator

Toya Ryo  熊本大学, 大学院生命科学研究部(医), 准教授 (60452893)

Co-Investigator(Kenkyū-buntansha) 甲斐 祐大  熊本大学, 病院, 診療放射線技師 (60816239)
Project Period (FY) 2018-04-01 – 2021-03-31
Keywords放射線治療 / 頭頸部腫瘍 / リンパ節転移 / 節外浸潤 / 機械学習
Outline of Final Research Achievements

We evaluated the diagnostic value of FDG-PET/CT for the identification of ENE in HNSCC patients. We recorded SUVmax and compared the results with pathologic findings of 94 HNSCC patients. An ROC curve analysis for SUVmax showed an AUC value of 0.913. A SUVmax cut-off of 3.0 achieved diagnostic performance for identifying ENE with sensitivity, specificity, and accuracy of 81.1%, 94.3% and 93.1%, respectively. We found that SUVmax cut-off of 3.0 provides appropriate diagnostic value in identifying ENE. Additionally, we evaluated the influence of spatial resolution on SUV based on phantom study. The images were reconstructed using three isotropic voxel sizes. Differences in the SUVmax were significant between the three voxel sizes (p<0.001). We found that spatial resolution influences on SUV, therefore, SUVmax cut-off should be defined based on spatial resolution.

Free Research Field

放射線腫瘍学

Academic Significance and Societal Importance of the Research Achievements

頭頸部腫瘍において、節外浸潤は予後不良因子であるとされ、その有無は治療方針決定に大きな影響を及ぼす。放射線治療の治療計画においても臨床標的体積の決定に必要な情報である。このため節外浸潤の診断は臨床的に非常に重要であるが、これまで診断能が高い方法は報告されていなかった。本研究によって節外浸潤の診断が非常に高い精度をもって可能になることが示唆された。また、近年導入が進んでいる高分解能PET/CT装置の導入における問題点についても新たな知見が得られ、今後更なる研究の発展が期待できるものと考えられる。

URL: 

Published: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi