Endoscopic Image-based Radiomics Classifiers for the Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer Patients

2022 Fiscal Year Final Research Report

• Project/Area Number: 19K16810
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 50020:Tumor diagnostics and therapeutics-related
• Research Institution: The University of Tokyo (2021-2022); Teikyo University (2019-2020)
• Principal Investigator: Ozawa Tsuyoshi 東京大学, 医学部附属病院, 届出研究員 (40829107)
• Project Period (FY): 2019-04-01 – 2023-03-31
• Keywords: 術前化学放射線治療 / 直腸癌 / 機械学習 / 内視鏡

Outline of Final Research Achievements

Neoadjuvant chemoradiotherapy is a standard treatment for rectal cancer worldwide.
In this study, we developed and evaluated machine-learning based classifiers to predict chemoradiotherapy response using endoscopic images in rectal cancer patients.
As a result, our developed classifiers were shown to be able to predict chemoradiotherapy response with high perfomances.

Free Research Field

腫瘍外科学

Academic Significance and Societal Importance of the Research Achievements

直腸癌に対する術前化学放射線治療の効果を内視鏡画像を用いて客観的に評価できるモデルを作成することで、1人1人の患者にあわせた効果的な治療選択が可能になると考えられる。