Establishment of artificial intelligence (AI)-based prediction of treatment efficacy for metastatic liver tumors

2022 Fiscal Year Final Research Report

• Project/Area Number: 19K08160
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 52040:Radiological sciences-related
• Research Institution: Iwate Medical University
• Principal Investigator: Tamura Akio (赤羽明生) 岩手医科大学, 医学部, 特任講師 (90714444)
• Co-Investigator(Kenkyū-buntansha): 石田 和之 獨協医科大学, 医学部, 教授 (40444004)
• Project Period (FY): 2019-04-01 – 2023-03-31
• Keywords: 大腸がん肝転移 / CT / 人工知能 / 薬物治療

Outline of Final Research Achievements

After preoperative drug therapy for colorectal cancer liver metastases, when intratumoral necrosis was predominantly infarct-like necrosis (ILN) with few residual cells, the tumor margins had clear boundaries and no contrast effect, while when ILN was predominant but residual tumor cells were numerous, there was a contrast effect at the tumor margins. The type of necrosis was related to the morphology of the tumor margins, and the presence or absence of residual tumor cells and the presence or absence of a dangerous halo were related to the contrast effect at the tumor margins, suggesting that tumor angiogenesis affected the contrast effect.

Free Research Field

放射線医学

Academic Significance and Societal Importance of the Research Achievements

大腸癌肝転移には術前化学療法を反映する組織像が存在し、化学療法のレジメンによってその組織所見は異なることが明らかになった。画像診断的にもそれぞれの組織像に対応した画像所見があり、サイズ以外の治療効果を反映した様々な所見に基づくことで、より客観性のある化学療法の組織学的効果判定が可能と考えられた。。