Predictive model of lymph node metastasis in T1 colorectal cancer using artificial intelligence

2018 Fiscal Year Final Research Report

• Project/Area Number: 17K15972
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Gastroenterology
• Research Institution: Showa University
• Principal Investigator: Ichimasa Katsuro 昭和大学, 医学部, 助教 (90595612)
• Project Period (FY): 2017-04-01 – 2019-03-31
• Keywords: 早期大腸癌 / 転移 / 人工知能

Outline of Final Research Achievements

We developed an AI model that predicts the presence of lymph node metastasis in early colorectal cancers and validate it. Compared with the current guidelines, AI significantly reduced unnecessary additional surgery after endoscopic resection of early colorectal cancers without missing lymph node metastasis positivity. AI will help in making decisions as to whether additional surgery is indicated after endoscopic resection of early colorectal cancers.
We have published these results in the journal of endoscopy in Europe and have reported in medical conferences in Japan, Europe and USA.

Free Research Field

消化器内科

Academic Significance and Societal Importance of the Research Achievements

早期大腸癌のリンパ節転移の有無を正確に予測し得る人工知能ソフトウェアの開発により、理論上、転移の可能性の少ない手術症例を選別でき、不要な外科手術を減らせることが示された。これにより外科手術ではなく内視鏡治療のみで治療を完結できる症例数の増加が見込め、低侵襲医療の提供および医療費削減の実現に貢献しうる可能性を見出せた。