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

three-dimensional AI cancer diagnosis

Research Project

Project/Area Number 17K19646
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Research Field General internal medicine and related fields
Research InstitutionThe University of Tokyo

Principal Investigator

Onodera Hiroshi  東京大学, 大学院工学系研究科(工学部), 特任教授 (20214207)

Research Collaborator ONO satoshi  
USHIKU tetsuo  
KONISHI kuniaki  
MATSUZAKI hiroki  
Project Period (FY) 2017-06-30 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2018: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2017: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Keywords臓器透明化 / 3次元画像解析 / 癌診断 / 病理学 / 多光子顕微鏡 / 共焦点顕微鏡 / 病理診断 / 人工知能 / 3次元診断 / 情報工学
Outline of Final Research Achievements

In order to obtain high resolution 3D cancer diagnosis of GI tract specimens, we developed a new type tissue clearing solvent. As a result, tissue structure over 1000micrometer depth was clearly visualized by using multiphoton microscope. As for confocal microscope, tissue strocture over 500micrometer depth was visible with the image quality suitable for pathological diagnosis. However, thousands of tissue images could not be handled by human pathologist. Thus, we developed a deep learning program, which utilizes convolutional neural network and long short term memory technique. This method provided a satisfactory sensitivity of 0.94 for cancer detection.

Academic Significance and Societal Importance of the Research Achievements

癌の病理診断は標本の断面を染色することによりなされているが全断面を観察することは現実的には不可能である.したがって標本内に小さな癌病変があった場合,見落としリスクをゼロにすることはできない.そこで我々は標本を透明化してレーザー顕微鏡で標本内部を全て観察する技術を確立した.この結果数千枚の画像データが作られるが,人間である病理診断医がすべての画像に目を通すことは不可能である.そこでディープラーニングを用いて癌が疑われる部分を抽出して癌診断を支援する方法を開発した.病変検出精度は94%に達し,癌を見落とさない診断技術として臨床に提供していきたい.

Report

(3 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • Research Products

    (1 results)

All 2018

All Journal Article (1 results) (of which Peer Reviewed: 1 results)

  • [Journal Article] Transparency-enhancing technology allows three-dimensional assessment of gastrointestinal mucosa: A porcine model2018

    • Author(s)
      Mizutani H, Ono S, Ushiku T, Kudo Y, Ikemura M, Kageyama N, Yamamichi N, Fujishiro M, Someya T, Fukayama M, Koike K, Onodera H.
    • Journal Title

      Pathology International

      Volume: 68 Pages: 102-108

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed

URL: 

Published: 2017-07-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi