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

Acquisition and Accumulation of Diagnostic Knowledge Based on Deep Learning of Organ and Disease recognitions in Multi-Dimensional Medical Images

Research Project

Project/Area Number 20K11827
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60080:Database-related
Research InstitutionGifu University

Principal Investigator

Zhou Xiangrong  岐阜大学, 工学部, 准教授 (00359738)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Keywords医用画像処理 / 深層学習 / 計算機支援診断 / 機械学習 / machine learning / deep learning / database / CT image / anatomical structures / 医用画像 / データベース / 診断知識の獲得 / 医用画像データベース / 臓器・疾患横断型深層学習法
Outline of Research at the Start

大規模の多次元医用画像(CT,MRI,PET)と医師の診断レポートを収集し,計算機で人体の解剖構造,機能,病変などの知識を逐次的に学習する.学習の結果(様々な画像診断知識を再現するモデル群)を計算機内で蓄積・集約・伝承する仕組みを提案し,知的画像診断支援のための知識ベース(辞書)を構築する.医師のように日々の医療活動から経験を逐次的に積み上げる計算機システムを開発する

Outline of Final Research Achievements

In this study, we constructed a large-scale medical image database for the development of medical AI aimed at efficiently organizing and integrating diverse information such as metabolic function and lesions in the human body on computers, based on the anatomical structures in images, by collecting a vast amount of multidimensional medical images (CT, MRI, PET) . Additionally, we proposed a mechanism for acquiring, accumulating, and transmitting advanced image diagnostic knowledge, including physicians' tacit knowledge, through the fusion of deep learning and dictionary learning, and established a knowledge base for intelligent image diagnostic support. Through these efforts, we have been advancing research towards establishing a machine learning approach that continuously builds upon existing diagnostic knowledge and practical wisdom, enabling adaptation to various diagnostic tasks and aiming for the evolution towards general-purpose AI.

Academic Significance and Societal Importance of the Research Achievements

医用画像の利用により,多くの患者の命が救われてきた.高精度の画像診断には,計算機の支援は必要不可欠である.多次元画像に含まれる膨大な情報から,必要な情報を瞬時に見つけることが重要であり,本研究が目指しているシステムは,以上の現実的な問題を解決できる唯一な方法と考える.医師の診断技術が長期的臨床経験の蓄積であり,貴重な「匠の技」である.しかし,臨床経験には,文字で表現できない暗黙知の部分が多く含まれ,他者との共有が困難かつ次の世代へ引き継げない問題がある.この問題を最終的に解決できれば,名医の「匠の技」を計算機の中に蓄積し続けることが可能となり,医学の発展への大きな波及効果が得られる.

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (20 results)

All 2024 2023 2022 2021 2020 Other

All Journal Article (8 results) (of which Peer Reviewed: 8 results,  Open Access: 3 results) Presentation (9 results) (of which Int'l Joint Research: 1 results) Remarks (3 results)

  • [Journal Article] Simultaneous Learning of Erector Spinae Muscles for Automatic Segmentation of Site-Specific Skeletal Muscles in Body CT Images2024

    • Author(s)
      Kawamoto Masahiro、Kamiya Naoki、Zhou Xiangrong、Kato Hiroki、Hara Takeshi、Fujita Hiroshi
    • Journal Title

      IEEE Access

      Volume: 12 Pages: 15468-15476

    • DOI

      10.1109/access.2023.3335948

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Performance Improvement of Automated Segmentation of Multiple Organs and Tissue Regions in Torso CT images:2023

    • Author(s)
      平林 顕都、周 向栄、原 武史、藤田 広志
    • Journal Title

      Medical Imaging and Information Sciences

      Volume: 40 Issue: 3 Pages: 61-64

    • DOI

      10.11318/mii.40.61

    • ISSN
      0910-1543, 1880-4977
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Tooth recognition of 32 tooth types by branched single shot multibox detector and integration processing in panoramic radiographs2022

    • Author(s)
      Morishita Takumi、Muramatsu Chisako、Seino Yuta、Takahashi Ryo、Hayashi Tatsuro、Nishiyama Wataru、Zhou Xiangrong、Hara Takeshi、Katsumata Akitoshi、Fujita Hiroshi
    • Journal Title

      Journal of Medical Imaging

      Volume: 9 Issue: 03 Pages: 034503-034503

    • DOI

      10.1117/1.jmi.9.3.034503

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Automatic Segmentation of Supraspinatus Muscle via Bone-Based Localization in Torso Computed Tomography Images Using U-Net2021

    • Author(s)
      Yuichi Wakamatsu , Naoki Kamiya , Xiangrong Zhou , Hiroki Kato , Takeshi Hara , Hiroshi Fujita
    • Journal Title

      IEEE ACCESS

      Volume: 9 Pages: 155555-155563

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] A hybrid approach for mammary gland segmentation on CT images by embedding visual explanations from a deep learning classifier into a Bayesian inference2021

    • Author(s)
      Zhou Xiangrong、Yamagishi Seiya、Hara Takeshi、Fujita Hiroshi
    • Journal Title

      SPIE Medical Imaging2021

      Volume: 11597 Pages: 1-6

    • DOI

      10.1117/12.2581924

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Tooth recognition and classification using multi-task learning and post-processing in dental panoramic radiographs2021

    • Author(s)
      Morishita Takumi、Muramatsu Chisako、Zhou Xiangrong、Takahashi Ryo、Hayashi Tatsuro、Nishiyama Wataru、Hara Takeshi、Ariji Yoshiko、Ariji Eiichiro、Katsumata Akitoshi、Fujita Hiroshi
    • Journal Title

      Proc. SPIE 11597, Medical Imaging 2021: Computer-Aided Diagnosis,

      Volume: 115971X Pages: 1-6

    • DOI

      10.1117/12.2582046

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Surface Muscle Segmentation Using 3D U-Net Based on Selective Voxel Patch Generation in Whole-Body CT Images2020

    • Author(s)
      Kamiya Naoki、Oshima Ami、Zhou Xiangrong、Kato Hiroki、Hara Takeshi、Miyoshi Toshiharu、Matsuo Masayuki、Fujita Hiroshi
    • Journal Title

      Applied Sciences

      Volume: 10 Issue: 13 Pages: 4477-4477

    • DOI

      10.3390/app10134477

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Semantic Segmentation of Eight Regions of Upper and Lower Limb Bones Using 3D U-Net in Whole-body CT Images2020

    • Author(s)
      Wakamatsu Yuichi、Kamiya Naoki、Zhou Xiangrong、Hara Takeshi、Fujita Hiroshi
    • Journal Title

      Japanese Journal of Radiological Technology

      Volume: 76 Issue: 11 Pages: 1125-1132

    • DOI

      10.6009/jjrt.2020_JSRT_76.11.1125

    • NAID

      130007941341

    • ISSN
      0369-4305, 1881-4883
    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Presentation] 複数データセットを用いたCT画像からの多臓器自動抽出の継続学習に関する研究2023

    • Author(s)
      西村 彼方,周 向栄,原 武史,藤田 広志
    • Organizer
      医用画像情報学会令和5年度秋季(第197回)大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 複数データセットによる CT 画像からの多臓器抽出法の性能評価 -TotalSegmentator との比較-2023

    • Author(s)
      大杉萌香, 周 向栄, 原 武史, 藤田広志
    • Organizer
      医用画像情報学会令和 5 年度秋季(197 回)大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 訓練データの生成方法がnnU-Netを利用するCT画像における多臓器抽出法の抽出精度に与える影響2023

    • Author(s)
      木村康汰,周向栄,原武志,藤田広志
    • Organizer
      医用画像情報学会令和 5 年度秋季(197 回)大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Automated segmentation of oblique abdominal muscle based on body cavity segmentation in torso CT images using U-Net2022

    • Author(s)
      Kamiya N, Zhou X, Kato H, Hara T, Fujita H
    • Organizer
      International Workshop on Advanced Imaging Technology
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] 深層学習に基づく3次元CT画像からの複数臓器の自動位置検出 ~ 2D-CNNとTransformerの融合 ~2022

    • Author(s)
      加納大暉 , 周 向栄 , 原 武史 , 藤田広志
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 深層ニューラルネットワークに基づく多時相CT画像の位置合わせと解剖構造の自動認識の共同学習に関する研究2022

    • Author(s)
      不破僚太郎 , 周 向栄 , 原 武史 , 藤田広志
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 腹部多時相CT画像の位置合わせのためのCycleGANによる3D Deep-CNNの性能改善に関する初期検討2021

    • Author(s)
      不破僚太郎 , 周 向栄 , 原 武史 , 藤田広志
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 腹部多時相CT画像の位置合わせのためのCycleGANによる3D Deep-CNNの性能改善に関する初期検討2021

    • Author(s)
      不破遼太郎、周 向栄,原 武史、藤田広志
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2020 Research-status Report
  • [Presentation] 胸部CT画像における結節状陰影からのAutoEncorderを用いた特徴抽出2021

    • Author(s)
      田中優多, 原 武史, 周 向栄, 松迫正樹, 野崎太希
    • Organizer
      電子情報通信学会技術研究報告
    • Related Report
      2020 Research-status Report
  • [Remarks] Research Map

    • URL

      https://researchmap.jp/read0108329

    • Related Report
      2023 Annual Research Report
  • [Remarks] Researchmap

    • URL

      https://researchmap.jp/read0108329

    • Related Report
      2021 Research-status Report
  • [Remarks] 研究業績(Research Map)

    • URL

      https://researchmap.jp/read0108329

    • Related Report
      2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi