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

Development of computer-aided diagnosis system for lung cancer CT screening using deep learning

Research Project

Project/Area Number 16K19883
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Radiation science
Research InstitutionKyoto University

Principal Investigator

Nishio Mizuho  京都大学, 医学研究科, 特定助教 (50581998)

Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywordsコンピューター支援診断 / 肺結節 / CT / 深層学習 / 機械学習 / テクスチャー解析 / 肺癌 / 肺気腫 / ホモロジー / 癌 / 放射線 / 情報工学
Outline of Final Research Achievements

Our research was conducted based on two major themes. One is quantitative evaluation of emphysema for predicting lung cancer base risk in CT lung cancer screening, and the other is development of computer-aided diagnosis system for differentiation of lung nodules detected in lung cancer CT screening.

In the former, we show that quantitative evaluation of pulmonary emphysema using homology method was useful for predicting the base risk of lung cancer. Also, in the latter, the accuracy of computer-aided diagnosis of lung nodule could be improved using deep learning.

Academic Significance and Societal Importance of the Research Achievements

CT肺癌検診は高い偽陽性で知られており、この偽陽性をいかに減らすかがCT肺癌検診の研究の焦点の一つである。この点から、今回の研究成果をCT肺癌検診に応用する際、以下の二点が有用になると考えられる。

一つ目のテーマの研究成果により、肺気腫の定量評価を用いて肺癌のベースのリスクが高い患者を選択することが可能となり、これが偽陽性の低減に間接的に有用と期待される。CT肺癌検診の偽陽性の直接の原因は検診で見つかった肺結節であり、これにどう対応するかで偽陽性が大きく変動する。今回のコンピューター支援診断のソフトウェアは肺結節の肺癌の確率を出力できるため、これは直接に偽陽性の低減に有用と期待される。

Report

(4 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (17 results)

All 2019 2018 2017

All Journal Article (10 results) (of which Peer Reviewed: 9 results,  Open Access: 6 results,  Acknowledgement Compliant: 1 results) Presentation (6 results) (of which Int'l Joint Research: 2 results,  Invited: 1 results) Book (1 results)

  • [Journal Article] Estimation of lung cancer risk using homology-based emphysema quantification in patients with lung nodules2019

    • Author(s)
      Nishio Mizuho、Kubo Takeshi、Togashi Kaori
    • Journal Title

      PLOS ONE

      Volume: 14 Issue: 1 Pages: e0210720-e0210720

    • DOI

      10.1371/journal.pone.0210720

    • NAID

      120006551762

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Automatic inference model construction for computer-aided diagnosis of lung nodule: Explanation adequacy, inference accuracy, and experts' knowledge.2018

    • Author(s)
      Kawagishi M, Kubo T, Sakamoto R, Yakami M, Fujimoto K, Aoyama G, Emoto Y, Sekiguchi H, Sakai K, Iizuka Y, Nishio M, Yamamoto H, Togashi K.
    • Journal Title

      PLoS One

      Volume: 16 Issue: 11 Pages: e0207661-e0207661

    • DOI

      10.1371/journal.pone.0207661

    • NAID

      120006539611

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Computer-aided diagnosis of lung nodule classification between benign nodule, primary lung cancer, and metastatic lung cancer at different image size using deep convolutional neural network with transfer learning2018

    • Author(s)
      Nishio Mizuho、Sugiyama Osamu、Yakami Masahiro、Ueno Syoko、Kubo Takeshi、Kuroda Tomohiro、Togashi Kaori
    • Journal Title

      PLOS ONE

      Volume: 13 Issue: 7 Pages: e0200721-e0200721

    • DOI

      10.1371/journal.pone.0200721

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Convolutional neural networks: an overview and application in radiology2018

    • Author(s)
      Yamashita Rikiya、Nishio Mizuho、Do Richard Kinh Gian、Togashi Kaori
    • Journal Title

      Insights into Imaging

      Volume: 9 Issue: 4 Pages: 611-629

    • DOI

      10.1007/s13244-018-0639-9

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization2018

    • Author(s)
      Nishio Mizuho、Nishizawa Mitsuo、Sugiyama Osamu、Kojima Ryosuke、Yakami Masahiro、Kuroda Tomohiro、Togashi Kaori
    • Journal Title

      PLOS ONE

      Volume: 13 Issue: 4 Pages: e0195875-e0195875

    • DOI

      10.1371/journal.pone.0195875

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Computer-aided Diagnosis for Lung Cancer: Usefulness of Nodule Heterogeneity2017

    • Author(s)
      Nishio M, Nagashima C
    • Journal Title

      Acad Radiol.

      Volume: 24 Issue: 3 Pages: 328-336

    • DOI

      10.1016/j.acra.2016.11.007

    • Related Report
      2017 Research-status Report 2016 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] Response to the Letter from LUNGx Challenge2017

    • Author(s)
      Nishio Mizuho
    • Journal Title

      Academic Radiology

      Volume: 24 Issue: 7 Pages: 918-918

    • DOI

      10.1016/j.acra.2017.04.003

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] Automated prediction of emphysema visual score using homology-based quantification of low-attenuation lung region2017

    • Author(s)
      Nishio Mizuho、Nakane Kazuaki、Kubo Takeshi、Yakami Masahiro、Emoto Yutaka、Nishio Mari、Togashi Kaori
    • Journal Title

      PLOS ONE

      Volume: 12 Issue: 5 Pages: e0178217-e0178217

    • DOI

      10.1371/journal.pone.0178217

    • NAID

      120006358781

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Convolutional auto-encoder for image denoising of ultra-low-dose CT2017

    • Author(s)
      Nishio Mizuho、Nagashima Chihiro、Hirabayashi Saori、Ohnishi Akinori、Sasaki Kaori、Sagawa Tomoyuki、Hamada Masayuki、Yamashita Tatsuo
    • Journal Title

      Heliyon

      Volume: 3 Issue: 8 Pages: e00393-e00393

    • DOI

      10.1016/j.heliyon.2017.e00393

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] COPD・非COPD患者のCT画像における低濃度域の評価 -LAA%、D、ホモロジー法の3手法の対比-2017

    • Author(s)
      西尾瑞穂、中根和昭、田中豊
    • Journal Title

      臨床放射線

      Volume: 62 Pages: 179-187

    • Related Report
      2017 Research-status Report
  • [Presentation] Automatic segmentation of uterus with malignant tumor on MRI using U-net.2018

    • Author(s)
      Yasuhisa Kurata, Mizuho Nishio, Koji Fujimoto, Masahiro Yakami, Aki Kido, Hiroyoshi Isoda, Kaori Togashi
    • Organizer
      Computer Assisted Radiology and Surgery. 32th International Congress and Exhibition
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 深層学習とCT画像データベースを用いたコンピューター支援支援診断システムの開発2017

    • Author(s)
      西尾瑞穂
    • Organizer
      日本医療情報学会 関西支部2016年度 第2回講演会
    • Related Report
      2017 Research-status Report
    • Invited
  • [Presentation] ホモロジーによる肺気腫の定量評価と視覚評価の関係および機械学習による視覚評価の予測について2017

    • Author(s)
      西尾瑞穂、中根和昭、久保武、八上全弘、江本豊、西尾真理、富樫かおり
    • Organizer
      第9回呼吸機能イメージング研究会学術集会
    • Related Report
      2017 Research-status Report
  • [Presentation] 患者情報を考慮した胸部CT画像の診断支援の試み2017

    • Author(s)
      上野翔子, 杉山治, 西尾瑞穂, 八上全弘, 山本豪志朗, 岡本和也, 南部雅幸, 黒田知宏
    • Organizer
      第4回「JAMI医用知能情報学研究会-JSAI医用人工知能研究会」合同研究会
    • Related Report
      2017 Research-status Report
  • [Presentation] 3次元特徴を捉えた深層学習による肺結節のコンピュータ診断支援システムの設計2017

    • Author(s)
      上野翔子, 杉山治, 西尾瑞穂, 八上全弘, 山本豪志朗, 岡本和也, 南部雅幸, 黒田知宏
    • Organizer
      第61回 システム制御情報学会研究発表講演会
    • Related Report
      2017 Research-status Report
  • [Presentation] Relationship between lung cancer and homology-based CT quantification in CT database of lung nodules2017

    • Author(s)
      Mizuho Nishio, Kazuaki Nakane, Takeshi Kubo, Masahiro Yakami, Yutaka Emoto, Thai Aakasaka, Koji Onoue, Kaori Togashi
    • Organizer
      Computer Assisted Radiology and Surgery (CARS)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Book] Lung Imaging and CADx. Computer-aided diagnosis of lung nodules: systems for estimation of lung cancer probability and false positive reduction of lung nodule detection2019

    • Author(s)
      Mizuho Nishio
    • Publisher
      Taylor & Francis
    • Related Report
      2018 Annual Research Report

URL: 

Published: 2016-04-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi