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

Development of a next-generation mammography CAD system by using diagnostic logic extraction from bigdata

Research Project

Project/Area Number 26540112
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Intelligent informatics
Research InstitutionTohoku University

Principal Investigator

Homma Noriyasu  東北大学, 医学系研究科, 教授 (30282023)

Co-Investigator(Renkei-kenkyūsha) ISHIBASHI Tadashi  東北大学, 大学院医学系研究科, 教授 (40151401)
KAWASUMI Yusuke  東北大学, 大学院医学系研究科, 講師 (00513540)
YOSHIZAWA Makoto  東北大学, サイバーサイエンスセンター, 教授 (60166931)
Research Collaborator GUPTA Madan  University of Saskatchewan, College of Engineering, Professor Emeritus
HOU Zeng-Guang  Chinese Academy of Sciences, Institute of Automation, Professor
BUKOVSKY Ivo  Czech Technical University in Prague, Faculty of Mechanical Engineering, Associate Professor
ZHANG Xiaoyong  東北大学, 大学院工学研究科, 助教 (90722752)
Project Period (FY) 2014-04-01 – 2017-03-31
Project Status Completed (Fiscal Year 2016)
Budget Amount *help
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2016: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords計算機支援診断システム / 乳房X線撮影 / 機械学習 / 知能情報処理 / 乳房X線撮影 / 画像認識
Outline of Final Research Achievements

In breast cancer screening using mammography, due to the increase of the number of examinees, reading a lot of mammograms became burden for doctors, and it might lead to false detection and unnecessary biopsies. For reducing the work burden of doctors and improving their diagnostic accuracy, computer-aided diagnosis (CAD) systems have been developed. However, it is difficult to design the quantitative features that sufficiently represent the characteristics of abnormalities in mammograms for accurate diagnosis. To solve this problem, we have developed a new CAD system based on a deep learning technique that can extract such features through learning massive data sets. The experimental results showed that diagnostic sensitivity of a typical abnormality was about 90 % and false positive was 20 %. The results demonstrated that the proposed deep learning technique has a potential to be a key strategy for mammographic CAD systems.

Report

(4 results)
  • 2016 Annual Research Report   Final Research Report ( PDF )
  • 2015 Research-status Report
  • 2014 Research-status Report
  • Research Products

    (17 results)

All 2017 2016 2015 2014 Other

All Int'l Joint Research (4 results) Journal Article (2 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 2 results,  Acknowledgement Compliant: 2 results) Presentation (11 results) (of which Int'l Joint Research: 2 results)

  • [Int'l Joint Research] University of Saskatchewan(Canada)

    • Related Report
      2016 Annual Research Report
  • [Int'l Joint Research] Chinese Academy of Sciences(China)

    • Related Report
      2016 Annual Research Report
  • [Int'l Joint Research] Czech Technical University in Prague(チェコ)

    • Related Report
      2016 Annual Research Report
  • [Int'l Joint Research] University of Saskatchewan(Canada)

    • Related Report
      2015 Research-status Report
  • [Journal Article] An Approach to Stable Gradient-Descent Adaptation of Higher Order Neural Units2017

    • Author(s)
      I. Bukovsky, N. Homma
    • Journal Title

      IEEE Trans. Neural Networks and Learning System

      Volume: 印刷中 Issue: 9 Pages: 2022-2034

    • DOI

      10.1109/tnnls.2016.2572310

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
  • [Journal Article] Is Mammographic Breast Density a Risk Factor for Breast Cancer in Japanese Women?2015

    • Author(s)
      Xiaoyong ZHANG, Norimasa CHIKUSHIMA, Atsutoshi WATANABE, Yuji OHASHI, Nao HASEGAWA, Atsushi Tamura, Makoto Osanai, and Noriyasu HOMMA
    • Journal Title

      Bulletin of School of Health Sciences, Tohoku University

      Volume: 24 Pages: 45-51

    • NAID

      120005578868

    • Related Report
      2014 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Presentation] Deep Convolutional Neural Networkの転移学習による乳房X線画像上の腫瘤検出2017

    • Author(s)
      鈴木 真太郎,張 暁勇,本間 経康,吉澤 誠
    • Organizer
      SICE東北支部第307回研究集会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2017-02-27
    • Related Report
      2016 Annual Research Report
  • [Presentation] 乳房X線画像の乳房密度評価への胸筋領域の影響:正常例での胸筋領域の有無による乳房密度の比較2017

    • Author(s)
      魚住洋佑、張暁勇、市地慶、高根侑美、川住祐介、石橋忠司、本間経康
    • Organizer
      第50回日本生体医工学会東北支部大会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2017-01-21
    • Related Report
      2016 Annual Research Report
  • [Presentation] Statistical Analysis of Bilateral Breast Density Differences of Mammogram for Breast Cancer Risk Assessment2017

    • Author(s)
      J. Chen, X. Zhang, N. Homma
    • Organizer
      第50回日本生体医工学会東北支部大会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2017-01-21
    • Related Report
      2016 Annual Research Report
  • [Presentation] Detection of Masses in Mammograms Based on Transfer Learning of A Deep Convolutional Neural Network2016

    • Author(s)
      S. Suzuki, X. Zhang, N. Homma, K. Ichiji, Y. Uozumi, Y. Takane, Y. Kawasumi, T. Ishibashi, M. Yoshizawa
    • Organizer
      第10回コンピューテーショナル・インテリジェンス研究会
    • Place of Presentation
      富山県民会館(富山市)
    • Year and Date
      2016-12-16
    • Related Report
      2016 Annual Research Report
  • [Presentation] Mass Detection Using Deep Convolutional Neural Network for Mammographic Computer-Aided Diagnosis2016

    • Author(s)
      S. Suzuki, X. Zhang, N. Homma, K. Ichiji, Y. N. Sugita, Kawasumi, T. Ishibashi, M. Yoshizawa
    • Organizer
      SICE Annual Conference 2016
    • Place of Presentation
      つくば国際会議場(つくば市)
    • Year and Date
      2016-09-23
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Mammographic Mass Detection Method Based on Transfer Learning of Deep Convolutional Neural Network2016

    • Author(s)
      S. Suzuki, X. Zhang, N. Homma, M. Yoshizawa
    • Organizer
      電気関係学会東北支部連合大会
    • Place of Presentation
      東北工業大学(仙台市)
    • Year and Date
      2016-08-30
    • Related Report
      2016 Annual Research Report
  • [Presentation] Detection of Masses on Mammograms Using Deep Convolutional Neural Network: A Feasibility Study2016

    • Author(s)
      S. Suzuki, X. Zhang, N. Homma, K. Ichiji, Y. Kawasumi, T. Ishibashi, M. Yoshizawa
    • Organizer
      2016 AAPM Annual Meeting
    • Place of Presentation
      Washington DC, USA
    • Year and Date
      2016-08-03
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 乳房X線画像診断支援のための木構造自己組織化マップによる自動特徴抽出の試み2015

    • Author(s)
      長谷川奈保,本間経康,張暁勇,市地慶,小山内実,阿部誠,杉田典大,吉澤誠
    • Organizer
      第7回コンピューテーショナル・インテリジェンス研究会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2015-05-30
    • Related Report
      2015 Research-status Report
  • [Presentation] 群特性に着目した乳房X線画像の微小石灰化群検出性能改善2014

    • Author(s)
      大橋悠二,本間経康,張暁勇,石橋忠司,川住祐介,吉澤誠
    • Organizer
      計測自動制御学会東北支部50周年記念学術講演会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2014-12-11
    • Related Report
      2014 Research-status Report
  • [Presentation] 乳房X線画像診断支援のための多層自己組織化マップによる特徴分類2014

    • Author(s)
      長谷川奈保,本間経康,張暁勇,大橋悠二,吉澤誠
    • Organizer
      計測自動制御学会東北支部50周年記念学術講演会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2014-12-11
    • Related Report
      2014 Research-status Report
  • [Presentation] 輝度分布情報の考慮による乳房X線画像の微小石灰化検出性能改善2014

    • Author(s)
      大橋悠二,張暁勇,本間経康,吉澤誠
    • Organizer
      第48回日本生体医工学会東北支部大会
    • Place of Presentation
      東北大学(仙台市)
    • Year and Date
      2014-12-06
    • Related Report
      2014 Research-status Report

URL: 

Published: 2014-04-04   Modified: 2022-02-16  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi