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

A highly reliable marker-less tumor tracking algorithm for acquiring tumor and bone discrimination intelligence

Research Project

Project/Area Number 17K09054
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Medical Physics and Radiological Technology
Research InstitutionUniversity of Tsukuba

Principal Investigator

Terunuma Toshiyuki  筑波大学, 医学医療系, 助手 (40361349)

Co-Investigator(Kenkyū-buntansha) 榮 武二  筑波大学, 医学医療系, 教授 (60162278)
Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Keywords画像誘導 / 深層学習 / 放射線治療 / マーカーレス / マーカーレス腫瘍追跡 / ディープラーニング / 画像認識 / データ拡張 / X線透視画像 / 画像誘導放射線治療 / 輪郭抽出 / X線透視 / 医学物理 / 腫瘍追跡 / 粒子線治療
Outline of Final Research Achievements

This study aimed to develop a markerless tumor tracking algorithm for the next generation of radiotherapy. Using the feature extraction based on the co-occurrence probability of image features in deep learning image recognition, we developed a training image generation method to induce the effect of recognizing soft tissues, including tumors, as important features and bone structures as unimportant features. Retrospective tests using clinical X-ray fluoroscopy showed the algorithm could track a lung tumor successfully even though the tumor was overlapping on spine in the fluoroscopic images. The results show that the proposed method is a highly accurate and reliable tumor tracking technique.

Academic Significance and Societal Importance of the Research Achievements

本研究によって、ビックデータに依らない、治療対象患者のデータのみを使用する患者固有の深層学習法が初めて提案された。この方法は、従来法で問題となっていた骨特徴が障害となって誤追跡が生じる課題を解決する手法であり、深層学習によって骨特徴を無視するような画像認識を実現できる点が優れている。これまでの方法では腫瘍位置だけを追跡することが目的であったが、本研究方法では腫瘍形状も同時に確認できるという利点がある。臨床画像を利用した良好な追跡結果は、提案法が実用可能性の高い方法であること示した。

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (19 results)

All 2019 2018 2017

All Journal Article (3 results) (of which Peer Reviewed: 2 results,  Open Access: 1 results) Presentation (15 results) (of which Int'l Joint Research: 4 results,  Invited: 4 results) Patent(Industrial Property Rights) (1 results)

  • [Journal Article] Response to “Comments on ‘Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy”’2018

    • Author(s)
      Terunuma Toshiyuki、Sakae Takeji
    • Journal Title

      Radiological Physics and Technology

      Volume: 11 Issue: 3 Pages: 362-363

    • DOI

      10.1007/s12194-018-0471-4

    • NAID

      120007128443

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] [P266] Patient-optimized deep learning for robust tumor tracking2018

    • Author(s)
      Terunuma Toshiyuki、Tomoda Koichi、Sakae Takeji、Ohnishi Kayoko、Okumura Toshiyuki、Sakurai Hideyuki
    • Journal Title

      Physica Medica

      Volume: 52 Pages: 176-176

    • DOI

      10.1016/j.ejmp.2018.06.545

    • Related Report
      2018 Research-status Report
  • [Journal Article] Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy2018

    • Author(s)
      Terunuma Toshiyuki、Tokui Aoi、Sakae Takeji
    • Journal Title

      Radiological Physics and Technology

      Volume: 11 Issue: 1 Pages: 43-53

    • DOI

      10.1007/s12194-017-0435-0

    • NAID

      120007128690

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Application of Deep Learning in Radiotherapy2019

    • Author(s)
      Toshiyuki Terunuma
    • Organizer
      第117回日本医学物理学学術大会Joint Symposium 2:「Innovative Radiology with Artificial Intelligence (AI)」
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] Patient-specific deep learning for real-time tumor contouring2019

    • Author(s)
      Toshiyuki Terunuma
    • Organizer
      3rd NTU-UT Radiation Oncology Joint Symposium
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep learning for super-resolution digitally reconstructed radiography2019

    • Author(s)
      Tsubasa Abe, Toshiyuki Terunuma, Takeji Sakae
    • Organizer
      3rd NTU-UT Radiation Oncology Joint Symposium
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Projected-CTV tracking in MV image:A phantom study2019

    • Author(s)
      大谷篤史、照沼利之、榮武二
    • Organizer
      第118回日本医学物理学会学術大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Image quality improvement of DRR by super-resolution processing2019

    • Author(s)
      阿部飛翔、照沼利之、榮武二
    • Organizer
      第117回日本医学物理学会学術大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Real-time tumor-contouring by patient-specific deep learning: Evaluation using a respiratory moving phantom2019

    • Author(s)
      阿部飛翔、照沼利之、榮武二
    • Organizer
      第117回日本医学物理学会学術大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] X線透視によるマーカーレス腫瘍追跡のために腫瘍と骨の重要性認識制御が可能な深層学習用非線形データ拡張法の理解と臨床X線透視画像を使用した試験結果2018

    • Author(s)
      照沼 利之, 友田 光一, 榮 武二, 大西 かよ子, 奥村 敏之, 櫻井英幸
    • Organizer
      第181回医用画像情報学会大会
    • Related Report
      2018 Research-status Report
  • [Presentation] AIを用いた患者個別深層学習によるマーカーレス腫瘍輪郭追跡法2018

    • Author(s)
      照沼 利之, 友田 光一, 榮 武二, 大西 かよ子, 奥村 敏之, 櫻井英幸
    • Organizer
      日本放射線腫瘍学会第31回学術大会
    • Related Report
      2018 Research-status Report
  • [Presentation] 患者個別深層学習によるマーカーレス腫瘍追跡(1)訓練用DRRの画質改善2018

    • Author(s)
      友田 光一, 照沼 利之, 榮 武二
    • Organizer
      第116回日本医学物理学会学術大会
    • Related Report
      2018 Research-status Report
  • [Presentation] 患者個別深層学習によるマーカーレス腫瘍追跡(2)臨床X線透視画像を使用した追跡結果2018

    • Author(s)
      照沼 利之, 友田 光一, 榮 武二, 大西 かよ子, 奥村 敏之, 櫻井英幸
    • Organizer
      第116回日本医学物理学会学術大会
    • Related Report
      2018 Research-status Report
  • [Presentation] 画像誘導放射線治療のリアルタイム腫瘍追跡における 患者個別深層学習を実現する非線形データ拡張方法2018

    • Author(s)
      照沼 利之, 友田 光一, 榮 武二, 大西 かよ子, 奥村 敏之, 櫻井英幸
    • Organizer
      第37階日本医用画像工学会大会
    • Related Report
      2018 Research-status Report
  • [Presentation] Personalized deep learning - Real-time projected-CTV contouring in X-ray fluoroscopy2018

    • Author(s)
      Toshiyuki Terunuma
    • Organizer
      4D Treatment Workshop for Particle Therapy 2018
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] マーカーレス腫瘍追跡のための Deep Learning 用画像作成方法の改善2018

    • Author(s)
      友田光一、照沼利之、榮武二
    • Organizer
      第15回茨城放射線腫瘍研究会
    • Related Report
      2017 Research-status Report
  • [Presentation] Image Segmentation for Tumor Tracking by Deep Learning with Robustness for Obstacle Object Feature2017

    • Author(s)
      T. TERUNUMA and T. SAKAE
    • Organizer
      59th Annual meeting, american association of medical physics
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Markerless tumor tracking by classification of deep machine learning2017

    • Author(s)
      Toshiyuki Terunuma, Aoi Tokui and Takeji Sakae
    • Organizer
      第113回医学物理学会学術大会
    • Related Report
      2017 Research-status Report
  • [Patent(Industrial Property Rights)] 標的外径推定装置および治療装置2019

    • Inventor(s)
      照沼利之
    • Industrial Property Rights Holder
      照沼利之
    • Industrial Property Rights Type
      特許
    • Filing Date
      2019
    • Related Report
      2019 Annual Research Report

URL: 

Published: 2017-04-28   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi