Development of technology to predict and track the position and shape of luminal organs using artificial intelligence

• Project/Area Number: 18K15535
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 52040:Radiological sciences-related
• Research Institution: Hokkaido University
• Principal Investigator: Nishioka Kentaro 北海道大学, 医学研究院, 助教 (80463743)
• Project Period (FY): 2018-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000); Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000); Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
• Keywords: 人工知能 / セグメンテーション / 適合放射線治療 / 機械学習 / 膀胱癌 / 放射線治療 / 画像認識 / 深層学習 / 陽子線治療 / ディープラーニング / 医学物理（学）

Outline of Final Research Achievements

When radiotherapy is applied to luminal organs whose position and shape change from day to day, the status of target organ may not match between at the time of treatment planning and the actual time of treatment. In order to realize the optimized radiotherapy according to the position and shape of the target in the daily treatment, this study carried out to develop the technology which enable us to predict and track the position and shape of the organ using artificial intelligence. After machine learning using previously acquired MRI images of 100 patients as teacher data, artificial intelligence successfully delineated the bladder contour with a mean Dice coefficient index of 94.4%.

Academic Significance and Societal Importance of the Research Achievements

MRIは放射線被曝なしに画像情報を取得できるため、日々の放射線治療時の臓器の位置や形状を取得する手法として最適である。本研究で、人工知能の機械学習によりMRI画像上で日々の膀胱の位置・形状を高精度に取得できることが示された。この技術は他の管腔臓器においても利用可能であり、MRI撮像機能を搭載した放射線治療装置が既に開発されていることから、本研究はMRIを用いて日々の臓器の位置・形状に最適化した放射線治療(すなわち適合放射線治療)を実現するための礎になる。

Research Products

• [Journal Article] The urethral position may shift due to urethral catheter placement in the treatment planning for prostate radiation therapy (2019)
  • Author(s): Dekura Yasuhiro、Nishioka Kentaro、Hashimoto Takayuki、Miyamoto Naoki、Suzuki Ryusuke、Yoshimura Takaaki、Matsumoto Ryuji、Osawa Takahiro、Abe Takashige、Ito Yoichi M.、Shinohara Nobuo、Shirato Hiroki、Shimizu Shinichi
  • Journal Title: Radiation Oncology Volume: 14 Issue: 1 Pages: 226-226
  • DOI: 10.1186/s13014-019-1424-8
  • Peer Reviewed / Open Access
• [Presentation] Automatic bladder delineation on MR images using a convolution neural network for online image-guided radiotherapy (2020)
  • Author(s): Kentaro Nishioka, Yusuke Nomura, Takayuki Hashimoto, Rumiko Kinoshita, Norio Katoh, Hiroshi Taguchi, Koichi Yasuda, Takashi Mori, Yusuke Uchinami, Manami Otsuka, Taeko Matsuura, Seishin Takao, Ryusuke Suzuki, Sodai Tanaka, Takaaki Yoshimura, Hidefumi Aoyama, Shinichi Shimizu
  • Organizer: 62nd ASTRO Annual meeting
  • Int'l Joint Research
• [Presentation] 進行期前立腺癌に対する根治的IMRTの初期経験 (2019)
  • Author(s): 西岡 健太郎、橋本 孝之、森 崇、長江 伸樹、木下 留美子、安部 崇重、大澤 崇宏、松本 隆児、篠原 信雄、白土 博樹1、清水 伸一
  • Organizer: 日本放射線腫瘍学会第32回学術大会