Development of training-data-circulation-typed surgical assistant framework using medical big data and newly defined surgical information data format including pre- and post-operative data

• Project/Area Number: 15K21035
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Life / Health / Medical informatics; Biomedical engineering/Biomaterial science and engineering
• Research Institution: University of Yamanashi
• Principal Investigator: KAGIYAMA Yoshiyuki 山梨大学, 大学院総合研究部, 准教授 (30506506)
• Research Collaborator: TAKAO Masaki ; SATO Yoshinobu ; OTAKE Yoshito
• Project Period (FY): 2015-04-01 – 2018-03-31
• Project Status: Completed (Fiscal Year 2017)
• Budget Amount: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000); Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2015: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: 計算機支援外科 / 手術計画 / ビッグデータ / 統計アトラス / 深層学習 / 術前支援 / 術後評価 / 畳み込みニューラルネットワーク / 人工股関節全置換術 / 術後予測

Outline of Final Research Achievements

The purpose of this study is to develop a surgical information management method including pre- and post-operative data for total hip replacement and training-data-circulation-typed surgical assistant system using medical big data. In this study, we defined XML data format which is able to handle many patients' data and implants data efficiently, and developed the surgical assistant system which equips exchangeable traning-data-set module and post-operative evaluation. In the experiments of pre-operative phase, 100 cases were applied to the proposed system and several surgical criteria of the optimal plans were compared with surgeon's plans. As a result, one criterion was significantly better than the surgeon's and all the others were almost equivalent. In the experiments of post-operative phase, 19 cases were applied for automated estimation of implant positions and we confirmed the highly accurate determination. We considered that the results showed the usefulness of the system.

Research Products

• [Journal Article] CT-based automated planning of acetabular cup for total hip arthroplasty (THA) based on hybrid use of two statistical atlases. (2016)
  • Author(s): Kagiyama, Y, Sato Y, Otomaru I, Takao M, Nakamoto M, Yokota F, Tomiyama N, Tada Y, Sugano N.
  • Journal Title: International Journal of Computer Assisted Radiology and Surgery. Volume: 11(12) Issue: 12 Pages: 2253-2271
  • DOI: 10.1007/s11548-016-1428-x
  • Peer Reviewed / Open Access
• [Presentation] 人工股関節カップ自動手術計画システムにおける術後データ解析 ～術後CT画像からのカップ自動抽出と術前計画との比較～ (2018)
  • Author(s): 末長和馬，鍵山善之，中西裕紀，日朝祐太，横田太，大竹義人，高尾正樹，菅野伸彦，佐藤嘉伸
  • Organizer: 第12回日本CAOS研究会
• [Presentation] 前捻角統計予測による大腿骨ステム自動術前計画の異機種ステムへの対応 (2018)
  • Author(s): 中西裕紀，鍵山善之，高尾正樹，菅野伸彦，多田幸生，大竹義人，佐藤嘉伸
  • Organizer: 第12回日本CAOS研究会
• [Presentation] 人工股関節自動手術計画立案システムにおける大規模症例データ適用による精度調査 (2016)
  • Author(s): 鍵山善之，中西裕紀，横田太，高尾正樹，小川剛，菅野伸彦，大竹義人，伊藤安海，多田幸生，佐藤嘉伸
  • Organizer: 第二回日中高齢化社会政策と産業化シンポジウム
  • Place of Presentation: 東京工業大学大岡山キャンパス（東京都目黒区）
  • Year and Date: 2016-11-05
  • Int'l Joint Research
• [Presentation] 統計アトラスを用いた人工股関節自動手術計画立案システム (2015)
  • Author(s): 鍵山 善之
  • Organizer: パーティクルフィルタ研究会講演会
  • Place of Presentation: 山梨大学（山梨県・甲府市）
  • Year and Date: 2015-12-24
• [Presentation] Automated Planning System of THA (2015)
  • Author(s): Yoshiyuki Kagiyama
  • Organizer: International Symposium on Musculoskeletal Simulation
  • Place of Presentation: Osaka University Nakanoshima center（大阪府・大阪市）
  • Year and Date: 2015-08-29
  • Int'l Joint Research
• [Book] イラスト医工学 (2017)
  • Author(s): 伊藤安海，鍵山善之
  • Total Pages: 154
  • Publisher: 株式会社アドスリー
  • ISBN: 9784904419694
• [Remarks] 医療ビッグデータ活用による学習循環型手術支援フレームワーク"AutoImPlan"紹介Webサイト
  • URL: http://www.me.yamanashi.ac.jp/lab/ito/AutoImPlan/index.html