2016 Fiscal Year Final Research Report

Intelligent decision support systems for total hip arthroplasty (THA): Towards fully automated preoperative planning of orthopedic surgery

Research Project

PDF

Project/Area Number	25242051
Research Category	Grant-in-Aid for Scientific Research (A)
Allocation Type	Single-year Grants
Section	一般
Research Field	Medical systems
Research Institution	Nara Institute of Science and Technology (2014-2016) Osaka University (2013)
Principal Investigator	Sato Yoshinobu 奈良先端科学技術大学院大学, 情報科学研究科, 教授 (70243219)
Co-Investigator(Kenkyū-buntansha)	大竹義人奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (80349563) 横田太奈良先端科学技術大学院大学, 情報科学研究科, 助教 (60759900) 鍵山善之山梨大学, 総合研究部, 助教 (30506506) 高尾正樹大阪大学, 医学(系)研究科(研究院), 助教 (30528253) 鈴木直樹東京慈恵会医科大学, 医学部, 教授 (40147327) 田中正夫大阪大学, 基礎工学研究科, 教授 (40163571) 多田幸生神戸大学, システム情報学研究科, 教授 (70135812) 菅野伸彦大阪大学, 医学(系)研究科(研究院), 教授 (70273620) 中本将彦大阪大学, 医学系研究科, 助教 (00380634)
Co-Investigator(Renkei-kenkyūsha)	Miki Hidenobu 独立行政法人国立病院機構大阪医療センター, 臨床研究センター, 医長 (10335391)
Research Collaborator	Zheng Guoyan University of Bern, Associate Professor
Project Period (FY)	2013-04-01 – 2017-03-31
Keywords	遠隔診断治療システム / 医用画像・バイオイメージング / 関節病学 / 機械学習 / 画像情報処理 / 生体生命情報学 / 情報システム / 人工知能
Outline of Final Research Achievements	We developed automated preoperative planning systems from bone anatomy models, especially focusing on total hip arthroplasty (THA). In order to optimize both anatomical compatibility and joint functionalities from different aspects, the frameworks of multi-objective optimization and Bayesian estimation were adopted. A statistical surgical case model is constructed, and the problem is formulated as fitting the patient data with the statistical model. The formulation was generalized so as to deal with different types of the femoral stem implants and 2D X-ray images as input patient data (without 3D CT images). Further, the system was shown to be useful for other parts of bones and joints. Finally, we showed potential usefulness of fully automated preoperative planning of THA directly from CT images by combining both automation of CT segmentation and preoperative planning towards clinical applications.
Free Research Field	医用画像処理、コンピュータ外科、計算解剖学