Computer-Aided Diagnosis of Autopsy Imaging Based on Computational Anatomy

2013 Fiscal Year Final Research Report

• Project Area: Computational anatomy for computer-aided diagnosis and therapy :Frontiers of medical image sciences
• Project/Area Number: 21103007
• Research Category: Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
• Allocation Type: Single-year Grants
• Review Section: Science and Engineering
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: AKINOBU Shimizu 東京農工大学, 工学(系)研究科(研究院), 准教授 (80262880)
• Co-Investigator(Kenkyū-buntansha): YAMAMOTO Seiji 放射線医学総合研究所, 重粒子医科学センター, 医師 (40302567)
• Project Period (FY): 2009-07-23 – 2014-03-31
• Keywords: 計測工学 / 機械学習 / 計算機支援診断 / 統計数学 / オートプシー・イメージング / 画像診断 / 解剖学

Research Abstract

We carried out a study on computational anatomy and computer aided diagnosis of autopsy imaging. In practice, a computational anatomy model for an organ of autopsy imaging was constructed and a segmentation algorithm with the computational anatomy model for a postmortem CT volume was developed. Subsequently, we develop a bone fracture detection algorithm from a postmortem CT volume. Eventually we validated the performance of the segmentation algorithm and the bone fracture detection algorithm. It was confirmed from the validation results that the proposed algorithms were superior to conventional algorithms in terms of organ segmentation performance as well as bone fracture detection accuracy.

Research Products

• [Journal Article] Statistical Shape Model of a Liver for Autopsy Imaging (2014)
  • Author(s): Atsushi Saito, Akinobu Shimizu, Hidefumi Watanabe, Seiji Yamamoto, Shigeru Nawano and Hidefumi Kobatake
  • Journal Title: International Journal of Computer Assisted Radiology and Surgery Volume: Volume 9, Issue 2 Pages: 269-281
  • DOI: 10.1007/s11548-013-0923-6
• [Journal Article] A conditional statistical shape model with integrated error estimation of the conditions; application to liver segmentation in non-contrast CT images (2014)
  • Author(s): Sho Tomoshige, Elco Oost, Akinobu Shimizu, Hidefumi Watanabe, Shigeru Nawano
  • Journal Title: Medical Image Analysis Volume: vol.18 Pages: 130-143
  • DOI: 10.1016/j.media.2013.10.003
• [Journal Article] Multi-shape graph cuts with neighbor prior constraints and its application to lung segmentation from a chest CT volume (2013)
  • Author(s): Keita Nakagomi, Akinobu Shimizu, Hidefumi Kobatake, Masahiro Yakami, Koji Fujimoto, Kaori Togashi
  • Journal Title: Medical Image Analysis Volume: vol.17 Pages: 62-77
  • DOI: 10.1016/j.media.2012.08.002
• [Presentation] 死後CT 像のテクスチャ解析による死因・死後経過時間推定 (2014)
  • Author(s): 平野靖, 時安竣一, 徐睿, 橘理恵, 木戸尚治, 斉藤篤, 清水昭伸
  • Organizer: 日本医用画像工学会大会
  • Place of Presentation: 東京慈恵会医科大学 大学1号館
  • Year and Date: 2014-07-26
• [Presentation] Automated lung segmentation for autopsy imaging using graph cuts with a statistical shape model (2014)
  • Author(s): Atsushi Saito, Satoshi Okata, Akinobu Shimizu, Hidefumi Watanabe, Shigeru Nawano
  • Organizer: International Journal of Computer Assisted Radiology and Surgery
  • Place of Presentation: Fukuoka International Congress Center, Japan
  • Year and Date: 2014-06-26
• [Presentation] Automated liver segmentation from a CT volume of a cadaver using a statistical shape model (2013)
  • Author(s): Atsushi Saito, Akinobu Shimizu, Hidefumi Watanabe, Seiji Yamamoto, Hidefumi Kobatake
  • Organizer: International Journal of Computer Assisted Radiology and Surgery
  • Place of Presentation: Heidelberg Convention Center, Germany
  • Year and Date: 2013-06-28
• [Book] Condition Relaxation in Conditional Statistical Shape Models" In : Subspace Methods for Pattern Recognition in Intelligent Environment; Eds. Yen-Wie Chen, Lakhmi Jain (2014)
  • Author(s): Elco Oost, Sho Tomoshige and Akinobu Shimizu
  • Publisher: Springer-Verlag, Berlin, Germany
• [Remarks]
  • URL: http://www.comp-anatomy.org/wiki/