Statistical spatiotemporal model of anatomical and pathological structures and computer-aided diagnostic imaging

• Project/Area Number: 23500205
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: SHIMIZU Akinobu 東京農工大学, 工学(系)研究科(研究院), 准教授 (80262880)
• Project Period (FY): 2011 – 2013
• Project Status: Completed (Fiscal Year 2013)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2012: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2011: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
• Keywords: 医用画像 / 画像認識 / 統計モデル

Research Abstract

We proposed a statistical spatial model so as to describe the spatial relationship between anatomical structures in a medical imagery. A simultaneous segmentation algorithm of multiple structures based on the model was developed. Subsequently a novel conditional statistical model was proposed, in which a condition can be relaxed and it is automatically optimized based on an error model of the condition of training data. Further contributions are developments of a multi-layer segmentation algorithm with a statistical model of layers and simultaneous recognition algorithm of healthy and pathological structures based on an statistical image database.

Research Products

• [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: 18 Pages: 130-143
  • Peer Reviewed
• [Journal Article] An Automated Segmentation Algorithm for CT Volumes of Livers with Atypical Shapes and Large Pathological Lesions (2014)
  • Author(s): Shun Umetsu, Akinobu Shimizu,Hidefumi Watanabe, Hidefumi Kobatake, Shigeru Nawano
  • Journal Title: IEICE Transactions on Information and Systems Volume: E97.D Issue: 4 Pages: 951-963
  • DOI: 10.1587/transinf.E97.D.951
  • NAID: 130003394921
  • ISSN: 0916-8532, 1745-1361
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Ensemble Learning Based Segmentation of Metastatic Liver Tumours in Contrast-Enhanced Computed Tomography (2013)
  • Author(s): Akinobu Shimizu, Takuya Narihira, Daisuke Furukawa, Hidefumi Kobatake, Shigeru Nawano, Kenji Shinozaki
  • Journal Title: IEICE Transactions on Information and Systems Volume: E96.D Issue: 4 Pages: 864-868
  • DOI: 10.1587/transinf.E96.D.864
  • NAID: 10031182851
  • ISSN: 0916-8532, 1745-1361
  • Peer Reviewed
• [Journal Article] 統計的形状特徴を考慮可能な新しいブースティングアルゴリズムの提案と臓器抽出への応用 (2013)
  • Author(s): 清水昭伸，他
  • Journal Title: MEDICAL IMAGING TECHNOLOGY Volume: 31 Pages: 121-131
  • NAID: 130003374500
  • Peer Reviewed
• [Journal Article] Computer-Aided Diagnosis for a three dimensional CT image (2011)
  • Author(s): A. Shimizu
  • Journal Title: Journal of the Institute of Image Information and Television Engineers Volume: vol.65, no.4 Pages: 432-435
• [Presentation] グラフカットによる黄斑部 OCT 画像上の脈絡膜抽出処理の改良 (2014)
  • Author(s): 稲垣和樹, 清水昭伸, 安野嘉晃, 生野恭司
  • Organizer: 信学技報
  • Place of Presentation: 沖縄ぶんかテンブス館, 沖縄
  • Year and Date: 2014-01-26
• [Presentation] スパースモデリングに基づく確率アトラスの構築とセグメンテーションへの応用 (2014)
  • Author(s): 梅津 駿，清水昭伸，渡部秀文，縄野 繁
  • Organizer: 電子情報通信学会 医用画像研究会
  • Place of Presentation: 沖縄県、那覇市、テンブス館
• [Presentation] グラフカットによる黄斑部OCT画像上の脈絡膜抽出処理の改良 (2014)
  • Author(s): 稲垣和樹，清水昭伸，安野嘉晃，生野恭司
  • Organizer: 電子情報通信学会 医用画像研究会
  • Place of Presentation: 沖縄県、那覇市、テンブス館
• [Presentation] 3次元CT像上の大きな疾病を含む肝臓認識に関する検討 (2013)
  • Author(s): 梅津 駿，清水昭伸，渡部秀文，小畑秀文，縄野 繁
  • Organizer: 電子情報通信学会 医用画像研究会
  • Place of Presentation: 宮城県、仙台市、東北大学
• [Presentation] A Statistical Shape Model for Multiple Organs Based on Synthesized-Based Learning (2013)
  • Author(s): Atsushi Saito, Misaki Nakada, Elco Oost, Akinobu Shimizu, Hidefumi Watanabe, Shigeru Nawano
  • Organizer: Workshop on Computational and Clinical Applications in Abdominal Imaging in conjunction with MICCAI2013
  • Place of Presentation: Nagoya University, Nagoya, Aichi, Japan
• [Presentation] 条件の誤差モデルを用いた条件付き統計的形状モデルの改良 (2013)
  • Author(s): 朝重 青，他
  • Organizer: 医用画像研究会
  • Place of Presentation: 那覇市ぶんかテンブス館，那覇，沖縄
• [Presentation] アンサンブル学習とグラフカットを用いた黄斑部OCT画像からの網膜層セグメンテーション (2012)
  • Author(s): 稲垣和樹，他
  • Organizer: 医用画像研究会
  • Place of Presentation: 東京大学，東京
• [Presentation] Improvement of a simultaneous statistical shape model for multiple abdominal organs using synthesized-based learning (2012)
  • Author(s): Akinobu SHIMIZU, et al.
  • Organizer: CARS2012
  • Place of Presentation: Palazzo dei Congressi, Pisa, Italy
• [Presentation] Interlobar fissure extraction from a chest CT volume based on a new loss function for a boosting algorithm (2012)
  • Author(s): Akinobu SHIMIZU, et al.
  • Organizer: CARS2012
  • Place of Presentation: Palazzo dei Congressi, Pisa, Italy
• [Presentation] A statistical shape model of a dead liver for autopsy imaging (2012)
  • Author(s): Atsushi Saito, et al.
  • Organizer: International Forum on Medical Imaging in Asia
  • Place of Presentation: KAIST, Daejeon, Korea
• [Presentation] Concurrent estimation of regions of normal tissues and pathological lesions in a liver from CT volumes based on the lasso and application to segmentation of liver with lesions (2012)
  • Author(s): Shun Umetsu, et al.
  • Organizer: International Forum on Medical Imaging in Asia
  • Place of Presentation: KAIST, Daejeon, Korea
• [Presentation] Lassoを用いた被検者固有確率アトラスの構築と肝臓領域のセグメンテーション (2012)
  • Author(s): 梅津 駿，他
  • Organizer: バイオイメージ・インフォマティクス ワークショップ2012
  • Place of Presentation: 理化学研究所 発生・再生科学総合研究センター ，神戸
• [Presentation] Relaxed Conditional Statistical Shape Models and their Application to Non-Contrast Liver Segmentation (2012)
  • Author(s): Sho Tomoshige, et al.
  • Organizer: Workshop on Computational and Clinical Applications in Abdominal Imaging
  • Place of Presentation: Novotel Nice Centre Acropolis, Nice, France
• [Presentation] Proposal of a loss function of an object surface and its application to interlobar fissure extraction from a chest CT volume (2012)
  • Author(s): M. Kobayashi, K. Nakagomi, A. Shimizu, H. Kobatake, M. Yakami, K. Fujimoto, K. Togashi
  • Organizer: The Institute of Electronics, Information and Communication Engineers
  • Place of Presentation: 沖縄，那覇市ぶんかテンブス館
• [Presentation] A Statistical Shape Model of an Organ using Synthesized-based Learning (2012)
  • Author(s): A. Saito, M. Nakada, H. Watanabe, A. Shimizu, H. Kobatake, S. Nawano
  • Organizer: The Institute of Electronics, Information and Communication Engineers
  • Place of Presentation: 沖縄，那覇市ぶんかテンブス館
• [Presentation] A simultaneous statistical shape model for multiple abdominal organs (2012)
  • Author(s): M. Nakada, A. Saito, H. Watanabe, A. Shimizu, H. Kobatake, S. Nawano
  • Organizer: The Institute of Electronics, Information and Communication Engineers
  • Place of Presentation: 沖縄，那覇市ぶんかテンブス館
• [Presentation] Statistical shape models of multiple organs in an upper abdominal CT volume (2011)
  • Author(s): A. Shimizu, M. Nakada, H. Kobatake, S. Nawano
  • Organizer: Computer Assisted Radiology and Surgery
  • Place of Presentation: Germany, Berlin, ESTREL HOTEL BERLIN
• [Book] 医用画像工学ハンドブック (2012)
  • Author(s): 尾川浩一, 清水昭伸, 工藤博幸 編
  • Publisher: 日本医用画像工学会
• [Book] 医用画像工学ハンドブック (2012)
  • Author(s): 尾川浩一，他
  • Total Pages: 777
  • Publisher: 日本医用画像工学会
• [Remarks]
  • URL: http://www.tuat.ac.jp/~simizlab/