• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

1996 Fiscal Year Final Research Report Summary

Development of PET/MR image fusing system

Research Project

Project/Area Number 07555127
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section試験
Research Field 計測・制御工学
Research InstitutionTokyo Institute of Technology

Principal Investigator

KOSUGI Yukio  Tokyo Institute of Technology, Interdisciplinary Graduate School of Science and Engineering, Associate Professor, 大学院・総合理工学研究科, 助教授 (30108237)

Co-Investigator(Kenkyū-buntansha) KAMEYAMA Keisuke  Tokyo Institute of Technology, Interdisciplinary Graduate School of Science and, 大学院・総合理工学研究科, 助手 (40242309)
NISHIKAWA Junichi  University of Tokyo, School of Medicine, Associate Professor, 医学部, 助教授 (00010322)
Project Period (FY) 1995 – 1996
KeywordsPET / image fusion / neural networks / inverse problems / ill-posedness / MR images / dynamic regularization / blood-flow distribution
Research Abstract

Positron Emission Tomography (PET) will give important information in diagnosing intra-cranial metabolic disease as well as in investigating the functional mechanism of the brain, when we can get clear images.
Amongst variety of methods so far proposed, the MR-based deconvolution process might be one of the most important key-techniques in improving the PET imaging quality. In this research, we investigated the inverse problem of the deconvolving process within the framework of the network inversion technique, with respect to the neural network model for the partial volume effect arising in the positron emission tomography. To stabilize the inverse solution, we incorporate such a priori knowledge as the histological information given by MR images and the smoothness in the distribution of the blood-flow, which can be realized by the Tikhonov's regularization.
In particular, in this research we proposed a "dynamic regularization technique" in which the regularizing parameter should be changed according to each stage of the ongoing iterative optimization procedure. We developed the method and proved the effectiveness of the dynamic regularization in use with respect to a simple inverse problem, followed by the actual application to the brain PET image restoration process, with successful results demonstrated.

  • Research Products

    (12 results)

All Other

All Publications (12 results)

  • [Publications] Y.Kosugi et al.: "Neural Network Based PET Image Reconstruction" Methods of Information in Medicine. (印刷中). (1997)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Kosugi et al.: "CCE-Based Index Selection for Neuro Assisted MR-image Segmentation" Proc. IEEE Int. Conf. Image Processing. 249-252 (1996)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 植本尚子、小杉幸夫: "アプリオリ情報を用いたPET画像修復系の構成" 電子情報通信学会技術報告. MBE96-113. 95-102 (1997)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 松井和宏、小杉幸夫: "MRI組織分類における遺伝的アルゴリズムによる特徴量の選択" 電子情報通信学会論文誌(DII). J80-DII(印刷中). (1997)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 菅波、亀山、小杉 他: "MR援用PET画像処理における組織分数ニューラルネット" 電子情報通信学会技術報告. MBE95-95. 45-52 (1995)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 佐瀬、本田、小杉 他: "MR画像との融合によるPET画像の3次元デコンボリューション" 第4回日本コンピュータ外科学会抄録. 43-44 (1995)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Kosugi et al.: "Quantification of Brain Function Using PET" Academic Press (Ralph Myers et al. Eds)(第32章分担), 443 (1996)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Yukio Kosugi, Yusuke Suganami, Naoko Uemoto, Keisuke kameyama, Mikiya Sase, Toshimitsu Momose and Junichi Nishikawa: "CCE-Based Index Selection for Neuro Assisted MR-Image Segmentation" Proc.IEEE 1996 Intemationa Conference on Image Processing. 249-252 (1996)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Yukio Kosugi, Mikiya Sase, Yusuke Suganami, Naoko Uemoto, Toshimitsu Momose and Junichi Nishikawa: "Neural Network Based PET Image Reconstruction" Proc.2nd IFMBE-IMIA International Workshop on Biosignal Interpretation. 163-166 (1996)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Naoko Uemoto, Yukio Kosugi, Toshimitsu Momose and Junichi Nishikawa: "Dynamic Regularization Technique for the MR-Based Reconstruction of PET Images" Proc.First International Workshop on Advanced Signal Processing for Medical MRIS. (in Press). (1997)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Kazuhiro Matsui and Yukio Kosugi: "GA Approach to Select the Best Index Combination for Neural-network-aided MR Segmentation" Proc.First International Workshop on Advanced Signal Processing for Medical MRIS. (in Press). (1997)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Yukio Kosugi, Mikiya Sase, Yusuke Suganami, Toshimitsu Momose and Junichi Nishikawa: Dissolution of Partial Volume Effect in PET by an Inversion Technique with the MR-Embedded Nerual Network Model. R.Myers et al. (Eds.) Quantification of Brain Function Using PET (Chap.32). Academic Press, (1996)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 1999-03-09  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi