Presentation | 2007-05-24 Development of Medical Image Registration Method based on Anatomical Information Chuya FUKUDA, Akinobu SHIMIZU, Hidefumi KOBATAKE, Noboru ORIUCHI, Keigo ENDO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Most of the medical image registration methods between the images taken by different modalities are based on Mutual Information (MI), which is very simple and general criterion for image registration. However, the criterion often suffers from misregistration, because it is not based on anatomical information but intensity of image. The anatomical correspondence between the images to be aligned will compensate for the drawback of the conventional methods, hi this study, we propose a simultaneous registration and segmentation method based on maximizing a posterior probability of label of organs and mapping of the registration given intensity values of the images. Main contribution of the proposed method is that the posterior probability is defined using a probabilistic atlas of organs which is rich in the organ's information and suitable to incorporate the anatomical information into the registration process. We also present the experimental result of registration using pairs of CT and PET images to validate the proposed method and compare the results with those based on the conventional methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Simultaneous Registration and Segmentation / Posterior Probability / Probabilistic Atlas / CT and PET Images |
Paper # | PRMU2007-4,MI2007-4 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2007/5/17(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Development of Medical Image Registration Method based on Anatomical Information |
Sub Title (in English) | |
Keyword(1) | Simultaneous Registration and Segmentation |
Keyword(2) | Posterior Probability |
Keyword(3) | Probabilistic Atlas |
Keyword(4) | CT and PET Images |
1st Author's Name | Chuya FUKUDA |
1st Author's Affiliation | Tokyo University of Agriculture and Technology() |
2nd Author's Name | Akinobu SHIMIZU |
2nd Author's Affiliation | Tokyo University of Agriculture and Technology |
3rd Author's Name | Hidefumi KOBATAKE |
3rd Author's Affiliation | Tokyo University of Agriculture and Technology |
4th Author's Name | Noboru ORIUCHI |
4th Author's Affiliation | Department of Nuclear Medicine, Gunma University School of Medicine |
5th Author's Name | Keigo ENDO |
5th Author's Affiliation | Department of Nuclear Medicine, Gunma University School of Medicine |
Date | 2007-05-24 |
Paper # | PRMU2007-4,MI2007-4 |
Volume (vol) | vol.107 |
Number (no) | 57 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |