The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article propose un algorithme de segmentation automatisé pour les images cérébrales IRM grâce à l'utilisation complémentaire d'images pondérées T1, pondérées T2 et PD. L'algorithme de segmentation proposé est composé de 3 étapes. La première étape consiste à extraire des images cérébrales en plaçant un masque cérébral sur les trois images d’entrée. Dans la deuxième étape, des clusters exceptionnels représentant les tissus internes du cerveau sont choisis parmi les clusters tridimensionnels (3D). Les clusters 3D sont déterminés en croisant des parties densément distribuées d'un histogramme 3D dans un espace 2D formé à l'aide de trois images à échelle optimale. L'image à l'échelle optimale résulte de l'application d'un filtrage d'espace d'échelle à chaque histogramme 3D et à une structure graphique de recherche. En conséquence, l’image à l’échelle optimale peut décrire avec précision la forme des parties de pixels densément distribuées dans l’histogramme 2D. Dans la dernière étape, les images cérébrales sont segmentées par l'algorithme FCM (Fuzzy c-means) en utilisant la valeur centrale du cluster exceptionnelle comme valeur centrale initiale. La capacité de l'algorithme de segmentation proposé à calculer avec précision la valeur centrale du cluster compense alors la limitation actuelle de l'algorithme FCM, qui est indûment restreinte par la valeur centrale initiale utilisée. De plus, l’algorithme proposé, qui inclut une analyse multispectrale, peut obtenir de meilleurs résultats de segmentation qu’une analyse spectrale unique.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Ock-Kyung YOON, Dong-Min KWAK, Bum-Soo KIM, Dong-Whee KIM, Kil-Houm PARK, "Automated Segmentation of MR Brain Images Using 3-Dimensional Clustering" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 4, pp. 773-781, April 2002, doi: .
Abstract: This paper proposed an automated segmentation algorithm for MR brain images through the complementary use of T1-weighted, T2-weighted, and PD images. The proposed segmentation algorithm is composed of 3 steps. The first step involves the extraction of cerebrum images by placing a cerebrum mask over the three input images. In the second step, outstanding clusters that represent the inner tissues of the cerebrum are chosen from among the 3-dimensional (3D) clusters. The 3D clusters are determined by intersecting densely distributed parts of a 2D histogram in 3D space formed using three optimal scale images. The optimal scale image results from applying scale-space filtering to each 2D histogram and a searching graph structure. As a result, the optimal scale image can accurately describe the shape of the densely distributed pixel parts in the 2D histogram. In the final step, the cerebrum images are segmented by the FCM (Fuzzy c-means) algorithm using the outstanding cluster center value as the initial center value. The ability of the proposed segmentation algorithm to calculate the cluster center value accurately then compensates for the current limitation of the FCM algorithm, which is unduly restricted by the initial center value used. In addition, the proposed algorithm, which includes a multi spectral analysis, can achieve better segmentation results than a single spectral analysis.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_4_773/_p
Copier
@ARTICLE{e85-d_4_773,
author={Ock-Kyung YOON, Dong-Min KWAK, Bum-Soo KIM, Dong-Whee KIM, Kil-Houm PARK, },
journal={IEICE TRANSACTIONS on Information},
title={Automated Segmentation of MR Brain Images Using 3-Dimensional Clustering},
year={2002},
volume={E85-D},
number={4},
pages={773-781},
abstract={This paper proposed an automated segmentation algorithm for MR brain images through the complementary use of T1-weighted, T2-weighted, and PD images. The proposed segmentation algorithm is composed of 3 steps. The first step involves the extraction of cerebrum images by placing a cerebrum mask over the three input images. In the second step, outstanding clusters that represent the inner tissues of the cerebrum are chosen from among the 3-dimensional (3D) clusters. The 3D clusters are determined by intersecting densely distributed parts of a 2D histogram in 3D space formed using three optimal scale images. The optimal scale image results from applying scale-space filtering to each 2D histogram and a searching graph structure. As a result, the optimal scale image can accurately describe the shape of the densely distributed pixel parts in the 2D histogram. In the final step, the cerebrum images are segmented by the FCM (Fuzzy c-means) algorithm using the outstanding cluster center value as the initial center value. The ability of the proposed segmentation algorithm to calculate the cluster center value accurately then compensates for the current limitation of the FCM algorithm, which is unduly restricted by the initial center value used. In addition, the proposed algorithm, which includes a multi spectral analysis, can achieve better segmentation results than a single spectral analysis.},
keywords={},
doi={},
ISSN={},
month={April},}
Copier
TY - JOUR
TI - Automated Segmentation of MR Brain Images Using 3-Dimensional Clustering
T2 - IEICE TRANSACTIONS on Information
SP - 773
EP - 781
AU - Ock-Kyung YOON
AU - Dong-Min KWAK
AU - Bum-Soo KIM
AU - Dong-Whee KIM
AU - Kil-Houm PARK
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2002
AB - This paper proposed an automated segmentation algorithm for MR brain images through the complementary use of T1-weighted, T2-weighted, and PD images. The proposed segmentation algorithm is composed of 3 steps. The first step involves the extraction of cerebrum images by placing a cerebrum mask over the three input images. In the second step, outstanding clusters that represent the inner tissues of the cerebrum are chosen from among the 3-dimensional (3D) clusters. The 3D clusters are determined by intersecting densely distributed parts of a 2D histogram in 3D space formed using three optimal scale images. The optimal scale image results from applying scale-space filtering to each 2D histogram and a searching graph structure. As a result, the optimal scale image can accurately describe the shape of the densely distributed pixel parts in the 2D histogram. In the final step, the cerebrum images are segmented by the FCM (Fuzzy c-means) algorithm using the outstanding cluster center value as the initial center value. The ability of the proposed segmentation algorithm to calculate the cluster center value accurately then compensates for the current limitation of the FCM algorithm, which is unduly restricted by the initial center value used. In addition, the proposed algorithm, which includes a multi spectral analysis, can achieve better segmentation results than a single spectral analysis.
ER -