Segmentation of whole body bone SPECT image based on BP neural network / 生物医学工程学杂志
Journal of Biomedical Engineering
;
(6): 1050-1053, 2007.
Article
Dans Chinois
| WPRIM
| ID: wpr-346013
ABSTRACT
In this paper, BP neural network is used to segment whole body bone SPECT image so that the lesion area can be recognized automatically. For the uncertain characteristics of SPECT images, it is hard to achieve good segmentation result if only the BP neural network is employed. Therefore, the segmentation process is divided into three steps:
first, the optimal gray threshold segmentation method is employed for preprocessing, then BP neural network is used to roughly identify the lesions, and finally template match method and symmetry-removing program are adopted to delete the wrongly recognized areas.
Texte intégral:
Disponible
Indice:
WPRIM (Pacifique occidental)
Sujet Principal:
Os et tissu osseux
/
Algorithmes
/
Reconnaissance automatique des formes
/
Imagerie diagnostique
/
Interprétation d'images assistée par ordinateur
/
Tomographie par émission monophotonique
/
/
Imagerie du corps entier
/
Méthodes
Type d'étude:
Etude diagnostique
/
Étude pronostique
Limites du sujet:
Humains
langue:
Chinois
Texte intégral:
Journal of Biomedical Engineering
Année:
2007
Type:
Article
Documents relatifs à ce sujet
MEDLINE
...
LILACS
LIS