A medical image semantic modeling based on hierarchical Bayesian networks / 生物医学工程学杂志
Journal of Biomedical Engineering
;
(6): 400-404, 2009.
Article
in Chinese
| WPRIM
| ID: wpr-280191
ABSTRACT
A semantic modeling approach for medical image semantic retrieval based on hierarchical Bayesian networks was proposed, in allusion to characters of medical images. It used GMM (Gaussian mixture models) to map low-level image features into object semantics with probabilities, then it captured high-level semantics through fusing these object semantics using a Bayesian network, so that it built a multi-layer medical image semantic model, aiming to enable automatic image annotation and semantic retrieval by using various keywords at different semantic levels. As for the validity of this method, we have built a multi-level semantic model from a small set of astrocytoma MRI (magnetic resonance imaging) samples, in order to extract semantics of astrocytoma in malignant degree. Experiment results show that this is a superior approach.
Full text:
Available
Index:
WPRIM (Western Pacific)
Main subject:
Astrocytoma
/
Semantics
/
Image Processing, Computer-Assisted
/
Brain Neoplasms
/
Artificial Intelligence
/
Diagnostic Imaging
/
Magnetic Resonance Imaging
/
Image Interpretation, Computer-Assisted
/
Bayes Theorem
/
Diagnosis
Type of study:
Diagnostic study
/
Prognostic study
Limits:
Humans
Language:
Chinese
Journal:
Journal of Biomedical Engineering
Year:
2009
Type:
Article
Similar
MEDLINE
...
LILACS
LIS