A medical image semantic modeling based on hierarchical Bayesian networks.
- Author:
Chunyi LIN
1
;
Lihong MA
;
Junxun YIN
;
Jianyu CHEN
Author Information
1. Department of Biomedical Engineering, Sun Yat-sen University, Guangzhou 510080, China.
- Publication Type:Journal Article
- MeSH:
Artificial Intelligence;
Astrocytoma;
diagnosis;
Bayes Theorem;
Brain Neoplasms;
diagnosis;
Diagnostic Imaging;
methods;
Humans;
Image Interpretation, Computer-Assisted;
methods;
Image Processing, Computer-Assisted;
methods;
Magnetic Resonance Imaging;
Models, Theoretical;
Semantics
- From:
Journal of Biomedical Engineering
2009;26(2):400-404
- CountryChina
- Language:Chinese
-
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.
