Article Preview
Top1. Introduction
In the last decade, a large number of digital medical images have been produced in hospitals. Such digital medical images include X-ray, computed tomography (CT), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), magnetic resonance spectroscopy (MRS), magnetic source imaging (MSI), digital subtraction angiography (DSA), positron emission tomography (PET), ultrasound (US), nuclear medical imaging, endoscopy, microscopy, scanning laser ophtalmoscopy (SLO), and so on. These medical images are stored in large-scale image databases and can facilitate medical doctors, professionals, researchers, and medical college students to compare the current patients and the previous cases, and provide valuable information for their studies. Due to the increasing use of digital medical images, there is a need to develop advanced information retrieval techniques. Among various information retrieval techniques, automatic image annotation is considered as a prerequisite task for image database management (Hersh, 2009). Automatic annotation can provide textual labels for images and thus added labels can be used to access images using textual queries, thereby improving the effectiveness of browsing and searching of large medical image databases.
Automatic image annotation has been a hot topic in the areas of multimedia, information retrieval, and machine learning. To correspond to this trend, this paper presents an image annotation scheme, which includes mammographic feature extraction and an approach to do automatic mammogram annotation. The rest of this paper is organized as follows: Section 2 reviews methods of visual feature extraction and automatic image annotation in the medical domain. Section 3 provides a set of features for describing calcification lesions in mammogram. Section 4 proposes a probabilistic SVM approach to image classification. The experimental results are presented and discussed in Section 5. Finally, the conclusion is made in Section 6.