Automatic Multilevel Medical Image Annotation and Retrieval

Abstract

Image retrieval at the semantic level mostly depends on image annotation or image classification. Image annotation performance largely depends on three issues: (1) automatic image feature extraction; (2) a semantic image concept modeling; (3) algorithm for semantic image annotation. To address first issue, multilevel features are extracted to construct the feature vector, which represents the contents of the image. To address second issue, domain-dependent concept hierarchy is constructed for interpretation of image semantic concepts. To address third issue, automatic multilevel code generation is proposed for image classification and multilevel image annotation. We make use of the existing image annotation to address second and third issues. Our experiments on a specific domain of X-ray images have given encouraging results.

Automatic medical image annotation and keyword-based image retrieval using relevance feedback

“…First, to measure the annotation performance, we compare the proposed classification method with the widely used MSVM [4][5][6] with the same local WCS-LBP by estimating the error rate and error count. The error rate means the percentage of codes that have at least one error in one position within one axis (T, D, A, B).…”

“…Mueen et al [5] proposed a multilevel automatic medical image annotation and retrieval via keywords method based on concept hierarchy or class hierarchy. To address the semantic annotation, SVM-based approach by support vectors at different semantic level is used.…”

“…However, automatic keyword annotation considering semantic concept of medical images is a difficult work. To overcome the limitations of manual annotation and provide semantic keywords to medical images, some recent researches [3][4][5] have proposed automatic keyword annotation based on image classification.…”

ImageCLEF 2014: Overview and Analysis of the Results

“…The first group uses global features and the second group employs local features. Mueen et al [18] have implemented the annotation using three-hierarchy-level SVM classification on X-ray images. Devrim et al [33] used two approaches to automatically annotate X-ray images.…”

Application of Color Change Feature in Gastroscopic Image Retrieval

“…To apply content-based image retrieval (CBIR) method to different medical image becomes a heated topic in image retrieval field [1][2][3]. Because of medical image's inherent characteristic, the retrieval methods in CBIR can not be simply repotted in content-based medical image retrieval (CBMIR).…”