Managing Biomedical Image Metadata for Search and Retrieval of Similar Images

Abstract

Radiology images are generally disconnected from the metadata describing their contents, such as imaging observations ("semantic" metadata), which are usually described in text reports that are not directly linked to the images. We developed a system, the Biomedical Image Metadata Manager (BIMM) to (1) address the problem of managing biomedical image metadata and (2) facilitate the retrieval of similar images using semantic feature metadata. Our approach allows radiologists, researchers, and students to take advantage of the vast and growing repositories of medical image data by explicitly linking images to their associated metadata in a relational database that is globally accessible through a Web application. BIMM receives input in the form of standard-based metadata files using Web service and parses and stores the metadata in a relational database allowing efficient data query and maintenance capabilities. Upon querying BIMM for images, 2D regions of interest (ROIs) stored as metadata are automatically rendered onto preview images included in search results. The system's "match observations" function retrieves images with similar ROIs based on specific semantic features describing imaging observation characteristics (IOCs). We demonstrate that the system, using IOCs alone, can accurately retrieve images with diagnoses matching the query images, and we evaluate its performance on a set of annotated liver lesion images. BIMM has several potential applications, e.g., computer-aided detection and diagnosis, content-based image retrieval, automating medical analysis protocols, and gathering population statistics like disease prevalences. The system provides a framework for decision support systems, potentially improving their diagnostic accuracy and selection of appropriate therapies.

On combining image-based and ontological semantic dissimilarities for medical image retrieval applications

“…We used 72 CT images of liver lesions (with one lesion per targeted image) in the portal venous phase acquired from 44 patients, including six types of lesion diagnoses (Table 1) that were used in a previous research study (Korenblum et al, 2011). These types of lesions are common and span a range of visual appearances in CT. Scans were acquired during the time period February 2007 and August 2008 and used the following range of parameters: 120 kVp, 140–400 mAs, and 5 mm slice thickness.…”

A hierarchical knowledge-based approach for retrieving similar medical images described with semantic annotations

“…Consequently, it leads to different possible descriptions for a same image, thwarting good performance of CBIR systems based purely on semantic image descriptions. To deal with this issue, recent works in the semantic domain [27] used controlled vocabularies for annotating the images. A controlled vocabulary provides a set of pre-defined terms with definitions that can facilitate the annotation of large sets of images since it provides standard terms for describing the features in images.…”

Efficient similarity search on 3D bounding box annotations

“…4, the electronic representation of a liver lesion is derived from exact 2D segmentation annotations of the lesion's center slice, and it is focused rather on semantic ROI features than on automatically-generated image features, as elaborated in Ref. 12. A recent extension using only automatic image features still requires the exact segmentation of the lesion as it specifically targets the lesion's shape.…”