Share Email Print
cover

Proceedings Paper

Object-based modeling, identification, and labeling of medical images for content-based retrieval by querying on intervals of attribute values
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The classification and measuring of objects in medical images is important in radiological diagnostics and education, especially when using large databases as knowledge resources, for instance a picture archiving and communication system (PACS). The main challenge is the modeling of medical knowledge and the diagnostic context to label the sought objects. This task is referred to as closing the semantic gap between low-level pixel information and high level application knowledge. This work describes an approach which allows labeling of a-priori unknown objects in an intuitive way. Our approach consists of four main components. At first an image is completely decomposed into all visually relevant partitions on different scales. This provides a hierarchical organized set of regions. Afterwards, for each of the obtained regions a set of descriptive features is computed. In this data structure objects are represented by regions with characteristic attributes. The actual object identification is the formulation of a query. It consists of attributes on which intervals are defined describing those regions that correspond to the sought objects. Since the objects are a-priori unknown, they are described by a medical expert by means of an intuitive graphical user interface (GUI). This GUI is the fourth component. It enables complex object definitions by browsing the data structure and examinating the attributes to formulate the query. The query is executed and if the sought objects have not been identified its parameterization is refined. By using this heuristic approach, object models for hand radiographs have been developed to extract bones from a single hand in different anatomical contexts. This demonstrates the applicability of the labeling concept. By using a rule for metacarpal bones on a series of 105 images, this type of bone could be retrieved with a precision of 0.53 % and a recall of 0.6%.

Paper Details

Date Published: 15 April 2005
PDF: 10 pages
Proc. SPIE 5748, Medical Imaging 2005: PACS and Imaging Informatics, (15 April 2005); doi: 10.1117/12.596001
Show Author Affiliations
Christian Thies, RWTH-Aachen (Germany)
Tamara Ostwald, RWTH-Aachen (Germany)
Benedikt Fischer, RWTH-Aachen (Germany)
Thomas Martin Lehmann, RWTH-Aachen (Germany)


Published in SPIE Proceedings Vol. 5748:
Medical Imaging 2005: PACS and Imaging Informatics
Osman M. Ratib; Steven C. Horii, Editor(s)

© SPIE. Terms of Use
Back to Top