Design of a Medical Image Database with Content-Based Retrieval Capabilities
This paper presents the architecture of an image administration system that supports the medical practice in tasks such as teaching, diagnosis and telemedicine. The proposed system has a multi-tier, web-based architecture and supports content-based retrie
- PDF / 434,719 Bytes
- 13 Pages / 430 x 660 pts Page_size
- 35 Downloads / 156 Views
Abstract. This paper presents the architecture of an image administration system that supports the medical practice in tasks such as teaching, diagnosis and telemedicine. The proposed system has a multi-tier, web-based architecture and supports content-based retrieval. The paper discusses the design aspects of the system as well as the proposed contentbased retrieval approach. The system was tested with real pathology images to evaluate its performance, reaching a precision rate of 67%. The detailed results are presented and discussed. Keywords: content-based image retrieval, medical imaging, image databases.
1
Introduction
Nowadays medical environments generate a large number of digital images to support clinical decisions, the Geneve University Hospital reported a production rate of 12.000 daily images during 2,002 [1]. The problem of archiving those medical image collections have been addressed with different solutions such as PACS1 [2,3] or modular and specialized systems for image databases [4,5]. Effectiveness of those systems may be critical in clinical practice [6] since they are responsible for storing medical images in a dependable way. Besides, these systems must allow users to efficiently access this information. Traditional medical image database systems store images as a complementary data of textual information, providing the most basic and common operations on images: transfer and visualization. Usually, these systems are restricted to query a database only through keywords, but this kind of queries limit information access, since it does not exploit the intrinsec nature of medical images. On the other hand, a medical image database system must have a flexible architecture along with a wide variety of functionalities supporting clinical, academic and research tasks [7]. Medical users must count on a set of automated and efficient tools, which permits efficient access to relevant information. A recent approach to medical image database management is the retrieval of information by content, named Content-Based Image Retrieval (CBIR)[1]. This 1
Picture Archiving and Comunication Systems.
D. Mery and L. Rueda (Eds.): PSIVT 2007, LNCS 4872, pp. 919–931, 2007. c Springer-Verlag Berlin Heidelberg 2007
920
J.C. Caicedo et al.
kind of systems allow evaluation of new clinical cases so that when similar cases are required, the system is able to retrieve comparable information for supporting diagnoses in the decision making process. Several systems have been developed following this approach such as ASSERT [8], IRMA [9], FIRE [10] among others [11,12,13]. The main idea of this kind of systems is to achieve adequate support to physicians in reaching their medical goals [7]. This paper presents the design, implementation and evaluation of an image database system for the Telemedicine Centre at the National University of Colombia. Physicians asociated to the Telemedicine Centre have attended to cases in dermathology, pathology and radiology, related to general and tropical diseases in remote places since 2,002.
Data Loading...
