Content-based retrieval in picture archiving and communication systems

Abstract

A COntent-Based Retrieval Architecture [COBRA) for picture archiving and communication systems (PACS) is introduced. COBRA improves the diagnosis, research, and training capabilities of PACS systems by adding retrieval by content features to those systems.COBRA is an open architecture based on widely used health care and technology standards. In addition to regular PACS components, COBRA includes additional components to handle representation, storage, and content-based similarity retrieval. Within COBRA, an anatomy ciassification algorithm is introduced to automatically classify PACS studies based on their anatomy. Such a classification allows the use of different segmentation and image-processing algorithms for different anatomies. COBRA uses primitive retrieval criteria such as color, texture, shape, and more complex criteria including object-based spatial relations and regions of interest. A prototype content-based retrieval system for MR brain images was developed to illustrate the concepts introduced in COBRA. Copyright 9 2000 by W.B. Saunders CompanyKEY WORDS: content-based image retrieval, medical image databases, medical information system, picture archiving and communication systems, information retrieval.

Challenges of medical image processing

“…CBIR-PACS integration has also been addressed in recent research [15,46,61]. However, CBIR-based methods are still unavailable in today's radiological routine.…”

Automatic categorization of medical images for content-based retrieval and data mining

“…The ImageEngine [12] is primarily a text-based information retrieval system but first experiments produced interesting results in combination with some basic components of computer vision. Both, I 2 C [13] and COBRA [14] characterize the images based on global features only. In I 2 C, these features are calculated from the complete image and in COBRA, they are extracted from an automatically segmented image region.…”

X-ray image retrieval system based on visual feature discrimination

“…Therefore, mining useful information from these databases needs efficient retrieval tool. Recently, Content Based Image Retrieval (CBIR) emerged as useful technique for medical diagnosis application, and number of medical CBIR systems such as KMeD [2], COBRA [3] , medGIFT [4], IRMA [5] have been developed in order to improve the accuracy of the medical diagnosis. CBIR consists in retrieving images based on the relevance of their visual content.…”