Integration of a Research CBIR System with RIS and PACS for Radiological Routine

In this work, a concept for coupling a system for content-based image retrieval in medical applications (IRMA) with hospital information systems is presented. We aim at improving the work flow of radiologists and evaluating the recognition performance of the IRMA system in clinical routine. The integration is designed such that a failure of IRMA does not affect the routine operation of the other systems. The coupling is realized by generic communication modules with the radiology information system, and the picture archiving and communication system (PACS) over the standard protocols Digital Imaging and Communications in Medicine (DICOM) and Health Layer 7 (HL7). An optional plug-in for the radiological viewing station further enhances the usability. Based on this concept, the pre-fetching of relevant images for recurrent examinations is improved. When an examination is scheduled, all previous images of the patient are read by the IRMA system with DICOM query/retrieve. If the images were not present before in our database, features are extracted, stored, and indexed. After the acquisition of new images from the imaging modality, the new images are automatically retrieved by the IRMA system with DICOM query/retrieve and similar images are selected based on the stored global signatures. These images are then loaded into the online storage of the PACS and are available for diagnostic purposes together with those images already pre-selected by the PACS. Thus the radiologist can avoid further delays resulting from manually fetching further images from archives which have not been automatically selected by alphanumerical meta data. In addition, he is able to sort all fetched images by the computed IRMA-similarity. Furthermore, the hanging of images in the viewing software is planned to be organized by IRMA suggestions automatically, further shortening the time for the examination and reducing manual interactions. Based on the generality of our integration concept, a CBIR-based second opinion to support the diagnostics, and computer-based training of radiologists will be established in near future.