A versatile knowledge-based clinical imaging annotation system for breast cancer screening

Abstract

Medical information is evolving towards more complex multimedia data representation, as new imaging modalities are made available by sophisticated devices. Features such as segmented lesions can now be extracted through analysis techniques and need to be integrated into clinical patient data. The management of structured information extracted from multimedia has been addressed in knowledge based annotation systems providing methods to attach interpretative semantics to multimedia content. Building on these methods, we develop a new clinical imaging annotation system for computer aided breast cancer screening. The proposed system aims at more consistent, efficient and standardised data mark-up of digital and digitalised radiology images. The objective is to provide detailed characterisation of abnormalities as an aid in the diagnostic task through integrated annotation management. The system combines imaging analysis results and radiologist diagnostic information about suspicious findings by mapping well-established visual and low-level descriptors into pathology specific profiles. The versatile characterisation allows differentiating annotation descriptors for different types of findings. Our approach of semi-automatic integrated annotations supports increased quality assurance in screening practice. This is achieved through detailed and objective patient imaging information while providing user-friendly means for their manipulation that is oriented to relieving the radiologist's workload.

Towards Standardized Pen-Based Annotation of Breast Cancer Findings

“…This paper focuses on the design and the evaluation of the annotation tool; refer to [5] for more details about the semi-automatic lesion detection tool. A prototype for lesion annotation, based on semantic web technologies, was presented during SPIE Medical Imaging 2007 [4]. Our work goes further mainly by providing BC-experts with a new interaction style to characterize findings: the penbased annotation with a graphics tablet.…”

Towards an ontology for sharing medical images and regions of interest in neuroimaging

“…9) is exploited using the CORESE 10 search engine [22] which internally works on conceptual graphs. It implements RDF, RDFS 11 and some statements from OWL-Lite and the query pattern part of SPARQL 12 . The query language integrates additional features such as approximate search by computing semantic distance between concepts.…”

“…Such a verification may be automatically achieved by a file selector in order to filter only the datasets that meet these two conditions. The corresponding query Q 2 retrieves information about space variables (11)(12)(13)(14)(15)(16) through the Scalar Functions (3-5), which represent the Datasets concerning a subject (1-2), and the Intervals (8-10), which compose the domain (6-7) of the Scalar Function.…”

“…This third issue is fundamental for using imaging biomarkers consistently and relating observations of the same reality through several imaging modalities, and for exploring various aspects of brain structure and brain metabolism or function. The literature contains many relevant contributions [10][11][12], but is still incomplete.…”