No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Entities and relations in medical imaging: An analysis of computed tomography reporting
Abstract
Biomedical ontologies define entities and relations in order to represent knowledge in the biomedical domain. In addition, many ontologies further represent supplementary knowledge by linking terms from an external controlled vocabulary to the entities defined within the ontology itself. In this paper we concentrate on the domain of medical imaging, for which controlled vocabularies are emerging, but no ontology currently exists. We analyzed computed tomography reports in order to determine to which entities terms used in such reports refer and which relations are used with regard to the recently published Open Biomedical Ontologies (OBO) Relation Ontology. Our analysis revealed that the majority of entities referred to in radiological reporting practice are anatomical entities and anatomical coordinates. Based on the Open Biomedical Ontologies (OBO) Relation Ontology we provide a set of additional relations for the ontological structuring of image features such as shape, morphology, size and signal, frequently found in the reports. On the basis of these results we conclude that the construction of an imaging ontology may benefit greatly from already existing reference ontologies such as the Foundational Model of Anatomy (FMA), which represent those entities to which radiological reports most frequently refer.
... The reason for this is to reutilise existing medical background knowledge formalised in such ontologies as the FMA (Rosse and Mejino, 2007) and terminologies as RadLex (Langlotz, 2006) and ICD-10. Different studies, e.g., or Marwede and Fielding (2007), came to the conclusion that biomedical ontologies and terminologies are applicable for indexing medical knowledge such as CT scans of the brain or radiograph reports of the shoulder. Annotations of medical data are stored as instances of well-defined OWL classes. ...
Explanation-aware software design aims at making software systems smarter in interactions with their users. The long-term goal is to provide methods and tools for systematically engineering understandability into the respective (knowledge-based) software system. In this paper, we describe how we improved a semantic search engine, i.e., RadSem, regarding understandability. The research project MEDICO aims at developing an intelligent, robust and scalable semantic search engine for medical documents. RadSem is based on formal ontologies and designated for different kinds of users. Since semantic search results are often hard to understand, an explanation facility for justifying and exploring search results was integrated into RadSem employing the same ontologies used for searching also for explanation generation. We evaluated the understandability of selected concept labels in an experiment with different user groups using semantic networks as form of depicting explanations and using a class frequency approach for selecting appropriate labels.
Biomedical software ontologies provide a means for the representation of facts gathered through biomedical research and clinical observation. At the foundation of good software ontology design lays a sound philosophical realism that supplies the basic framework required to support the computable management of this information correctly and consistently. In numerous biomedical subdomains (such as anatomy, disease classification, or functional genomics), a good degree of success has been achieved through the realist approach. In the field of psychiatry, however, the analytic tools of ontological realism are challenged to account for subjective mental experiences that typically lay beyond their scope. Although psychiatric symptoms, such as delusions, hallucinations, or memory loss, may be too ethereal to account for in terms of a realist ontology, by focusing on some psychiatric signs, such as images of the human brain (which are in themselves subject to ontological analysis), we may be able to make some in-roads toward an application ontology of the psychiatric domain. In this paper, via the ontological framework of Polish phenomenologist Roman Ingarden, we discuss the differences between the ontology of the body and the ontology of the image, and apply the subsequent image-ontology framework to the domain of neuroimaging. We aim to demonstrate how such an ontology may lead to the perspicuous structuring of clinical information in psychiatry and the benefits application ontologies afford may subsequently be attained within a portion of this particularly difficult domain.
MEDICO aims to develop an intelligent, robust, and scalable semantic search engine for medical images. The search engine of
the MEDICO demonstrator RadSem is based on formal ontologies and designated for different kinds of users such as medical doctors
or patients. An explanation facility integrated into RadSem justifies search results by showing a connection between query
and result. The constructed explanations are depicted as semantic networks containing various medical concepts and labels.
This paper addresses the tailoring of justifications to different kinds of users regarding such quality aspects as understandability
or amount of information. A user experiment shows that under certain conditions the quality of justifications can be pre-estimated
by considering the usage frequency of medical terms in natural language.
Biomedical ontologies define entities and relations in order to represent knowledge in the biomedical domain. In this paper we concentrate on the domain of medical imaging. In previous work, we analyzed a representative sample of computed tomography reports in order to determine to which entities and relations the terms used in such reports refer (with regard to the Foundational Model of Anatomy (FMA) and the recently published Open Biomedical Ontology (OBO) Relation Ontology, respectively) in order to construct an imaging ontology for electronic reporting in radiology. In this paper we expand the role of two OBO relations in particular, as they may be applied to radiological image information: the relations located_in and adjacent_to. Defining these relations in terms of the basic topological relations of Region Connection Calculus (RCC), we show how the qualitative description of image feature locations in radiological reporting may be formalized for reasoning.
In this presentation we survey preliminary results from the Interdisciplinary Prostate Ontology Project (IPOP), in which ontologies from the Open Biomedical Ontologies (OBO) library have been used to annotate clinical reports about prostate cancer. First we discuss why we rejected several controlled vocabularies, including SNOMED, DICOM, and RadLex, preferring instead to use the OBO library. We then briefly describe the database-backed website we have created around the relevant OBO ontologies, and provide excerpts of reports from radiology, surgery, and pathology which we have hyperlinked to the ontology terms. This method allows us to discover which relevant terms exist in the OBO library, and which do not. The final section of this paper discusses these gaps in the OBO library and considers methods of filling them.
The structural and informational content of clinical radiology reports was examined to develop a comprehensive representational schema of the concepts in the domain. The model involves several different conceptual levels, ranging from the high level description of the report to the lower level description of the clinical concepts contained in the reports and the specification of the terms used to express the concepts. The design of an adequate structured representation for the domain has important implications for the design of the electronic patient record, for the unification of different controlled vocabularies by enabling them to be mapped to one common representation, and for the facilitation of natural language processing of clinical reports so that coded data may be obtained.
this paper we present in detail the mechanisms used to represent part-whole relations in the OpenGALEN Common Reference Model of medicine 1 . We compare our approach with specific mechanisms used by others in the medical and conceptual modelling communities. (Comparison with formal mereology 2 and lexical semantics 3 are beyond the scope of this paper.) Relevant Features Of The Grail Description Logic The GRAIL description logic formalism and the issues in its design are described in detail elsewhere 4,5 . However, certain features of the formalism are specifically relevant to representing part-whole relations. These are summarised here: . Semantic links (`attributes') can be declared as transitive, e.g. to represent formally that `parts of parts of a whole' are `parts of the whole'
The Foundational Model of Anatomy (FMA), initially developed as an enhancement of the anatomical content of UMLS, is a domain ontology of the concepts and relationships that pertain to the structural organization of the human body. It encompasses the material objects from the molecular to the macroscopic levels that constitute the body and associates with them non-material entities (spaces, surfaces, lines, and points) required for describing structural relationships. The disciplined modeling approach employed for the development of the FMA relies on a set of declared principles, high level schemes, Aristotelian definitions and a frame-based authoring environment. We propose the FMA as a reference ontology in biomedical informatics for correlating different views of anatomy, aligning existing and emerging ontologies in bioinformatics ontologies and providing a structure-based template for representing biological functions.
Medical assessment of penetrating injuries is a difficult and knowledge-intensive task, and rapid determination of the extent of internal injuries is vital for triage and for determining the appropriate treatment. Physical examination and computed tomographic (CT) imaging data must be combined with detailed anatomic, physiologic, and biomechanical knowledge to assess the injured subject. We are developing a methodology to automate reasoning about penetrating injuries using canonical knowledge combined with specific subject image data.
In our approach, we build a three-dimensional geometric model of a subject from segmented images. We link regions in this model to entities in two knowledge sources: (1) a comprehensive ontology of anatomy containing organ identities, adjacencies, and other information useful for anatomic reasoning and (2) an ontology of regional perfusion containing formal definitions of arterial anatomy and corresponding regions of perfusion. We created computer reasoning services ("problem solvers") that use the ontologies to evaluate the geometric model of the subject and deduce the consequences of penetrating injuries.
We developed and tested our methods using data from the Visible Human. Our problem solvers can determine the organs that are injured given particular trajectories of projectiles, whether vital structures--such as a coronary artery--are injured, and they can predict the propagation of injury ensuing after vital structures are injured.
We have demonstrated the capability of using ontologies with medical images to support computer reasoning about injury based on those images. Our methodology demonstrates an approach to creating intelligent computer applications that reason with image data, and it may have value in helping practitioners in the assessment of penetrating injury.