The complexity of standard radiology terminologies such as RadLex makes them difficult to manage. Few specialized tools are available to help developers browse, visualize, and edit large taxonomies.
The complexity of standard radiology terminologies such as RadLex makes them difficult to manage. Few specialized tools are available to help developers browse, visualize, and edit large taxonomies.Researchers at Stanford University have created Protégé, an open-source solution that allows developers to create and manage terminologies and ontologies (J Digit Imaging 2007 Aug 9; [Epub ahead of print]). "RadLex was initially developed using word processors and spreadsheets, but it soon became evident that these tools were not suitable for distributing RadLex on the web or for making it accessible to applications," said Dr. Daniel L. Rubin, a clinical assistant professor of radiology at Stanford and scientific director of the National Center of Biomedical Ontology. RadLex is a program for development of a comprehensive radiology lexicon announced last November by University of Pennsylvania radiologist Dr. Curtis P. Langlotz (Radiographics 2006;26(6):1595-1597). It is available free through the RSNA. RadLex developers recently adopted Protégé for managing its terminology.Rubin said RadLex contains many attributes associated with each term, making it difficult to maintain this information in correct structured form as RadLex grows. A tool tailored to the needs of terminology development and dissemination in radiology was needed."RadLex meets the needs of the radiology community by providing standard terminology to describe all radiology information, and computer applications that use RadLex can help radiologists create better radiology reports, permit researchers to mine clinical databases, and enable the community to search for relevant case material," Rubin said.
Rubin said Protégé is of interest to three user groups:
There are more than 70,000 registered Protégé users employing the system to manage terminologies and ontologies in many different domains.
Since Protégé is open-source, Rubin expects that software developers will continue contributing specialized Protégé plug-ins specifically geared to radiology, as they have for other biomedical domains, thereby benefiting the entire radiology community.
For more online information, refer to Diagnostic Imaging's
PACSweb
section.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.