Purpose: Collecting and analyzing findings constitute the basis of medical activity. Computer assisted medical activity raises the problem of modelling findings. We propose a unified representation of findings integrating the representations of findings in the GAMUTS in Radiology [M.M. Reeder, B. Felson, GAMUTS in radiology Comprehensive lists of roentgen differential diagnosis, fourth ed., 2003], the Unified Medical Language System (UMLS), and the Digital Imaging and Communication in Medicine Structured Report (DICOM-SR).
Materials And Methods: Starting from a corpus of findings in bone and joint radiology [M.M. Reeder, B. Felson, GAMUTS in Radiology comprehensive lists of roentgen differential diagnosis, fourth ed., 2003] (3481 words), an automated mapping to the UMLS was performed with the Metamap Program. The resulting UMLS terms and Semantic Types were analyzed in order to find a generic template in accordance with DICOM-SR structure.
Results: UMLS Concepts were missing for 45% of the GAMUTS findings. Three kinds of regularities were observed in the way the Semantic Types were combined: "pathological findings", "physiological findings" and "anatomical findings". A generic and original DICOM-SR template modelling finding was proposed. It was evaluated for representing GAMUTS jaws findings. 21% missing terms had to be picked up from Radlex (5%) or created (16%).
Discussion-conclusion: This article shows that it is possible to represent findings using the UMLS and the DICOM SR formalism with a semi-automated method. The Metamap program helped to find a model to represent the semantic structure of free texts with standardized terms (UMLS Concepts). Nevertheless, the coverage of the UMLS is not comprehensive. This study shows that the UMLS should include more technical concepts and more concepts regarding findings, signs and symptoms to be suitable for radiology representation. The semi-automated translation of the whole GAMUTS using the UMLS concepts and the DICOM SR relations could help to create or supplement the DCMR Templates and Context Groups pertaining to the description of imaging findings.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.ijmedinf.2007.11.003 | DOI Listing |
AJNR Am J Neuroradiol
October 2024
From the Department of Radiology (S.A., T.C.G.), Indiana University School of Medicine, Indianapolis, IN, USA; Department of Surgery (K.K.), University of California, Los Angeles David Geffen School of Medicine, Los Angeles, CA, USA; Department of Neurological Surgery (D.M.M., R.J.A., A.S., T.K., S.P.P.), University of Chicago Pritzker School of Medicine, Chicago, IL, USA; Department of Radiology (T.J.C., M.C.H.), The University of Chicago, Chicago, IL, USA.
Traditional guidance for intracranial aneurysm (IA) management is dichotomized by rupture status. Fundamental to ruptured aneurysm management is the detection and treatment of subarachnoid hemorrhage, along with securing the aneurysm by the safest technique. On the other hand, unruptured aneurysms first require a careful assessment of natural history versus treatment risk, including an imaging assessment of aneurysm size, location, and morphology, along with additional evidence-based risk factors such as smoking, hypertension, and family history.
View Article and Find Full Text PDFIbrain
May 2024
Institute for Bioengineering of Catalunya (IBEC) The Barcelona Institute of Science and Technology (BIST), Barcelona (Spain), Carrer Baldiri I Reixac Barcelona Spain.
J Imaging Inform Med
September 2024
Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3400 Spruce Street, Philadelphia, 19104, PA, USA.
Natural language processing (NLP) is crucial to extract information accurately from unstructured text to provide insights for clinical decision-making, quality improvement, and medical research. This study compared the performance of a rule-based NLP system and a medical-domain transformer-based model to detect negated concepts in radiology reports. Using a corpus of 984 de-identified radiology reports from a large U.
View Article and Find Full Text PDFRadiographics
July 2024
From the Department of Radiology, Beth Israel Deaconess Medical Center, 330 Brookline Ave, Boston, MA 02215.
Cognitive biases are systematic thought processes involving the use of a filter of personal experiences and preferences arising from the tendency of the human brain to simplify information processing, especially when taking in vast amounts of data such as from imaging studies. These biases encompass a wide spectrum of thought processes and frequently overlap in their concepts, with multiple biases usually in operation when interpretive and perceptual errors occur in radiology. The authors review the gamut of cognitive biases that occur in radiology.
View Article and Find Full Text PDFNeurol India
March 2024
Department of Plastic, Reconstructive and Burns Surgery, All India Institute of Medical Sciences, New Delhi, India.
Background: Currently, clinical assessment is the main tool for the evaluation of brachial plexus injury, complemented by electrophysiologic studies (EPS), and imaging studies whenever available. Imaging plays an important role as it enables the differentiation of pre-ganglionic and postganglionic injuries, and adds objectivity to presurgical evaluation.
Objectives: The primary objective was to evaluate the utility of magnetic resonance imaging (MRI) and high-resolution ultrasonography (USG) in the localization and characterization of brachial plexus injury in infants.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!