Radiology
-
Radiological reporting has generated large quantities of digital content within the electronic health record, which is potentially a valuable source of information for improving clinical care and supporting research. Although radiology reports are stored for communication and documentation of diagnostic imaging, harnessing their potential requires efficient and automated information extraction: they exist mainly as free-text clinical narrative, from which it is a major challenge to obtain structured data. Natural language processing (NLP) provides techniques that aid the conversion of text into a structured representation, and thus enables computers to derive meaning from human (ie, natural language) input. ⋯ A systematic literature search identified 67 relevant publications describing NLP methods that support practical applications in radiology. This review takes a close look at the individual studies in terms of tasks (ie, the extracted information), the NLP methodology and tools used, and their application purpose and performance results. Additionally, limitations, future challenges, and requirements for advancing NLP in radiology will be discussed.
-
The use of computed tomography (CT) for hemodynamically stable victims of penetrating torso trauma continues to increase but remains less singular to the work-up than in blunt trauma. Research in this area has focused on the incremental benefits of CT within the context of evolving diagnostic algorithms and in conjunction with techniques such as laparoscopy, endoscopy, and angiographic intervention. This review centers on the current state of multidetector CT as a triage tool for penetrating torso trauma and the primacy of trajectory evaluation in diagnosis, while emphasizing diagnostic challenges that have lingered despite tremendous technological advances since CT was first used in this setting 3 decades ago. As treatment strategies have also changed considerably over the years in parallel with advances in CT, current management implications of organ-specific injuries depicted at multidetector CT are also discussed.
-
Hypertrophic cardiomyopathy ( HCM hypertrophic cardiomyopathy ), the most common genetically transmitted cardiac disorder, has been the focus of extensive research over the past 50 years. HCM hypertrophic cardiomyopathy is a multifaceted disease with highly heterogeneous genetic background, phenotypic expression, clinical presentation, and long-term outcome. Though most patients have an indolent course with a life expectancy comparable to that of the general population, early diagnosis and accurate risk profiling are essential to identify the sizeable subset at increased risk of sudden cardiac death or disease progression and heart failure-related complications, requiring aggressive management options. ⋯ Moreover, MR is key in differentiating HCM hypertrophic cardiomyopathy from "phenocopies"-that is, hearts with similar morphology but profoundly different etiology, such as amyloid or Anderson-Fabry disease. Long term, the incremental information provided by MR is relevant to planning of septal reduction therapies, identification of the early stages of end-stage progression, and stratification of arrhythmic risk. The aim of this review is to depict the increasingly important role of MR imaging in relation to the complexity of HCM hypertrophic cardiomyopathy , highlighting its role in clinical decision making.