MR and CT angiography in the diagnosis of vasculitides.

Vasculitides represent the wide-ranging series of complex inflammatory diseases that involve inflammation of blood vessel walls. These conditions are characterized according to the caliber of the predominantly involved vessels. The work-up of vasculitides often includes imaging to narrow a differential diagnosis and guide management. Findings from CT and MR angiography in conjunction with a thorough history and physical exam are of utmost importance in making an accurate diagnosis. Further, imaging can be used for follow-up, in order to monitor disease progression and response to treatment. This wide-ranging literature review serves as the primary resource for clinicians looking to diagnose and monitor the progression of rare vascular inflammatory conditions. This article provides a comprehensive summary of the main findings on imaging related to each of these vasculitides. For each of the named vasculitis conditions, a thorough overview of the diagnostic modalities and their respective findings is described. Many specific hallmarks of pathology are included in this review article.

Automated classification of radiology reports to facilitate retrospective study in radiology.

Retrospective research is an import tool in radiology. Identifying imaging examinations appropriate for a given research question from the unstructured radiology reports is extremely useful, but labor-intensive. Using the machine learning text-mining methods implemented in LingPipe [1], we evaluated the performance of the dynamic language model (DLM) and the Naïve Bayesian (NB) classifiers in classifying radiology reports to facilitate identification of radiological examinations for research projects. The training dataset consisted of 14,325 sentences from 11,432 radiology reports randomly selected from a database of 5,104,594 reports in all disciplines of radiology. The training sentences were categorized manually into six categories (Positive, Differential, Post Treatment, Negative, Normal, and History). A 10-fold cross-validation [2] was used to evaluate the performance of the models, which were tested in classification of radiology reports for cases of sellar or suprasellar masses and colloid cysts. The average accuracies for the DLM and NB classifiers were 88.5% with 95% confidence interval (CI) of 1.9% and 85.9% with 95% CI of 2.0%, respectively. The DLM performed slightly better and was used to classify 1,397 radiology reports containing the keywords "sellar or suprasellar mass", or "colloid cyst". The DLM model produced an accuracy of 88.2% with 95% CI of 2.1% for 959 reports that contain "sellar or suprasellar mass" and an accuracy of 86.3% with 95% CI of 2.5% for 437 reports of "colloid cyst". We conclude that automated classification of radiology reports using machine learning techniques can effectively facilitate the identification of cases suitable for retrospective research.