Deep-learning for automated detection of MSU deposits on DECT: evaluating impact on efficiency and reader confidence

Active contour segmentation and its robust implementation using level set methods are well-established theoretical approaches that have been studied thoroughly in the image analysis literature. Despite the existence of these powerful segmentation methods, the needs of clinical research continue to be fulfilled, to a large extent, using slice-by-slice manual tracing. To bridge the gap between methodological advances and clinical routine, we developed an open source application called ITK-SNAP, which is intended to make level set segmentation easily accessible to a wide range of users, including those with little or no mathematical expertise. This paper describes the methods and software engineering philosophy behind this new tool and provides the results of validation experiments performed in the context of an ongoing child autism neuroimaging study. The validation establishes SNAP intrarater and interrater reliability and overlap error statistics for the caudate nucleus and finds that SNAP is a highly reliable and efficient alternative to manual tracing. Analogous results for lateral ventricle segmentation are provided. Show more

Objective Existing criteria for the classification of gout have suboptimal sensitivity and/or specificity, and were developed at a time when advanced imaging was not available. The current effort was undertaken to develop new classification criteria for gout. Methods An international group of investigators, supported by the American College of Rheumatology and the European League Against Rheumatism, conducted a systematic review of the literature on advanced imaging of gout, a diagnostic study in which the presence of monosodium urate monohydrate (MSU) crystals in synovial fluid or tophus was the gold standard, a ranking exercise of paper patient cases, and a multi-criterion decision analysis exercise. These data formed the basis for developing the classification criteria, which were tested in an independent data set. Results The entry criterion for the new classification criteria requires the occurrence of at least one episode of peripheral joint or bursal swelling, pain, or tenderness. The presence of MSU crystals in a symptomatic joint/bursa (ie, synovial fluid) or in a tophus is a sufficient criterion for classification of the subject as having gout, and does not require further scoring. The domains of the new classification criteria include clinical (pattern of joint/bursa involvement, characteristics and time course of symptomatic episodes), laboratory (serum urate, MSU-negative synovial fluid aspirate), and imaging (double-contour sign on ultrasound or urate on dual-energy CT, radiographic gout-related erosion). The sensitivity and specificity of the criteria are high (92% and 89%, respectively). Conclusions The new classification criteria, developed using a data-driven and decision-analytic approach, have excellent performance characteristics and incorporate current state-of-the-art evidence regarding gout. Show more

Bias is a form of systematic error that can affect scientific investigations and distort the measurement process. A biased study loses validity in relation to the degree of the bias. While some study designs are more prone to bias, its presence is universal. It is difficult or even impossible to completely eliminate bias. In the process of attempting to do so, new bias may be introduced or a study may be rendered less generalizable. Therefore, the goals are to minimize bias and for both investigators and readers to comprehend its residual effects, limiting misinterpretation and misuse of data. Numerous forms of bias have been described, and the terminology can be confusing, overlapping, and specific to a medical specialty. Much of the terminology is drawn from the epidemiology literature and may not be common parlance for radiologists. In this review, various types of bias are discussed, with emphasis on the radiology literature, and common study designs in which bias occurs are presented. Copyright RSNA, 2006. Show more