In this work, we present the use of Bayesian networks for radiologist decision support during clinical interpretation. This computational approach has the advantage of avoiding incorrect diagnoses that result from known human cognitive biases such as anchoring bias, framing effect, availability bias, and premature closure. To integrate Bayesian networks into clinical practice, we developed an open-source web application that provides diagnostic support for a variety of radiology disease entities (e.g., basal ganglia diseases, bone lesions). The Clinical tool presents the user with a set of buttons representing clinical and imaging features of interest. These buttons are used to set the value for each observed feature. As features are identified, the conditional probabilities for each possible diagnosis are updated in real time. Additionally, using sensitivity analysis, the interface may be set to inform the user which remaining imaging features provide maximum discriminatory information to choose the most likely diagnosis. The Case Submission tools allow the user to submit a validated case and the associated imaging features to a database, which can then be used for future tuning/testing of the Bayesian networks. These submitted cases are then reviewed by an assigned expert using the provided QC tool. The Research tool presents users with cases with previously labeled features and a chosen diagnosis, for the purpose of performance evaluation. Similarly, the Education page presents cases with known features, but provides real time feedback on feature selection.
The aim of this study was to examine the registration of diffusion tensor magnetic resonance images. A method for estimating a smooth, continuous mapping between two tensor images is presented. This method includes a tensor-to-tensor measure of similarity as well as a neighborhood similarity measure intended to preserve the relative position of adjacent structures. Additionally, tensor reorientation is integrated into the algorithm in order to insure that the structural information provided by the diffusion tensor is retained. This method was tested on a variety of synthetic data sets. Experiments indicate that the orientation similarity term plays an important role in both accuracy and speed. Additionally, an investigation of the effect of signal to noise ratio (SNR) was conducted to insure the usefulness of the methods at clinically obtainable values. Qualitative examination of the results obtained with this method suggest its potential usefulness in the examination of in vivo human data, but some extension of the method as well as further testing will be necessary to fully understand its limitations for use on clinical data.
The aim of this work was to develop a reliable semi-automatic method for quantifying carotid atherosclerotic lesion burden using black-blood high-resolution MR images. Vessel wall volume was quantified by measuring its cross-sectional area in adjacent slices. Two methods for obtaining this measure are presented. The first method approximates the outer boundary of the vessel on a slice-by-slice basis by fitting an ellipse to user-identified points and automatically identifying the lumen through examination of the histogram obtained from a local region of interest (ROI). The second, method identifies the lumen and wall throughout the entire volume based upon user-selected points in a single slice. Radially directed intensity profiles are examined in order to automatically locate points on the outer boundary, and the same histogram-based method is used for lumen delineation. The measure of wall area provided by the manual outer boundary selection has an intra-class correlation coefficient (ICC) of 0.83 for test-retest comparisons, but the ICC values for the inter-observer comparisons (0.84, 0.65) suggest that user bias remains a potential source of error. A susceptibility to low image signal-to-noise ratio (SNR) may present a limitation on the usefulness of the automated outer boundary selection method for use on whole image volumes.