We present an interactive visual analytics framework, GazeDx (abbr. of GazeDiagnosis), for the comparative analysis of gaze data from multiple readers examining volumetric images while integrating important contextual information with the gaze data. Gaze pattern comparison is essential to understanding how radiologists examine medical images, and to identifying factors influencing the examination. Most prior work depended upon comparisons with manually juxtaposed static images of gaze tracking results. Comparative gaze analysis with volumetric images is more challenging due to the additional cognitive load on 3D perception. A recent study proposed a visualization design based on direct volume rendering (DVR) for visualizing gaze patterns in volumetric images; however, effective and comprehensive gaze pattern comparison is still challenging due to a lack of interactive visualization tools for comparative gaze analysis. We take the challenge with GazeDx while integrating crucial contextual information such as pupil size and windowing into the analysis process for more in-depth and ecologically valid findings. Among the interactive visualization components in GazeDx, a context-embedded interactive scatterplot is especially designed to help users examine abstract gaze data in diverse contexts by embedding medical imaging representations well known to radiologists in it. We present the results from two case studies with two experienced radiologists, where they compared the gaze patterns of 14 radiologists reading two patients' volumetric CT images.

This study aimed to evaluate three image fidelity metrics of different computational principles--peak signal-to-noise ratio (PSNR), high-dynamic range visual difference predictor (HDR-VDP), and multiscale structural similarity (MS-SSIM)--in measuring the fidelity of JPEG2000 compressed abdomen computed tomography images from a viewpoint of visually lossless compression. Three hundred images with 0.67- or 5-mm section thickness were compressed to one of five compression ratios ranging from reversible compression to 15:1. The fidelity of each compressed image was measured by five radiologists' visual analyses (distinguishable or indistinguishable from the original) and the three metrics. The Spearman rank correlation coefficients of the PSNR, HDR-VDP, and MS-SSIM values with the number of readers responding as indistinguishable were 0.86, 0.94, and 0.86, respectively. Using the pooled readers' responses as the reference standard, the area under the receiver-operating-characteristic curve for the HDR-VDP (0.99) was significantly greater than that for the PSNR (0.95) (p < 0.001) and for the MS-SSIM (0.96) (p = 0.003), and there was no significant difference between the PSNR and MS-SSIM (p = 0.70). In measuring the image fidelity, the HDR-VDP outperforms the PSNR and MS-SSIM, and the MS-SSIM and PSNR are comparable.

In this paper, we propose a fully automatic method to segment bone compartments in magnetic resonance (MR) images of knee joints gathered from a public database for research on knee osteoarthritis (OA), the osteoarthritis initiative (OAI). Considering the fixed scanning parameters which include position and flexion of the knee joint, the proposed method efficiently utilizes both shape and intensity priors obtained from pre-segmented data, and iteratively applies branch-and-mincut to a local subset of configurations of shape templates. More specifically, at each iteration, the optimal among a subset of the whole range in translation, rotation, and scale parameters are decomposed and separately computed, and motion is greedily selected by the lowest energy. Experimental results demonstrate the increased accuracy and efficiency compared to when only shape priors are applied and when branch-and-mincut is applied to the whole range of parameters at once, respectively.

This paper presents an efficient feature-based nonrigid registration method for multiphase liver CT volumes. While radiologists routinely examine multiphase liver CT to detect hepatic diseases, they usually search corresponding points between 3D CT volumes by visual inspections using 2D slice images. As the liver is a deformable organ, there exist complex nonrigid transformations between liver CT volumes obtained at difference time points (phases). We introduce a fully automatic registration application for multiphase liver CT volumes. For two given liver CT volumes, we extract 3D features with their descriptors, and estimate correspondences by finding nearest neighbor in descriptor space. An energy function is constructed using the correspondence information and the smoothness measure of free-form deformation model based on B-splines. We integrate an approximated smoothness energy function and a robust correspondence energy estimator controlled by the confidence radius of the matching distance in this energy model. The energy function is optimized by sequentially reducing the confidence radius, and outlier correspondences are discarded systematically during convergence. We propose a highly efficient optimization procedure using the preconditioned nonlinear conjugate gradient method. In the experiments, we will provide quantitative and qualitative results on synthetic and clinical data sets. 1