Pulmonary vascular morphology as an imaging biomarker in chronic thromboembolic pulmonary hypertension.

Patients with chronic thromboembolic pulmonary hypertension (CTEPH) have morphologic changes to the pulmonary vasculature. These include pruning of the distal vessels, dilation of the proximal vessels, and increased vascular tortuosity. Advances in image processing and computer vision enable objective detection and quantification of these processes in clinically acquired computed tomographic (CT) scans. Three-dimensional reconstructions of the pulmonary vasculature were created from the CT angiograms of 18 patients with CTEPH diagnosed using imaging and hemodynamics as well as 15 control patients referred to our Dyspnea Clinic and found to have no evidence of pulmonary vascular disease. Compared to controls, CTEPH patients exhibited greater pruning of the distal vasculature (median density of small-vessel volume: 2.7 [interquartile range (IQR): 2.5-3.0] vs. 3.2 [3.0-3.8]; P = 0.008), greater dilation of proximal arteries (median fraction of blood in large arteries: 0.35 [IQR: 0.30-0.41] vs. 0.23 [0.21-0.31]; P = 0.0005), and increased tortuosity in the pulmonary arterial tree (median: 4.92% [IQR: 4.85%-5.21%] vs. 4.63% [4.39%-4.92%]; P = 0.004). CTEPH was not associated with dilation of proximal veins or increased tortuosity in the venous system. Distal pruning of the vasculature was correlated with the cardiac index (R = 0.51, P = 0.04). Quantitative models derived from CT scans can be used to measure changes in vascular morphology previously described subjectively in CTEPH. These measurements are also correlated with invasive metrics of pulmonary hemodynamics, suggesting that they may be used to assess disease severity. Further work in a larger cohort may enable the use of such measures as a biomarker for diagnostic, phenotyping, and prognostic purposes.

Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model.

A stochastic deformable model is proposed for the segmentation of the myocardium in Magnetic Resonance Imaging. The segmentation is posed as a probabilistic optimization problem in which the optimal time-dependent surface is obtained for the myocardium of the heart in a discrete space of locations built upon simple geometric assumptions. For this purpose, first, the left ventricle is detected by a set of image analysis tools gathered from the literature. Then, the segmentation solution is obtained by the Maximization of the Posterior Marginals for the myocardium location in a Markov Random Field framework which optimally integrates temporal-spatial smoothness with intensity and gradient related features in an unsupervised way by the Maximum Likelihood estimation of the parameters of the field. This scheme provides a flexible and robust segmentation method which has been able to generate results comparable to manually segmented images for some derived cardiac function parameters in a set of 43 patients affected in different degrees by an Acute Myocardial Infarction.

Probabilistic-driven oriented Speckle reducing anisotropic diffusion with application to cardiac ultrasonic images.

A novel anisotropic diffusion filter is proposed in this work with application to cardiac ultrasonic images. It includes probabilistic models which describe the probability density function (PDF) of tissues and adapts the diffusion tensor to the image iteratively. For this purpose, a preliminary study is performed in order to select the probability models that best fit the stastitical behavior of each tissue class in cardiac ultrasonic images. Then, the parameters of the diffusion tensor are defined taking into account the statistical properties of the image at each voxel. When the structure tensor of the probability of belonging to each tissue is included in the diffusion tensor definition, a better boundaries estimates can be obtained instead of calculating directly the boundaries from the image. This is the main contribution of this work. Additionally, the proposed method follows the statistical properties of the image in each iteration. This is considered as a second contribution since state-of-the-art methods suppose that noise or statistical properties of the image do not change during the filter process.