Search

Techniques for unsupervised segmentation of multimodal grayscale images are proposed, such that each region-of-interest relates to a single dominant mode of the empirical marginal probability distribution of grey levels. Experiments show that the developed techniques segment different types of complex multimodal medical images more accurately than other known algorithms.

A new algorithm for segmenting a multimodal grey-scale image is proposed. The image is described as a sample of a joint Gibbs random field of region labels and grey levels. To initialize the model, a mixed multimodal empirical grey-level distribution is approximated with linear combinations of Gaussians, one combination per region. Bayesian decisions involving expectation maximization and genetic optimization techniques are used to sequentially estimate and refine parameters of the model, including the number of Gaussians for each region. The final estimates are more accurate than with conventional normal mixture models and result in more adequate region borders in the image. Experiments show that the proposed technique segments complex multimodal medical images of different types more accurately than several other known algorithms.

A novel framework for the classification of acute rejection versus nonrejection status of renal transplants from 2-D dynamic contrast-enhanced magnetic resonance imaging is proposed. The framework consists of four steps. First, kidney objects are segmented from adjacent structures with a level set deformable boundary guided by a stochastic speed function that accounts for a fourth-order Markov–Gibbs random field model of the kidney/background shape and appearance. Second, a Laplace-based nonrigid registration approach is used to account for local deformations caused by physiological effects. Namely, the target kidney object is deformed over closed, equispaced contours (iso-contours) to closely match the reference object. Next, the cortex is segmented as it is the functional kidney unit that is most affected by rejection. To characterize rejection, perfusion is estimated from contrast agent kinetics using empirical indexes, namely, the transient phase indexes (peak signal intensity, time-to-peak, and initial up-slope), and a steady-phase index defined as the average signal change during the slowly varying tissue phase of agent transit. We used a k_n-nearest neighbor classifier to distinguish between acute rejection and nonrejection. Performance of our method was evaluated using the receiver operating characteristics (ROC). Experimental results in 50 subjects, using a combinatoric k_n-classifier, correctly classified 92% of training subjects, 100% of the test subjects, and yielded an area under the ROC curve that approached the ideal value. Our proposed framework thus holds promise as a reliable noninvasive diagnostic tool. [ABSTRACT FROM AUTHOR]

Accurate automatic extraction of a 3-D cerebrovascular system from images obtained by time-of-flight (TOF) or phase contrast (PC) magnetic resonance angiography (MRA) is a challenging segmentation problem due to the small size objects of interest (blood vessels) in each 2-D MRA slice and complex surrounding anatomical structures (e.g., fat, bones, or gray and white brain matter). We show that due to the multimodal nature of MRA data, blood vessels can be accurately separated from the background in each slice using a voxel-wise classification based on precisely identified probability models of voxel intensities. To identify the models, an empirical marginal probability distribution of intensities is closely approximated with a linear combination of discrete Gaussians (LCDG) with alternate signs, using our previous EM-based techniques for precise linear combination of Gaussian-approximation adapted to deal with the LCDGs. The high accuracy of the proposed approach is experimentally validated on 85 real MRA datasets (50 TOF and 35 PC) as well as on synthetic MRA data for special 3-D geometrical phantoms of known shapes.

Acquisition of noncontrast agent cine cardiac magnetic resonance (CMR) gated images through the cardiac cycle is, at present, a well-established part of examining cardiac global function. However, regional quantification is less well established. We propose a new automated framework for analyzing the wall thickness and thickening function on these images that consists of three main steps. First, inner and outer wall borders are segmented from their surrounding tissues with a geometric deformable model guided by a special stochastic speed relationship. The latter accounts for Markov-Gibbs shape and appearance models of the object-of-interest and its background. In the second step, point-to-point correspondences between the inner and outer borders are found by solving the Laplace equation and provide initial estimates of the local wall thickness and the thickening function index. Finally, the effects of the segmentation error is reduced and a continuity analysis of the LV wall thickening is performed through iterative energy minimization using a generalized Gauss-Markov random field (GGMRF) image model. The framework was evaluated on 26 datasets from clinical cine CMR images that have been collected from patients with eleven independent studies, with chronic ischemic heart disease and heart damage. The performance evaluation of the proposed segmentation approach, based on the receiver operating characteristic (ROC) and Dice similarity coefficients (DSC) between manually drawn and automatically segmented contours, confirmed a high robustness and accuracy of the proposed segmentation approach. Furthermore, the Bland-Altman plot is used to assess the limit of agreement of our measurements of the global function parameters compared to the ground truth. Importantly, comparative results on the publicly available database (MICCAI 2009 Cardiac MR Left Ventricle Segmentation) demonstrated a superior performance of the proposed segmentation approach over published methods., (© 2011 IEEE)