Abstract
The purpose of the research herein presented is the automatic delimitation of lung fields in posterior-anterior digital chest radiographs. In a computer-aided diagnosis system the precise location of the lungs is important as it allows the reduction of the re-ion under analysis, decreasing the computation time and facilitating data compression. Furthermore, it allows the delimitation of the search area, easing the selective tuning of the abnormalities detection algorithms. The results produced by the automatic method were validated by comparison with manual contours traced by experienced radiologists. Two programs with friendly interfaces were developed for this purpose.

Abstract

Abstract
A 3-D data acquisition and scene segmentation system is described. For 3-D data acquisition a structured light technique based on the ratio of two intensity images is used. This technique avoids the correspondence problem, that appears in other structured light techniques, and allows the acquisition of dense range images. The calibration steps of the system are described. Measurement results with different scenes are presented and system accuracy is evaluated. Taking into account that this system allows the acquisition of a dense range image and an intensity image, registered with it, a new approach to the segmentation of 3-D scenes using both range and intensity information is proposed. The two images are segmented separately and iteratively. At each iteration, the segmentation results are combined. The segmentation proceeds until all segments are planar or no more splits are possible. A two-step merging procedure follows: first, planar surfaces that may have been split are "reconstructed", by merging adjacent planar regions that satisfy some constraints; then, regions belonging to curved surfaces are identified and merged, using a curvature analysis along line segments delimited by edge points, combined from both images. Finally, the resulting surfaces are described, using adequate functions. © 1996 IEEE.

Abstract
This paper proposes a new approach for the segmentation of both near-end and far-end intima-media regions of the common carotid artery in ultrasound images. The method requires minimal user interaction and is able to segment the near-end wall in arteries with large, hypoechogenic and irregular plaques, issues usually not considered previously due to the increased segmentation difficulty. The adventitia is detected by searching for the best fit of a cubic spline to edges having features compatible with the adventitia boundary. The algorithm uses a global smoothness constraint and integrates discriminating features of the adventitia to reduce the attraction by other edges. Afterwards, using the information of the adventitia location, the lumen boundary is detected by combining dynamic programming, smooth intensity thresholding surfaces and geometric snakes. Smooth contours that correctly adapt to the intima are produced, even in the presence of deep concavities. Moreover, unlike balloon-based snakes, the propagation force does not depend on gradients and does not require a predefined direction. An extensive statistical evaluation is computed, using a set of 47 images from 24 different symptomatic patients, including several classes, sizes and shapes of plaques. Bland-Altman plots of the mean intima-media thickness, for manual segmentations of two medical experts, show a high intra-observer and inter-observer agreement, with mean differences close to zero (mean between -0.10 mm and 0.18 mm) and with the large majority of differences within the limits of agreement (standard deviation between 0.10 mm and 0.12 mm). Similar Plots reveal it good agreement between the automatic and the manual segmentations (mean between -0.07 mm and 0.11 mm and standard deviation between 0.11 mm and 0.12 mm).

Abstract
A new algorithm is proposed for the semi-automatic segmentation of the near-end and the far-end adventitia boundary of the common carotid artery in ultrasound images. It uses the random sample consensus method to estimate the most significant cubic splines fitting the edge map of a longitudinal section. The consensus of the geometric model (a spline) is evaluated through a new gain function, which integrates the responses to different discriminating features of the carotid boundary: the proximity of the geometric model to any edge or to valley shaped edges; the consistency between the orientation of the normal to the geometric model and the intensity gradient; and the distance to a rough estimate of the lumen boundary. A set of 50 longitudinal B-mode images of the common carotid and their manual segmentations performed by two medical experts were used to assess the performance of the method. The image set was taken from 25 different subjects, most of them having plaques of different classes (class II to class IV), sizes and shapes. The quantitative evaluation showed promising results, having detection errors similar to the ones observed in manual segmentations for 95% of the far-end boundaries and 73% of the near-end boundaries.

Abstract
This paper presents a new method for the automatic segmentation of the common carotid artery in B-mode images. This method uses the instantaneous coefficient of variation edge detector, fuzzy classification of edges and dynamic programming. Several discriminating features of the intima and adventitia boundaries are considered, like the edge strength, the intensity gradient orientation, the valley shaped intensity profile and contextual information of the region delimited by those boundaries. The adopted fuzzy classification of edges helps avoiding low-pass filtering. The method is suited to real-time processing and user interaction is not required. Both the near and far wall boundaries can be detected in arteries with plaques of different types and sizes. Both expert manual and automatic tracings are significantly better for the far wall, due to the better visibility of the intima and adventitia boundaries. The automatic detection of the far wall shows an accuracy similar to the manual detections. For this wall, the error coefficient of variation for the mean intima-media thickness is in the range [5.6, 6.6 %] for automatic detections and in [6.7, 7.1 %] for manual ones. In the case of the near wall, the same coefficient of variation is in [11.2, 13.0 %] for automatic detections and in [5.9, 9.0 %] for manual detections. The mean intima-media thickness measurement errors observed for the far wall ([0.15; 0.17] mm, [1.7; 1.9] pixel) are among the best values reported for other fully automatic approaches. The application of this approach in clinical practice is encouraged by the results for the far wall and the short processing time (mean of 2.1 s per image).