Showing papers in "Medical Image Analysis in 2007"

TL;DR: A new approach is proposed that uses measurements of vessel diameters and branching angles as a validation criterion to compare the authors' segmented images with those hand segmented from public databases, and demonstrated that borders found by the method are less biased and follow more consistently the border of the vessel and therefore they yield more confident geometric values.

TL;DR: In this paper, the automatic detection of microaneurysms in color fundus images, which plays a key role in computer assisted diagnosis of diabetic retinopathy, a serious and frequent eye disease.

TL;DR: An inverse finite element solution was developed using ANSYS finite element package to estimate the optimum values of viscoelastic and nonlinear hyperelastic material properties of pig liver through iterations and the initial estimates of the material properties for the iterations were extracted from the experimental data for faster convergence of the solutions.

TL;DR: It is concluded that fast and accurate predictions of the post-operative facial outcome are possible and the usage of a maxillofacial soft tissue prediction system is relevant and suitable for daily clinical practice.

TL;DR: An image processing approach is presented that extracts the vibrating vocal fold edges from digital high-speed movies and enables an objective and highly accurate description of vocal fold vibrations which is essential to realize extensive clinical studies which focus on the classification of voice disorders.

TL;DR: This work presents a new method based on the modified Radon transform that identifies the axis of instrument shafts as bright patterns in planar projections that is sufficient for real-time tracking at the 26 volumes per second rate of the ultrasound machine.

TL;DR: This paper proposes a novel method to construct a patient-specific three-dimensional model that provides an appropriate intra-operative visualization without the need for a pre or intra-operatively imaging.

TL;DR: This relatively simple inverse finite-element approach is investigated within the context of a series of phantom experiments, two in vivo cases, and a simulation study and preliminary results indicate that the approach recaptured on average 93% of surface shift for the simulation, phantom, and in vivo experiments.

TL;DR: Two new techniques are proposed (edge-based and clustering-based) to classify video frames into two classes, informative and non-informative frames, and it is suggested that precision, sensitivity, specificity, and accuracy for the specular reflection detection technique and the two informative frame classification techniques are greater than 90% and 95%, respectively.

TL;DR: An evaluation study over 10 clinical datasets indicate that the segmentations obtained by the proposed segmentation method favorably compares to other alternative techniques based on deformable models, namely parametric geodesic active regions and active contours without edges.

TL;DR: A method to detect and correct brain shift using pre-operative MR images and intraoperative Doppler ultrasound data and present its validation with both real and simulated data is designed and implemented.

TL;DR: A vascular reconstruction algorithm which combines automatic seeding and tracking of vessels with radius detection based on active contours and which satisfies the key requirements of automation of processing and sub-voxel accuracy.

TL;DR: This work uses the logarithm of the odds ratio (LogOdds) to place probabilistic atlases in a linear vector space and finds that the LogOdds approach better preserves shapes in a complex multiple object setting.

TL;DR: The present observations suggest that stiffness increase cannot be attributed to the tumoral tissue itself, but rather to the fibrotic stroma that often arise within or adjacent to the tumor.

TL;DR: A nonparametric Bayesian model is proposed for tissue classification of MR images of the brain, known as Dirichlet process mixture model, which uses Dirichlets process priors to overcome the limitations of current parametric finite mixture models.

TL;DR: A methodology for fully automated voxel-by-voxel classification of airways, fissures, nodules, and vessels from chest CT images using a single feature set and classification method is developed.

TL;DR: A vessel-based registration technique for correction of brain-shift using retrospective clinical data from five patients, showing that it can be completed in 30 s per dataset, and registrations can be performed in less than 30s, well suited for intra-operative use.

TL;DR: The registration methodology lends itself immediately to the construction of dynamic mesh models in which vessel wall motion is obtained directly using registration, and is shown to be 2-3 times more accurate than a standard published algorithm based on maximising normalised mutual information.

TL;DR: A novel method for vertebral fracture quantification from X-ray images that takes the full shape into account, it uses a patient-specific reference by combining population-based information on biological variation in vertebra shape and vertebra interrelations, and it provides a continuous measure of deformity.

TL;DR: A system for automatic segmentation and labeling of the complete rib cage in chest CT scans is presented and is very accurate for over 80% of all ribs, with slight errors otherwise.

TL;DR: A model for needle insertion and withdrawal can be used to generate a 1-DOF force versus position profile that can be experienced by a user operating a haptic device.

TL;DR: 3D bone volumes and that of their projections are measured and it is demonstrated that a simple projection provides 3D information about the bone structure, which can be a valuable adjunct to the bone mineral density for the early diagnosis of osteoporosis.

TL;DR: A new method of automatically correcting intensity inhomogeneities in magnetic resonance images using a nonparametric coarse to fine approach which allows bias fields to be modeled with different frequency ranges without user supervision is presented.

TL;DR: It is proposed that anisotropy creases provide a basis for extracting a skeleton of the major white matter pathways, in that ridges of anisOTropy coincide with interiors of fiber tracts, and valleys of an isotropic coincide with the interfaces between adjacent but distinctly oriented tracts.

TL;DR: In this paper, singular-value analysis is used to optimize experimental parameters relevant to the design and operation of emerging 360° fluorescence molecular tomography methods and systems for small animal imaging.

TL;DR: A new level-set based method to segment and quantify stenosed internal carotid arteries (ICAs) in 3D contrast-enhanced computed tomography angiography (CTA) and different kinds of plaques were almost completely excluded from the segmented regions.

TL;DR: A novel framework to segment vessels on their cross-sections that starts with a probabilistic vessel axis tracing in a gray-scale three-dimensional angiogram, followed by vessel boundary delineation on cross-section derived from the extracted axis to promote a more intuitive delineation of vessel boundaries.

TL;DR: This paper considers the automatic classification of textured tissues in 3D MRI and includes features extracted from the phase of the MR signal to improve texture discrimination in the bone segmentation.

TL;DR: This paper presents a new framework for shape modeling and analysis, rooted in the pattern recognition theory and based on artificial neural networks, which is reproducible, robust to noise, and capable of capturing real variations within and between groups of shapes.

TL;DR: A filtering method based on cosine functions that is more adapted than standard averaging techniques for DOI specifically and a new mode-locking technique to recover small signals and locate them temporally with high precision (shift method) are provided.