Cemil Kirbas

A review of vessel extraction techniques and algorithms

Vessel segmentation algorithms are the critical components of circulatory blood vessel analysis systems. We present a survey of vessel extraction techniques and algorithms. We put the various vessel extraction approaches and techniques in perspective by means of a classification of the existing research. While we have mainly targeted the extraction of blood vessels, neurosvascular structure in particular, we have also reviewed some of the segmentation methods for the tubular objects that show similar characteristics to vessels. We have divided vessel segmentation algorithms and techniques into six main categories: (1) pattern recognition techniques, (2) model-based approaches, (3) tracking-based approaches, (4) artificial intelligence-based approaches, (5) neural network-based approaches, and (6) tube-like object detection approaches. Some of these categories are further divided into subcategories. We have also created tables to compare the papers in each category against such criteria as dimensionality, input type, preprocessing, user interaction, and result type.

Vessel extraction techniques and algorithms: a survey

Vessel segmentation algorithms are critical components of circulatory blood vessel analysis systems. We present a survey of vessel extraction techniques and algorithms, putting the various approaches and techniques in perspective by means of a classification of the existing research. While we target mainly the extraction of blood vessels, neurovascular structure in particular we also review some of the segmentation methods for the tubular objects that show similar characteristics to vessels. We divide vessel segmentation algorithms and techniques into six main categories: (1) pattern recognition techniques, (2) model-based approaches, (3) tracking-based approaches, (4) artificial intelligence-based approaches, (5) neural network-based approaches, and (6) miscellaneous tube-like object detection approaches. Some of these categories are further divided into sub-categories. A table compares the papers against such criteria as dimensionality, input type, preprocessing, user interaction, and result type.

Surface parameterization in volumetric images for curvature-based feature classification

Curvature-based surface features are well suited for use in multimodal medical image registration. The accuracy of such feature-based registration techniques is dependent upon the reliability of the feature computation. The computation of curvature features requires second derivative information that is best obtained from a parametric surface representation. We present a method of explicitly parameterizing surfaces from volumetric data. Surfaces are extracted, without a global thresholding, using active contour models. A monge/spl acute/ basis for each surface patch is estimated and used to transform the patch into local, or parametric, coordinates. Surface patches are fit to a bicubic polynomial in local coordinates using least squares solved by singular value decomposition. We tested our method by reconstructing surfaces from the surface model and analytically computing Gaussian and mean curvatures. The model was tested on analytical and medical data.

A Multimedia System for Temporally Situated Perceptual Psycholinguistic Analysis

Perceptual analysis of video (analysis by unaided ear and eye) plays an important role in such disciplines as psychology, psycholinguistics, linguistics, anthropology, and neurology. In the specific domain of psycholinguistic analysis of gesture and speech, researchers micro-analyze videos of subjects using a high quality video cassette recorder that has a digital freeze capability down to the specific frame. Such analyses are very labor intensive and slow. We present a multimedia system for perceptual analysis of video data using a multiple, dynamically linked representation model. The system components are linked through a time portal with a current time focus. The system provides mechanisms to analyze overlapping hierarchical interpretations of the discourse, and integrates visual gesture analysis, speech analysis, video gaze analysis, and text transcription into a coordinated whole. The various interaction components facilitate accurate multi-point access to the data. While this system is currently used to analyze gesture, speech and gaze in human discourse, the system described may be applied to any other field where careful analysis of temporal synchronies in video is important.

AIM: attentionally based interaction model for the interpretation of vascular angiography

We propose a model to interpret neurovascular X-ray angiogram (XRA) images interactively. This attentionally based interactive model (AIM) exploits human interaction as part of the solution. AIM posits two channels of interaction: context (what to look for) and focus-of-attention (where to look) as the locus of spatial information exchange between the user and the machine. In an AIM system, the user specifies a context (e.g., a carotid vessel) and directs the attentional spotlight to focus machine processing. AIM involves the user with the computer as integral partners and facilitates varying degrees of human intervention in the process. A hierarchy of context abstractions permits the system to function more autonomously (doing high-level tasks like extracting an arterial vessel) in routine interpretation and to require more user intervention (e.g., locating arterial wall boundaries) as the image complexity increases. This is especially important in medical imaging where the medical professional must have ultimate control and confidence in the system. Such technology can have a significant impact on the design of radiological systems.

Functional MRI mapping of visual function and selective attention for performance assessment and presurgical planning using conjunctive visual search

Accurate mapping of visual function and selective attention using fMRI is important in the study of human performance as well as in presurgical treatment planning of lesions in or near visual centers of the brain. Conjunctive visual search (CVS) is a useful tool for mapping visual function during fMRI because of its greater activation extent compared with high‐capacity parallel search processes.

3d wave propagation and traceback in vascular extraction

Presents an approach for the extraction of vasculature from a volume of magnetic resonance angiography (MRA) images by using a 3D wave propagation and traceback mechanism. The method employs a dual-sigmoid filter to label each voxel in the MRA image volume with the likelihood that it is within a vessel. Resulting likelihood image is modeled as a medium, represented as an array of refractive indices, through which a wave may be propagated. Starting from the base of the vasculature, the digital wave propagates through the medium and extracts the vascular tree while washing over the local noise perturbations.

Evaluation of a Clinical fMRI Cueing System Utilizing Complex Scene and Auditory Stimuli for Neurosurgical Treatment Planning of Patients with Cognitive and Physical Deficits

Purpose: The adoption of functional MRI for presurgical planning in neuro-oncology has been limited by the high degree of patient compliance required to generate accurate activation maps. The purpose of this work was to evaluate the brain activation properties and patient head motion associated with a presurgical fMRI cueing system utilizing complex scene and auditory commands to enhance compliance in patients with cognitive and physical deficits. Materials and Methods: An fMRI cueing system which delivered simultaneous audio and video task instructions was compared to a simple visual cueing system across 10 healthy volunteers, each performing two different motor tasks (40 total fMRI acquisitions). Statistical differences between the complex and simple cueing systems were evaluated using a mixed effects modeling method which was able to carry up variances from the individual analyses to the group analysis. Differences in relative head motion between the systems were evaluated using a paired t-test. Results: Both cueing systems demonstrated typical somatotopic activity distributions in the pre- and postcentral gyrus of the left hemisphere. No significant differences were found between the systems in target brain regions. Furthermore, relative head motion using the complex system was found to not differ statistically from the simple method. Conclusion: The fMRI cueing system using complex scene stimuli produced results comparable to a simple cueing system in target regions of the brain. In patients presenting with deficits that lead to noncompliance with fMRI procedures, the use of complex scene stimuli may provide a good alternative to conventional cueing methods.

Comparison of bicubic and Bezier polynomials for surface parameterization in volumetric images

Curvature-based surface features are well suited for use in multimodal medical image registration. The accuracy of such feature-based registration techniques is dependent upon the reliability of the feature computation. The computation of curvature features requires second derivative information that is best obtained from a parametric surface representation. We present a method of explicitly parameterizing surfaces from volumetric data. Surfaces are extracted, without a global thresholding, using active contour models. A Mong basis for each surface patch is estimated and used to transform the patch into local, or parametric, coordinates. Surface patches are fit to first a bicubic polynomial and second to a Bezier polynomial. The bicubic polynomial is fit in local coordinates using least squares solved by singular value decomposition. Bezier polynomial is fit using de Casteljau algorithm. We tested our method by reconstructing surfaces from the surface model and analytically computing Gaussian and mean curvatures. The model was tested on analytical and medical data and the results of both methods are compared.