Fig 3 - uploaded by Horst Bischof
Content may be subject to copyright.
Contrast CT dataset of the aorta containing a severe stenosis due to calcification. Top row (overview): volume rendering of the original dataset, CS of the proposed approach and Hassouna's approach. Bottom row (subregion around the stenosis): CS of the the proposed approach, Krissian's approach, Hassouna's approach, Bouix's approach, and Palagyi's approach (green: proposed approach; red: other approaches).
Source publication
The extraction of curve skeletons from tubular networks is a necessary prerequisite for virtual endoscopy applications. We
present an approach for curve skeleton extraction directly from gray value images that supersedes the need to deal with segmentations
and skeletonizations. The approach uses properties of the Gradient Vector Flow to derive a tu...
Contexts in source publication
Context 1
... three clinical datasets we used for evaluation show a bronchial tree (see Fig. 2), a contrast CT of an aorta containing a severe stenosis due to calcification (see Fig. 3), and a CT angiography image of the brain (see Fig. 4). High quality segmentations of the bronchial tree and the aorta were available; the segmentation of the aorta follows the interior of the aorta excluding the calcifications. For the CTA of the brain only a low quality segmentation based on thresholding was ...
Context 2
... the aorta dataset (see Fig. 3) the different methods show the major differ- ences at the junction with the stenotic area. Krissian's multi-scale tube detection filter was influenced by the calcification and thus the resulting centerline moved far away from the desired position. Our approach was able to extract a medial curve that stayed centered in proximity of the ...
Similar publications
This article proposes an architecture, which allows the prediction of intention by internally simulating perceptual states represented by action pattern vectors. To this end, associative self-organising neural networks (A-SOM) is utilised to build a hierarchical cognitive architecture for recognition and simulation of the skeleton based human actio...
A new approach for shape comparison based on skeleton matching is proposed. The skeleton of a binary image is encoded as a series of primitives (chain of primitives). Traditionally, a primitive is a pair of numbers, the first one is the length of the some edge and the second one is the angle between this and the neighbour edges. As a novelty we off...
Citations
... We emphasize that DDT has two advantages over vanilla segmentation networks: (1) It guides tubular structure segmentation by taking the geometric property of tubular structures into account. This reduces the difficulty to segment tubular structures from complex surrounding structures and ensures that the segmentation results have a proper shape prototype; (2) It predicts the crosssectional scales of a tubular structure as by-products, which are important for the further study of the tubular structure, such as clinical diagnosis and virtual endoscopy [7]. ...
... Bauer et al. proposed to recover a parametric model based on a tubular spine [5]. For digital data (generally segmented images), there are two main families of methods: methods based on the medial axis extraction, for which we can find a survey in [12] with implementations, and methods exploiting image gradient information [13], for instance the works of Hassouna et al. [14] or Bauer et al. [15] dedicated to virtual endoscopy. Unfortunately these methods are not adapted to deal with partially defined shapes (like partial scans, images with occlusions, etc), and this limitation is a serious drawback for numerous applications. ...
... To process volumetric discrete objects, Gradient Vector Flow [24] was exploited by Hassouna and Farag in order to propose a robust skeleton curve extraction [11]. This method was also adapted to process gray values volumetric images used in virtual endoscopy [5]. In the field of discrete geometry we can mention a method which propose to specifically exploit 3D discrete tools to extract some medial axis on grey-level images [4]. ...
This paper proposes a simple and efficient method for the reconstruction and extraction of geometric parameters from 3D tubular objects. Our method constructs an image that accumulates surface normal information, then peaks within this image are located by tracking. Finally, the positions of these are optimized to lie precisely on the tubular shape centerline. This method is very versatile, and is able to process various input data types like full or partial mesh acquired from 3D laser scans, 3D height map or discrete volumetric images. The proposed algorithm is simple to implement, contains few parameters and can be computed in linear time with respect to the number of surface faces. Since the extracted tube centerline is accurate, we are able to decompose the tube into rectilinear parts and torus-like parts. This is done with a new linear time 3D torus detection algorithm, which follows the same principle of a previous work on 2D arc circle recognition. Detailed experiments show the versatility, accuracy and robustness of our new method.
... They proposed an improved ridge traversal method based on a set of ridge criteria, and different methods for handling noise. Bauer and Bischof (2008) showed how this method could be used together with GVF. However, ridge traversal is not a data parallel algorithm and therefore not suited for GPU acceleration. ...
Segmentation of anatomical structures, from modalities like computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound, is a key enabling technology for medical applications such as diagnostics, planning and guidance. More efficient implementations are necessary, as most segmentation methods are computationally expensive, and the amount of medical imaging data is growing. The increased programmability of graphic processing units (GPUs) in recent years have enabled their use in several areas. GPUs can solve large data parallel problems at a higher speed than the traditional CPU, while being more affordable and energy efficient than distributed systems. Furthermore, using a GPU enables concurrent visualization and interactive segmentation, where the user can help the algorithm to achieve a satisfactory result. This review investigates the use of GPUs to accelerate medical image segmentation methods. A set of criteria for efficient use of GPUs are defined and each segmentation method is rated accordingly. In addition, references to relevant GPU implementations and insight into GPU optimization are provided and discussed. The review concludes that most segmentation methods may benefit from GPU processing due to the methods' data parallel structure and high thread count. However, factors such as synchronization, branch divergence and memory usage can limit the speedup.
... Bauer and Bischof [3] developed a novel approach to use the GVF as a replacement for the scale-space framework in Hessian based tube detection. Hassouna and Farag [10] and Bauer and Bischof [4] used the GVF to extract skeletons from objects. Ray and Acton [14] used GVF to track leukocytes from intravital video microscopy. ...
... If the Manhatten distance is even the voxel is red, and if it is odd the voxel is black. The first kernel, GaussSeidelRed, calculates the red voxels using Equation 4. Thus this kernel only works on half the voxels in the dataset. ...
Gradient vector flow (GVF) is a feature-preserving spatial diffusion of image gradients. It was introduced to overcome the limited capture range in traditional active contour segmentation. However, the original iterative solver for GVF, using Euler’s method, converges very slowly. Thus, many iterations are needed to achieve the desired capture range. Several groups have investigated the use of graphic processing units (GPUs) to accelerate the GVF computation. Still, this does not reduce the number of iterations needed. Multigrid methods, on the other hand, have been shown to provide a much better capture range using considerable less iterations. However, non-GPU implementations of the multigrid method are not as fast as the Euler method when executed on the GPU. In this paper, a novel GPU implementation of a multigrid solver for GVF written in OpenCL is presented. The results show that this implementation converges and provides a better capture range about 2–5 times faster than the conventional iterative GVF solver on the GPU.
... However, the response of the proposed TDF is invariant to the contrast due to the use of the normalized gradient V n in (5). Nevertheless, Bauer and Bischof [4] proposed a solution to this by adding a parameter F max for the maximum contrast. Any gradient with a magnitude above this parameter would be normalized and any below, divided by this parameter. ...
Tube detection filters (TDFs) are useful for segmentation and centerline extraction of tubular structures such as blood vessels and airways in medical images. Most TDFs assume that the cross-sectional profile of the tubular structure is circular. This assumption is not always correct, for instance in the case of abdominal aortic aneurysms (AAAs). Another problem with several TDFs is that they give a false response at strong edges. In this paper, a new TDF is proposed and compared to other TDFs on synthetic and clinical datasets. The results show that the proposed TDF is able to detect large non-circular tubular structures such as AAAs and avoid false positives.
... Aylward et al. [2] provides a review of different centerline extraction methods and proposed an improved ridge traversal algorithm based on a set of ridge criteria and different methods for handling noise. Bauer et al. [6] showed how this method could be used together with Gradient Vector Flow. For applications where only the centerline is needed, segmentation can be skipped using this method and thus reduce processing time. ...
... Centerline extraction from TDF results has primarily been done by ridge traversal [2,4,6,5]. One problem with the ridge traversal procedure is that it can't be run in parallel. ...
... vessels and airways), organs and modalities. Some examples are Bauer et al. [3][4][5][6][7][8], Krissian et al. [26], Aylward et al. [2], Benmansour et al. [10], Li et al. [30], Behrens et al. [9], Cohen et al. [12], Lorigo and Faugeras [33] and Spuhler et al. [44]. However, most of these present results only for a few datasets of one or two organs/modalities. ...
To create a fast and generic method with sufficient quality for extracting tubular structures such as blood vessels and airways from different modalities (CT, MR and US) and organs (brain, lungs and liver) by utilizing the computational power of graphic processing units (GPUs).
A cropping algorithm is used to remove unnecessary data from the datasets on the GPU. A model-based tube detection filter combined with a new parallel centerline extraction algorithm and a parallelized region growing segmentation algorithm is used to extract the tubular structures completely on the GPU. Accuracy of the proposed GPU method and centerline algorithm is compared with the ridge traversal and skeletonization/thinning methods using synthetic vascular datasets.
The implementation is tested on several datasets from three different modalities: airways from CT, blood vessels from MR, and 3D Doppler Ultrasound. The results show that the method is able to extract airways and vessels in 3-5 s on a modern GPU and is less sensitive to noise than other centerline extraction methods.
Tubular structures such as blood vessels and airways can be extracted from various organs imaged by different modalities in a matter of seconds, even for large datasets.
... Ray and Acton applied the GVF to track leukocytes from intravital video microsopy [24]. While Bauer et al. [4] applied the GVF to extract skeletons from gray value images for virtual endoscopy, Hassouna et al. [11] applied the GVF to compute continuous curve skeletons from generic volumetric objects. Bauer et al. [3] also proposed a novel approach to use the GVF as a replacement for the multi-scale gradient computation in the application of tubular object detection in medical images. ...
Multiple sequence alignment (MSA) is essential as an initial step in studying molecular phylogeny as well as during the identification of genomic rearrangements. Recent advances in sequencing techniques have led to a tremendous increase in the number of sequences to be analyzed. As a result, a greater demand is being placed on visualization techniques, as they have the potential to reveal the underlying information in large-scale MSAs. In this work, we present a novel visualization technique for conveying the patterns in large-scale MSAs. By applying gradient vector flow analysis to the MSA data, we can extract and visually emphasize conservations and other patterns that are relevant during the MSA exploration process. In contrast to the traditional visual representation of MSAs, which exploits color-coded tables, the proposed visual metaphor allows us to provide an overview of large MSAs as well as to highlight global patterns, outliers, and data distributions. We will motivate and describe the proposed algorithm, and further demonstrate its application to large-scale MSAs.
... It has been used as basis for a criterion similar to the Frangi's vesselness [27]. In [50,48], the local Jacobian of the GVF is used instead of the classical Hessian matrix to describe a mono scale, smoothed, vesselness measure. ...
This thesis addresses the segmentation and the tracking of thin curvilinear structures. The proposed methodology is applied to the delineation and the tracking of the guide-wires that are used during cardiac angioplasty. During these interventions, cardiologists assess the displacement of the different devices with a real-time fluoroscopic imaging system. The obtained images are very noisy and, as a result, guide-wires are particularly challenging to segment and track. The contributions of this thesis can be grouped into three parts. The first part is devoted to the detection of the guide-wires, the second part addresses their segmentation and the last part focuses on their spatio-temporal tracking. Partial detection of guide-wires is addressed either through the selection of appropriate filter operators or using modern machine learning methods. First, a learning framework using an asymmetric Boosting algorithm for training a guidewire detector is presented. A second method enhancing the output of a steerable filter by using an efficient tensor voting variant is then described. In the second part, a bottom-up method is proposed, that consists in grouping points selected by the wire detector, in extracting primitives from these aggregates and in linking these primitives together. Two local grouping procedures are investigated: one based on unsupervised graph-based clustering followed by a linesegment extraction and one based on a graphical model formulation followed by a graph-based centerline extraction. Subsequently, two variants of linking methods are investigated: one is based on integer programming and one on a local search heuristic. In the last part, registration methods are exploited for improving the segmentation via an image fusion method and then for tracking the wires. This latter is performed by a graph-based iconic tracking method coupled with a graphbased geometric tracking that encodes to certain extend a predictive model. This method uses a coupled graphical model that seeks both optimal position (segmentation) and spatio-temporal correspondences (tracking). The optimal solution of this graphical model simultaneously determines the guide-wire displacements and matches the landmarks that are extracted along it, what provides a robust estimation of the wire deformations with respect to large motion and noise.
... Fully automatic vessel extraction algorithms such as [37], [38] implicitly deal with branching. Interactive methods mostly do not handle branching, since user interaction is provided for every branch. ...
In this paper, we present a tubular structure segmentation method that utilizes a second order tensor constructed from directional intensity measurements, which is inspired from diffusion tensor image (DTI) modeling. The constructed anisotropic tensor which is fit inside a vessel drives the segmentation analogously to a tractography approach in DTI. Our model is initialized at a single seed point and is capable of capturing whole vessel trees by an automatic branch detection algorithm developed in the same framework. The centerline of the vessel as well as its thickness is extracted. Performance results within the Rotterdam Coronary Artery Algorithm Evaluation framework are provided for comparison with existing techniques. 96.4% average overlap with ground truth delineated by experts is obtained in addition to other measures reported in the paper. Moreover, we demonstrate further quantitative results over synthetic vascular datasets, and we provide quantitative experiments for branch detection on patient Computed Tomography Angiography (CTA) volumes, as well as qualitative evaluations on the same CTA datasets, from visual scores by a cardiologist expert.
