Generalized pixel profiling and comparative segmentation with application to arteriovenous malformation segmentation

Babin, Danilo; Pižurica, Aleksandra; Bellens, Rik; Bock, Jasper De; Shang, Yanfeng; Goossens, Bart; Vansteenkiste, Ewout; Philips, Wilfried

doi:10.1016/j.media.2012.02.006

Cited by 21 publications

(29 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some cases, pixel inhomogeneities are highly present in veins proximate to the AVM, which can lead to higher over-estimation of the volume (case 2 in Table 1). This can be solved by extracting the vein region from the AVM based on vessel radii [6].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Skeleton calculation for automatic extraction of arteriovenous malformation in 3-D CTA images

Babin

Spyrantis

Pižurica

et al. 2014

2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Cerebral arteriovenous malformation (AVM) presents a great health threat due to its high probability of rupture which can cause severe brain damage or even death. For planing of embolization procedure of an AVM, the accurate knowledge of the location and size of the malformation is of utmost importance. We propose in this paper a novel AVM delineation approach using ordered thinning-based skeletonization. The main contribution is a new method for creating the graph-type skeleton from the result of the ordered skeletonization, and an automatic method for AVM detection and extraction. The main idea in our work is to use the structural (anatomical) vessel differences and the inhomogeneities in distribution of pixel gray values to locate and extract the AVM. The algorithm takes the segmentation result as an input to perform AVM delineation. It determines the AVM region automatically, without any user interaction, independently of the used segmentation algorithm. The proposed approach is validated on brain blood vessel CTA images before and after embolization. The results obtained using the Dice coefficient comparisons, the volume relative error and the AVM center position show high accuracy of our method and indicate potentials for use in surgical planning.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Model-based AVM nidus extraction was recently proposed in [5]. In our earlier work on AVM delineation [6] we used multi-scale segmentation approach in combination with vessel radii-based ordered skeletonization.…”

Section: Introductionmentioning

confidence: 99%

Skeleton calculation for automatic extraction of arteriovenous malformation in 3-D CTA images

Babin

Spyrantis

Pižurica

et al. 2014

2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

show abstract

“…Some approaches use the pixel intensity distribution inhomogeneity in the AVM imaging. Pixel profiling in images is one of the most promising techniques for automatic segmentation of blood vessels and AVMs . A blood vessel tree analysis approach using ordered thinning‐based skeletonization for automatic detection of AVMs in CTA has also been investigated and successfully applied for planning of embolization procedures .…”

Section: Computational Modelsmentioning

confidence: 99%

“…Pixel profiling in images is one of the most promising techniques for automatic segmentation of blood vessels and AVMs. 21 A blood vessel tree analysis approach using ordered thinning-based skeletonization for automatic detection of AVMs in CTA has also been investigated and successfully applied for planning of embolization procedures. 22 In a similar way, high-resolution 3-and 4-dimensional flow MRIs have been used for automatic nidus segmentation by means of a voxel-wise support vector machine (SVM) and fuzzy-logic, offering a reproducible and fast extraction of the nidus for therapy planning.…”

Section: Computational Modelsmentioning

confidence: 99%

Computational Analyses of Arteriovenous Malformations in Neuroimaging

Ieva

Boukadoum

Lahmiri

et al. 2014

Journal of Neuroimaging

View full text Add to dashboard Cite

Computational models have been investigated for the analysis of the physiopathology and morphology of arteriovenous malformation (AVM) in recent years. Special emphasis has been given to image fusion in multimodal imaging and 3-dimensional rendering of the AVM, with the aim to improve the visualization of the lesion (for diagnostic purposes) and the selection of the nidus (for therapeutic aims, like the selection of the region of interest for the gamma knife radiosurgery plan). Searching for new diagnostic and prognostic neuroimaging biomarkers, fractal-based computational models have been proposed for describing and quantifying the angioarchitecture of the nidus. Computational modeling in the AVM field offers promising tools of analysis and requires a strict collaboration among neurosurgeons, neuroradiologists, clinicians, computer scientists, and engineers. We present here some updated state-of-the-art exemplary cases in the field, focusing on recent neuroimaging computational modeling with clinical relevance, which might offer useful clinical tools for the management of AVMs in the future.

show abstract

“…Such approaches were applied either on 3DRA, magnetic resonance angiography (MRA) or computed tomography angiography (CTA) images [11]. Morphological tools have also been used to segment 3D-CTA images of AVM [12], but these approaches require low noise images. Moreover, model-based methods such as Geodesic Active Regions (GAR) or level sets were used for an automated segmentation of cerebral vasculature in 3DRA [13,14] or for cerebral aneurysms segmentation in 3DRA and CTA [15].…”

Section: B Vascular Network Segmentationmentioning

confidence: 99%

Segmentation and reconstruction of cerebral vessels from 3D Rotational Angiography for AVM embolization planning

Chenoune

Ouenniche

et al. 2014

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Diagnosis and computer-guided therapy of cerebral Arterio-Venous Malformations (AVM) require an accurate understanding of the cerebral vascular network both from structural and biomechanical point of view. We propose to obtain such information by analyzing three Dimensional Rotational Angiography (3DRA) images. In this paper, we describe a two-step process allowing 1) the 3D automatic segmentation of cerebral vessels from 3DRA images using a region-growing based algorithm and 2) the reconstruction of the segmented vessels using the 3D constrained Delaunay Triangulation method. The proposed algorithm was successfully applied to reconstruct cerebral blood vessels from ten datasets of 3DRA images. This software allows the neuroradiologist to separately analyze cerebral vessels for pre-operative interventions planning and therapeutic decision making.

show abstract

Generalized pixel profiling and comparative segmentation with application to arteriovenous malformation segmentation

Cited by 21 publications

References 28 publications

Skeleton calculation for automatic extraction of arteriovenous malformation in 3-D CTA images

Skeleton calculation for automatic extraction of arteriovenous malformation in 3-D CTA images

Computational Analyses of Arteriovenous Malformations in Neuroimaging

Segmentation and reconstruction of cerebral vessels from 3D Rotational Angiography for AVM embolization planning

Contact Info

Product

Resources

About