Tissue metabolism driven arterial tree generation

Schneider, Matthias; Reichold, Johannes; Weber, Bruno; Székely, Gábor; Hirsch, Sven

doi:10.1016/j.media.2012.04.009

Cited by 62 publications

(98 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synthetic data is obtained as follows: An artificial, yet physiologically plausible, arterial tree model is generated for a box-shaped simulation domain as described in Schneider et al (2012). The vascular network is represented as a discrete graph structure (rooted tree) where each vessel segment is modeled as rigid cylindrical tube with a constant radius inscribed in the vessel lumen.…”

Section: Centerline Extractionmentioning

confidence: 99%

“…An axial slice is shown in Figure 5b with superimposed segmentation and centerline labels. We generate two synthetic datasets for training and testing using different random seeds to drive the arterial tree simulation of Schneider et al (2012). Thus, we obtain different yet morphologically similar training and test data (see Figure 4).…”

Section: Centerline Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters

Schneider

Hirsch

Weber

et al. 2015

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

Contributions We propose a novel framework for joint 3-D vessel segmentation and centerline extraction. The approach is based on multivariate Hough voting and oblique random forests (RFs) that we learn from noisy annotations. It relies on steerable filters for the efficient computation of local image features at different scales and orientations. Experiments We validate both the segmentation performance and the centerline accuracy of our approach both on synthetic vascular data and four 3-D imaging datasets of the rat visual cortex at 700 nm resolution. First, we evaluate the most important structural components of our approach: (1) Orthogonal subspace filtering in comparison to steerable filters that show, qualitatively, similarities to the eigenspace filters learned from local image patches. (2) Standard RF against oblique RF. Second, we compare the overall approach to different state-of-the-art methods for (1) vessel segmentation based on optimally oriented flux (OOF) and the eigenstructure of the Hessian, and (2) centerline extraction based on homotopic skeletonization and geodesic path tracing. Results Our experiments reveal the benefit of steerable over eigenspace filters as well as the advantage of oblique split directions over univariate orthogonal splits. We further show that the learning-based approach outperforms different state-of-the-art methods and proves highly accurate and robust with regard to both vessel segmentation and centerline extraction in spite of the high level of label noise in the training data. AbstractContributions. We propose a novel framework for joint 3-D vessel segmentation and centerline extraction. The approach is based on multivariate Hough voting and oblique random forests (RFs) that we learn from noisy annotations. It relies on steerable filters for the efficient computation of local image features at different scales and orientations.Experiments. We validate both the segmentation performance and the centerline accuracy of our approach both on synthetic vascular data and four 3-D imaging datasets of the rat visual cortex at 700 nm resolution. First, we evaluate the most important structural components of our approach: (1) Orthogonal subspace filtering in comparison to steerable filters that show, qualitatively, similarities to the eigenspace filters learned from local image patches. (2) Standard RF against oblique RF. Second, we compare the overall approach to different state-of-the-art methods for (1) vessel segmentation based on optimally oriented flux (OOF) and the eigenstructure of the Hessian, and (2) centerline extraction based on homotopic skeletonization and geodesic path tracing. both vessel segmentation and centerline extraction in spite of the high level of label noise in the training data.

show abstract

Section: Centerline Extractionmentioning

confidence: 99%

Section: Centerline Extractionmentioning

confidence: 99%

Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters

Schneider

Hirsch

Weber

et al. 2015

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…More specifically, recent emphasis has been placed in terms of modeling human development [43]- [45] and disease progression [46]- [49] thus creating highly detailed spatio-temporal atlases. One of the challenges is to underpin current phenotypic generative models with biophysical and physiological principles (e.g., [50]). 4) Linking Anatomically Accurate Biophysical Models to Omics Data: VPH/Physiome models are sensu stricto multiscale models that link subcellular and cellular processes with tissue, organ and system levels.…”

Section: ) From Image Databases To Human Development and Disease Promentioning

confidence: 99%

Guest Editorial Special Issue on Medical Imaging and Image Computing in Computational Physiology

Frangi

Hose

Hunter

et al. 2013

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

International audienceThe January 2013 Special Issue of IEEE transactions on medical imaging discusses papers on medical imaging and image computing in computational physiology. Aslanid and co-researchers present an experimental technique based on stained micro computed tomography (CT) images to construct very detailed atrial models of the canine heart. The paper by Sebastian proposes a model of the cardiac conduction system (CCS) based on structural information derived from stained calf tissue. Ho, Mithraratne and Hunter present a numerical simulation of detailed cerebral venous flow. The third category of papers deals with computational methods for simulating medical imagery and incorporate knowledge of imaging physics and physiology/biophysics. The work by Morales showed how the combination of device modeling and virtual deployment, in addition to patient-specific image-based anatomical modeling, can help to carry out patient-specific treatment plans and assess alternative therapeutic strategies

show abstract

“…3 Several groups have performed the computation of μCBF in realistic vascular networks. [4][5][6][7][8][9][10][11][12][13][14] Several difficulties arise when the computation takes place over a real vascular network measured in vivo. This includes vessel diameter estimation and, therefore, estimation of resistances.…”

Section: Introductionmentioning

confidence: 99%

Multimodal reconstruction of microvascular-flow distributions using combined two-photon microscopy and Doppler optical coherence tomography

et al. 2015

View full text Add to dashboard Cite

Abstract. Computing microvascular cerebral blood flow (μCBF) in real cortical angiograms is challenging. Here, we investigated whether the use of Doppler optical coherence tomography (DOCT) flow measurements in individual vessel segments can help in reconstructing μCBF across the entire vasculature of a truncated cortical angiogram. A μCBF computational framework integrating DOCT measurements is presented. Simulations performed on a synthetic angiogram showed that the addition of DOCT measurements, especially close to large inflowing or outflowing vessels, reduces the impact of pressure boundary conditions and estimated vessel resistances resulting in a more accurate reconstruction of μCBF. Our technique was then applied to reconstruct microvascular flow distributions in the mouse cortex down to 660 μm by combining two-photon laser scanning microscopy angiography with DOCT.

show abstract

Tissue metabolism driven arterial tree generation

Cited by 62 publications

References 52 publications

Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters

Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters

Guest Editorial Special Issue on Medical Imaging and Image Computing in Computational Physiology

Multimodal reconstruction of microvascular-flow distributions using combined two-photon microscopy and Doppler optical coherence tomography

Contact Info

Product

Resources

About