Vessel Centerline Tracking in CTA and MRA Images Using Hough Transform

Macedo, Maysa M. G.; Mekkaoui, Choukri; Jackowski, Marcel P.

doi:10.1007/978-3-642-16687-7_41

Cited by 8 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A morphology-guided level set model is used in Santamaría-Pang et al ( 2007 ) to performed centerline extraction by learning the structural patterns of a tubular-like object, and estimating the centerline of a tubular object as the path with minimal cost with respect to outward flux in gray level images. Vesselness filters were adopted by Zheng et al ( 2012 ) to predict the location of the centerline, while Macedo et al ( 2010 ) used Hough transforms in handling a similar task. A Hough random forest with local image filters is designed in Schneider et al ( 2015 , 2012 ) to predict the centerline, and trained on centerline data previously extracted using one of the level set approaches.…”

Section: Introductionmentioning

confidence: 99%

DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes

et al. 2020

View full text Add to dashboard Cite

We present DeepVesselNet, an architecture tailored to the challenges faced when extracting vessel trees and networks and corresponding features in 3-D angiographic volumes using deep learning. We discuss the problems of low execution speed and high memory requirements associated with full 3-D networks, high-class imbalance arising from the low percentage (<3%) of vessel voxels, and unavailability of accurately annotated 3-D training data—and offer solutions as the building blocks of DeepVesselNet. First, we formulate 2-D orthogonal cross-hair filters which make use of 3-D context information at a reduced computational burden. Second, we introduce a class balancing cross-entropy loss function with false-positive rate correction to handle the high-class imbalance and high false positive rate problems associated with existing loss functions. Finally, we generate a synthetic dataset using a computational angiogenesis model capable of simulating vascular tree growth under physiological constraints on local network structure and topology and use these data for transfer learning. We demonstrate the performance on a range of angiographic volumes at different spatial scales including clinical MRA data of the human brain, as well as CTA microscopy scans of the rat brain. Our results show that cross-hair filters achieve over 23% improvement in speed, lower memory footprint, lower network complexity which prevents overfitting and comparable accuracy that does not differ from full 3-D filters. Our class balancing metric is crucial for training the network, and transfer learning with synthetic data is an efficient, robust, and very generalizable approach leading to a network that excels in a variety of angiography segmentation tasks. We observe that sub-sampling and max pooling layers may lead to a drop in performance in tasks that involve voxel-sized structures. To this end, the DeepVesselNet architecture does not use any form of sub-sampling layer and works well for vessel segmentation, centerline prediction, and bifurcation detection. We make our synthetic training data publicly available, fostering future research, and serving as one of the first public datasets for brain vessel tree segmentation and analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A second category tracks the centerline based on a filter or an assumed model. Commonly used filters are based on eigen-structure of local Hessian [24], idealized tubular models of vessels [25] and Hough transforms [26] to locate vessel direction and its cross vectors at a reference frame. For example, Hessian of the image is interpreted as second order partial derivatives of 3D sub-images at reference nodes, which requires extensive computation time.…”

Section: Related Work: Centerline Tracing Algorithmsmentioning

confidence: 99%

DeepNav: Joint View Learning for Direct Optimal Path Perception in Cochlear Surgical Platform Navigation

Zamani,

Demosthenous

2023

IEEE Access

View full text Add to dashboard Cite

Although much research has been conducted in the field of automated cochlear implant navigation, the problem remains challenging. Deep learning techniques have recently achieved impressive results in a variety of computer vision problems, raising expectations that they might be applied in other domains, such as identifying the optimal navigation zone (OPZ) in the cochlear. In this paper, a 2.5D jointview convolutional neural network (2.5D CNN) is proposed and evaluated for the identification of the OPZ in the cochlear segments. The proposed network consists of 2 complementary sagittal and bird-view (or top view) networks for the 3D OPZ recognition, each utilizing a ResNet-8 architecture consisting of 5 convolutional layers with rectified nonlinearity unit (ReLU) activations, followed by average pooling with size equal to the size of the final feature maps. The last fully connected layer of each network has 4 indicators, equivalent to the classes considered: the distance to the adjacent left and right walls, collision probability and heading angle. To demonstrate this, the 2.5D CNN was trained using a parametric data generation model, and then evaluated using anatomically constructed cochlea models from the micro-CT images of different cases. Prediction of the indicators demonstrates the effectiveness of the 2.5D CNN, for example the heading angle has less than 1˚ error with computation delays of less that <1 milliseconds.

show abstract

“…for each of the volumes and for the whole stitched volume. Furthermore, we also estimated the distribution of vascular diameters by using the Hough transform (provided in the scikit Python environment) 32,33 and the distributions of segment lengths.…”

Section: Image Analysismentioning

confidence: 99%

Brain micro‐vasculature imaging: An unsupervised deep learning algorithm for segmenting mouse brain volume probed by high‐resolution phase‐contrast X‐ray tomography

Patera

Zippo

Bonnin

et al. 2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

High-throughput synchrotron-based tomographic microscopy at third generation light sources allows to probe cm-sized samples at micrometer-resolution. In this work, we present an approach to image a full mouse brain. With Indianink as a contrast agent, it was possible to obtain 3D distribution of microvessels while a computational framework automatically extracted the morphological and geometrical embedding of the putative vascular systems. Results demonstrate the potentiality of the proposed methodology to visualize and quantify in 3D details of the brain tissue with an image quality and resolution previously unachievable.

show abstract

Vessel Centerline Tracking in CTA and MRA Images Using Hough Transform

Cited by 8 publications

References 10 publications

DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes

DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes

DeepNav: Joint View Learning for Direct Optimal Path Perception in Cochlear Surgical Platform Navigation

Brain micro‐vasculature imaging: An unsupervised deep learning algorithm for segmenting mouse brain volume probed by high‐resolution phase‐contrast X‐ray tomography

Contact Info

Product

Resources

About