In this paper we propose a novel approach based on multi-stage random forests to address problems faced by
traditional vessel segmentation algorithms on account of image artifacts such as stitches organ shadows etc.. Our
approach consists of collecting a very large number of training data consisting of positive and negative examples
of valid seed points. The method makes use of a 14x14 window around a putative seed point. For this window
three types of feature vectors are computed viz. vesselness, eigenvalue and a novel effective margin feature. A
random forest RF is trained for each of the feature vectors. At run time the three RFs are applied in succession
to a putative seed point generated by a naiive vessel detection algorithm based on vesselness. Our approach will
prune this set of putative seed points to correctly identify true seed points thereby avoiding false positives. We
demonstrate the effectiveness of our algorithm on a large dataset of angio images.
During interventional procedures, 3D imaging modalities like CT and MRI are not commonly used due to interference
with the surgery and radiation exposure concerns. Therefore, real-time information is usually limited and
building models of cardiac motion are difficult. In such case, vessel motion modeling based on 2-D angiography
images become indispensable. Due to issues with existing vessel segmentation algorithms and the lack of contrast
in occluded vessels, manual segmentation of certain branches is usually necessary. In addition, such occluded
branches are the most important vessels during coronary interventions and obtaining motion models for these
can greatly help in reducing the procedure time and radiation exposure. Segmenting different cardiac phases independently
does not guarantee temporal consistency and is not efficient for occluded branches required manual
segmentation. In this paper, we propose a coronary motion modeling system which extracts the coronary tree
for every cardiac phase, maintaining the segmentation by tracking the coronary tree during the cardiac cycle. It
is able to map every frame to the specific cardiac phase, thereby inferring the shape information of the coronary
arteries using the model corresponding to its phase. Our experiments show that our motion modeling system
can achieve promising results with real-time performance.
3D roadmap provided by pre-operative volumetric data that is aligned with fluoroscopy helps visualization and
navigation in Interventional Cardiology (IC), especially when contrast agent-injection used to highlight coronary vessels
cannot be systematically used during the whole procedure, or when there is low visibility in fluoroscopy for partially or
totally occluded vessels. The main contribution of this work is to register pre-operative volumetric data with intraoperative
fluoroscopy for specific vessel(s) occurring during the procedure, even without contrast agent injection, to
provide a useful 3D roadmap. In addition, this study incorporates automatic ECG gating for cardiac motion. Respiratory
motion is identified by rigid body registration of the vessels. The coronary vessels are first segmented from a multislice
computed tomography (MSCT) volume and correspondent vessel segments are identified on a single gated 2D
fluoroscopic frame. Registration can be explicitly constrained using one or multiple branches of a contrast-enhanced
vessel tree or the outline of guide wire used to navigate during the procedure. Finally, the alignment problem is solved
by Iterative Closest Point (ICP) algorithm. To be computationally efficient, a distance transform is computed from the
2D identification of each vessel such that distance is zero on the centerline of the vessel and increases away from the
centerline. Quantitative results were obtained by comparing the registration of random poses and a ground truth
alignment for 5 datasets. We conclude that the proposed method is promising for accurate 2D-3D registration, even for
difficult cases of occluded vessel without injection of contrast agent.
KEYWORDS: Image registration, Image segmentation, 3D image processing, Blood vessels, Image processing algorithms and systems, 3D acquisition, Error analysis, X-rays, Magnetic resonance imaging, Medical imaging
We propose a novel and fast way to perform 2D-3D registration between available intra-operative 2D images with pre-operative 3D images in order to provide better image-guidance. The current work is a feature based registration algorithm that allows the similarity to be evaluated in a very efficient and faster manner than that of intensity based approaches. The current approach is focused on solving the problem for neuro-interventional applications and therefore we use blood vessels, and specifically their centerlines as the features for registration. The blood vessels are segmented from the 3D datasets and their centerline is extracted using a sequential topological thinning algorithm. Segmentation of the 3D datasets is straightforward because of the injection of contrast agents. For the 2D image, segmentation of the blood vessel is performed by subtracting the image with no contrast (native) from the one with a contrast injection (fill). Following this we compute a modified version of the 2D distance transform. The modified distance transform is computed such that distance is zero on the centerline and increases as we move away from the centerline. This allows us a smooth metric that is minimal at the centerline and large as we move away from the vessel. This is a one time computation, and need not be reevaluated during the iterations. Also we simply sum over all the points rather than evaluating distances over all point pairs as would be done for similar Iterative Closest Point (ICP) based approaches. We estimate the three rotational and three translational parameters by minimizing this cost over all points in the 3D centerline. The speed improvement allows us to perform the registration in under a second on current workstations and therefore provides interactive registration for the interventionalist.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.