A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images

Hari Sundar, Ali Khamene, Chenyang Xu, Frank Sauer, Christos Davatzikos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6141
DOIs
StatePublished - 2006
Externally publishedYes
EventMedical Imaging 2006: Visualization, Image-Guided Procedures, and Display - San Diego, CA, United States
Duration: Feb 12 2006Feb 14 2006

Other

OtherMedical Imaging 2006: Visualization, Image-Guided Procedures, and Display
CountryUnited States
CitySan Diego, CA
Period2/12/062/14/06

Fingerprint

Blood vessels
Image segmentation
Costs

Keywords

  • 2D/3D Registration
  • Centerline Extraction
  • Distance Transform
  • Iterative closest point
  • Projective Registration
  • Similarity Measures

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sundar, H., Khamene, A., Xu, C., Sauer, F., & Davatzikos, C. (2006). A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 6141). [61412K] https://doi.org/10.1117/12.654251

A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images. / Sundar, Hari; Khamene, Ali; Xu, Chenyang; Sauer, Frank; Davatzikos, Christos.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6141 2006. 61412K.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sundar, H, Khamene, A, Xu, C, Sauer, F & Davatzikos, C 2006, A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 6141, 61412K, Medical Imaging 2006: Visualization, Image-Guided Procedures, and Display, San Diego, CA, United States, 2/12/06. https://doi.org/10.1117/12.654251
Sundar H, Khamene A, Xu C, Sauer F, Davatzikos C. A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6141. 2006. 61412K https://doi.org/10.1117/12.654251
Sundar, Hari ; Khamene, Ali ; Xu, Chenyang ; Sauer, Frank ; Davatzikos, Christos. / A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6141 2006.
@inproceedings{ce8b2140671141d9a74a8990db6dd6c6,
title = "A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images",
abstract = "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.",
keywords = "2D/3D Registration, Centerline Extraction, Distance Transform, Iterative closest point, Projective Registration, Similarity Measures",
author = "Hari Sundar and Ali Khamene and Chenyang Xu and Frank Sauer and Christos Davatzikos",
year = "2006",
doi = "10.1117/12.654251",
language = "English (US)",
isbn = "0819461849",
volume = "6141",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images

AU - Sundar, Hari

AU - Khamene, Ali

AU - Xu, Chenyang

AU - Sauer, Frank

AU - Davatzikos, Christos

PY - 2006

Y1 - 2006

N2 - 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.

AB - 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.

KW - 2D/3D Registration

KW - Centerline Extraction

KW - Distance Transform

KW - Iterative closest point

KW - Projective Registration

KW - Similarity Measures

UR - http://www.scopus.com/inward/record.url?scp=33745361722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745361722&partnerID=8YFLogxK

U2 - 10.1117/12.654251

DO - 10.1117/12.654251

M3 - Conference contribution

AN - SCOPUS:33745361722

SN - 0819461849

SN - 9780819461841

VL - 6141

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -