Real-time CT-video registration for continuous endoscopic guidance

Scott A. Merritt, Lav Rai, William Evan Higgins

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

28 Citations (Scopus)

Abstract

Previous research has shown that CT-image-based guidance could be useful for the bronchoscopic assessment of lung cancer. This research drew upon the registration of bronchoscopic video images to CT-based endoluminal renderings of the airway tree. The proposed methods either were restricted to discrete single-frame registration, which took several seconds to complete, or required non-real-time buffering and processing of video sequences. We have devised a fast 2D/3D image registration method that performs single-frame CT-Video registration in under 1/15th of a second. This allows the method to be used for real-time registration at full video frame rates without significantly altering the physician's behavior. The method achieves its speed through a gradient-based optimization method that allows most of the computation to be performed off-line. During live registration, the optimization iteratively steps toward the locally optimal viewpoint at which a CT-based endoluminal view is most similar to a current bronchoscopic video frame. After an initial registration to begin the process (generally done in the trachea for bronchoscopy), subsequent registrations are performed in real-time on each incoming video frame. As each new bronchoscopic video frame becomes available, the current optimization is initialized using the previous frame's optimization result, allowing continuous guidance to proceed without manual re-initialization. Tests were performed using both synthetic and pre-recorded bronchoscopic video. The results show that the method is robust to initialization errors, that registration accuracy is high, and that continuous registration can proceed on real-time video at >15 frames per sec. with minimal user-intervention.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2006
Subtitle of host publicationPhysiology, Function, and Structure from Medical Images
Volume6143 I
DOIs
StatePublished - Jun 30 2006
EventMedical Imaging 2006: Physiology, Function, and Structure from Medical Images - San Diego, CA, United States
Duration: Feb 12 2006Feb 14 2006

Other

OtherMedical Imaging 2006: Physiology, Function, and Structure from Medical Images
CountryUnited States
CitySan Diego, CA
Period2/12/062/14/06

Fingerprint

Image registration
Processing

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Merritt, S. A., Rai, L., & Higgins, W. E. (2006). Real-time CT-video registration for continuous endoscopic guidance. In Medical Imaging 2006: Physiology, Function, and Structure from Medical Images (Vol. 6143 I). [614313] https://doi.org/10.1117/12.651695
Merritt, Scott A. ; Rai, Lav ; Higgins, William Evan. / Real-time CT-video registration for continuous endoscopic guidance. Medical Imaging 2006: Physiology, Function, and Structure from Medical Images. Vol. 6143 I 2006.
@inproceedings{6483603d03ed41bfa894f567cdd54129,
title = "Real-time CT-video registration for continuous endoscopic guidance",
abstract = "Previous research has shown that CT-image-based guidance could be useful for the bronchoscopic assessment of lung cancer. This research drew upon the registration of bronchoscopic video images to CT-based endoluminal renderings of the airway tree. The proposed methods either were restricted to discrete single-frame registration, which took several seconds to complete, or required non-real-time buffering and processing of video sequences. We have devised a fast 2D/3D image registration method that performs single-frame CT-Video registration in under 1/15th of a second. This allows the method to be used for real-time registration at full video frame rates without significantly altering the physician's behavior. The method achieves its speed through a gradient-based optimization method that allows most of the computation to be performed off-line. During live registration, the optimization iteratively steps toward the locally optimal viewpoint at which a CT-based endoluminal view is most similar to a current bronchoscopic video frame. After an initial registration to begin the process (generally done in the trachea for bronchoscopy), subsequent registrations are performed in real-time on each incoming video frame. As each new bronchoscopic video frame becomes available, the current optimization is initialized using the previous frame's optimization result, allowing continuous guidance to proceed without manual re-initialization. Tests were performed using both synthetic and pre-recorded bronchoscopic video. The results show that the method is robust to initialization errors, that registration accuracy is high, and that continuous registration can proceed on real-time video at >15 frames per sec. with minimal user-intervention.",
author = "Merritt, {Scott A.} and Lav Rai and Higgins, {William Evan}",
year = "2006",
month = "6",
day = "30",
doi = "10.1117/12.651695",
language = "English (US)",
isbn = "0819461865",
volume = "6143 I",
booktitle = "Medical Imaging 2006",

}

Merritt, SA, Rai, L & Higgins, WE 2006, Real-time CT-video registration for continuous endoscopic guidance. in Medical Imaging 2006: Physiology, Function, and Structure from Medical Images. vol. 6143 I, 614313, Medical Imaging 2006: Physiology, Function, and Structure from Medical Images, San Diego, CA, United States, 2/12/06. https://doi.org/10.1117/12.651695

Real-time CT-video registration for continuous endoscopic guidance. / Merritt, Scott A.; Rai, Lav; Higgins, William Evan.

Medical Imaging 2006: Physiology, Function, and Structure from Medical Images. Vol. 6143 I 2006. 614313.

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

TY - GEN

T1 - Real-time CT-video registration for continuous endoscopic guidance

AU - Merritt, Scott A.

AU - Rai, Lav

AU - Higgins, William Evan

PY - 2006/6/30

Y1 - 2006/6/30

N2 - Previous research has shown that CT-image-based guidance could be useful for the bronchoscopic assessment of lung cancer. This research drew upon the registration of bronchoscopic video images to CT-based endoluminal renderings of the airway tree. The proposed methods either were restricted to discrete single-frame registration, which took several seconds to complete, or required non-real-time buffering and processing of video sequences. We have devised a fast 2D/3D image registration method that performs single-frame CT-Video registration in under 1/15th of a second. This allows the method to be used for real-time registration at full video frame rates without significantly altering the physician's behavior. The method achieves its speed through a gradient-based optimization method that allows most of the computation to be performed off-line. During live registration, the optimization iteratively steps toward the locally optimal viewpoint at which a CT-based endoluminal view is most similar to a current bronchoscopic video frame. After an initial registration to begin the process (generally done in the trachea for bronchoscopy), subsequent registrations are performed in real-time on each incoming video frame. As each new bronchoscopic video frame becomes available, the current optimization is initialized using the previous frame's optimization result, allowing continuous guidance to proceed without manual re-initialization. Tests were performed using both synthetic and pre-recorded bronchoscopic video. The results show that the method is robust to initialization errors, that registration accuracy is high, and that continuous registration can proceed on real-time video at >15 frames per sec. with minimal user-intervention.

AB - Previous research has shown that CT-image-based guidance could be useful for the bronchoscopic assessment of lung cancer. This research drew upon the registration of bronchoscopic video images to CT-based endoluminal renderings of the airway tree. The proposed methods either were restricted to discrete single-frame registration, which took several seconds to complete, or required non-real-time buffering and processing of video sequences. We have devised a fast 2D/3D image registration method that performs single-frame CT-Video registration in under 1/15th of a second. This allows the method to be used for real-time registration at full video frame rates without significantly altering the physician's behavior. The method achieves its speed through a gradient-based optimization method that allows most of the computation to be performed off-line. During live registration, the optimization iteratively steps toward the locally optimal viewpoint at which a CT-based endoluminal view is most similar to a current bronchoscopic video frame. After an initial registration to begin the process (generally done in the trachea for bronchoscopy), subsequent registrations are performed in real-time on each incoming video frame. As each new bronchoscopic video frame becomes available, the current optimization is initialized using the previous frame's optimization result, allowing continuous guidance to proceed without manual re-initialization. Tests were performed using both synthetic and pre-recorded bronchoscopic video. The results show that the method is robust to initialization errors, that registration accuracy is high, and that continuous registration can proceed on real-time video at >15 frames per sec. with minimal user-intervention.

UR - http://www.scopus.com/inward/record.url?scp=33745369378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745369378&partnerID=8YFLogxK

U2 - 10.1117/12.651695

DO - 10.1117/12.651695

M3 - Conference contribution

SN - 0819461865

SN - 9780819461865

VL - 6143 I

BT - Medical Imaging 2006

ER -

Merritt SA, Rai L, Higgins WE. Real-time CT-video registration for continuous endoscopic guidance. In Medical Imaging 2006: Physiology, Function, and Structure from Medical Images. Vol. 6143 I. 2006. 614313 https://doi.org/10.1117/12.651695