Real-time image-based guidance method for lung-cancer assessment

Lav Rai, Scott A. Merritt, William Evan Higgins

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

16 Citations (Scopus)

Abstract

The assessment of lung cancer involves off-line three-dimensional (3D) computed-tomography (CT) image assessment followed by live bronchoscopy. While standard bronchoscopy provides live video of information inside the lung airways, it does not give any information outside the airways. This results in a low procedure success rate. The success rate can be improved if the physician receives 3D CT-based image guidance. We describe a fast robust method that provides 3D CT-based image guidance during live bronchoscopy. The method enables a continuous registration between the 3D CT image space and the real bronchoscopic video. At a top level, it involves an inter-leaving of continuous video tracking and CT-video fine registration. During video tracking, the bronchoscope's 3D motion is estimated using a point-based 3D-2D pose estimation method. Registration is performed via a warping-based Gauss-Newton method that uses a normalized cross-correlation-based cost for measuring similarity between the bronchoscopic video and CT image data. The method operates at a real-time rate of 10 frames per second, which is over an order of magnitude faster than past approaches. This real-time performance enables live guidance during a procedure. The method is incorporated into a computer-based system for image-guided bronchoscopy and has been applied to human lung-cancer patients. Results are presented for a phantom and lung-cancer patients.

Original languageEnglish (US)
Title of host publicationProceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages2437-2444
Number of pages8
Volume2
DOIs
StatePublished - 2006
Event2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States
Duration: Jun 17 2006Jun 22 2006

Other

Other2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
CountryUnited States
CityNew York, NY
Period6/17/066/22/06

Fingerprint

Tomography
Newton-Raphson method
Costs

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Rai, L., Merritt, S. A., & Higgins, W. E. (2006). Real-time image-based guidance method for lung-cancer assessment. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (Vol. 2, pp. 2437-2444). [1641052] https://doi.org/10.1109/CVPR.2006.238
Rai, Lav ; Merritt, Scott A. ; Higgins, William Evan. / Real-time image-based guidance method for lung-cancer assessment. Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. Vol. 2 2006. pp. 2437-2444
@inproceedings{ad997df6f9ac4f659a0612e088e7e243,
title = "Real-time image-based guidance method for lung-cancer assessment",
abstract = "The assessment of lung cancer involves off-line three-dimensional (3D) computed-tomography (CT) image assessment followed by live bronchoscopy. While standard bronchoscopy provides live video of information inside the lung airways, it does not give any information outside the airways. This results in a low procedure success rate. The success rate can be improved if the physician receives 3D CT-based image guidance. We describe a fast robust method that provides 3D CT-based image guidance during live bronchoscopy. The method enables a continuous registration between the 3D CT image space and the real bronchoscopic video. At a top level, it involves an inter-leaving of continuous video tracking and CT-video fine registration. During video tracking, the bronchoscope's 3D motion is estimated using a point-based 3D-2D pose estimation method. Registration is performed via a warping-based Gauss-Newton method that uses a normalized cross-correlation-based cost for measuring similarity between the bronchoscopic video and CT image data. The method operates at a real-time rate of 10 frames per second, which is over an order of magnitude faster than past approaches. This real-time performance enables live guidance during a procedure. The method is incorporated into a computer-based system for image-guided bronchoscopy and has been applied to human lung-cancer patients. Results are presented for a phantom and lung-cancer patients.",
author = "Lav Rai and Merritt, {Scott A.} and Higgins, {William Evan}",
year = "2006",
doi = "10.1109/CVPR.2006.238",
language = "English (US)",
isbn = "0769525970",
volume = "2",
pages = "2437--2444",
booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

}

Rai, L, Merritt, SA & Higgins, WE 2006, Real-time image-based guidance method for lung-cancer assessment. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. vol. 2, 1641052, pp. 2437-2444, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.238

Real-time image-based guidance method for lung-cancer assessment. / Rai, Lav; Merritt, Scott A.; Higgins, William Evan.

Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. Vol. 2 2006. p. 2437-2444 1641052.

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

TY - GEN

T1 - Real-time image-based guidance method for lung-cancer assessment

AU - Rai, Lav

AU - Merritt, Scott A.

AU - Higgins, William Evan

PY - 2006

Y1 - 2006

N2 - The assessment of lung cancer involves off-line three-dimensional (3D) computed-tomography (CT) image assessment followed by live bronchoscopy. While standard bronchoscopy provides live video of information inside the lung airways, it does not give any information outside the airways. This results in a low procedure success rate. The success rate can be improved if the physician receives 3D CT-based image guidance. We describe a fast robust method that provides 3D CT-based image guidance during live bronchoscopy. The method enables a continuous registration between the 3D CT image space and the real bronchoscopic video. At a top level, it involves an inter-leaving of continuous video tracking and CT-video fine registration. During video tracking, the bronchoscope's 3D motion is estimated using a point-based 3D-2D pose estimation method. Registration is performed via a warping-based Gauss-Newton method that uses a normalized cross-correlation-based cost for measuring similarity between the bronchoscopic video and CT image data. The method operates at a real-time rate of 10 frames per second, which is over an order of magnitude faster than past approaches. This real-time performance enables live guidance during a procedure. The method is incorporated into a computer-based system for image-guided bronchoscopy and has been applied to human lung-cancer patients. Results are presented for a phantom and lung-cancer patients.

AB - The assessment of lung cancer involves off-line three-dimensional (3D) computed-tomography (CT) image assessment followed by live bronchoscopy. While standard bronchoscopy provides live video of information inside the lung airways, it does not give any information outside the airways. This results in a low procedure success rate. The success rate can be improved if the physician receives 3D CT-based image guidance. We describe a fast robust method that provides 3D CT-based image guidance during live bronchoscopy. The method enables a continuous registration between the 3D CT image space and the real bronchoscopic video. At a top level, it involves an inter-leaving of continuous video tracking and CT-video fine registration. During video tracking, the bronchoscope's 3D motion is estimated using a point-based 3D-2D pose estimation method. Registration is performed via a warping-based Gauss-Newton method that uses a normalized cross-correlation-based cost for measuring similarity between the bronchoscopic video and CT image data. The method operates at a real-time rate of 10 frames per second, which is over an order of magnitude faster than past approaches. This real-time performance enables live guidance during a procedure. The method is incorporated into a computer-based system for image-guided bronchoscopy and has been applied to human lung-cancer patients. Results are presented for a phantom and lung-cancer patients.

UR - http://www.scopus.com/inward/record.url?scp=33845574224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845574224&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.238

DO - 10.1109/CVPR.2006.238

M3 - Conference contribution

SN - 0769525970

SN - 9780769525976

VL - 2

SP - 2437

EP - 2444

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

ER -

Rai L, Merritt SA, Higgins WE. Real-time image-based guidance method for lung-cancer assessment. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. Vol. 2. 2006. p. 2437-2444. 1641052 https://doi.org/10.1109/CVPR.2006.238