Application of statistical cancer atlas for 3D biopsy

Ramkrishnan Narayanan, Dinggang Shen, Christos Davatzikos, E. David Crawford, Albaha Barqawi, Priya Werahera, Dinesh Kumar, Jasjit S. Suri

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

Abstract

Prostate cancer is the most commonly diagnosed cancer in males in the United States and the second leading cause of cancer death. While the exact cause is still under investigation, researchers agree on certain risk factors like age, family history, dietary habits, lifestyle and race. It is also widely accepted that cancer distribution within the prostate is inhomogeneous, i.e. certain regions have a higher likelihood of developing cancer. In this regard extensive work has been done to study the distribution of cancer in order to perform biopsy more effectively. Recently a statistical cancer atlas of the prostate was demonstrated along with an optimal biopsy scheme achieving a high detection rate. In this paper we discuss the complete construction and application of such an atlas that can be used in a clinical setting to effectively target high cancer zones during biopsy. The method consists of integrating intensity statistics in the form of cancer probabilities at every voxel in the image with shape statistics of the prostate in order to quickly warp the atlas onto a subject ultrasound image. While the atlas surface can be registered to a pre-segmented subject prostate surface or instead used to perform segmentation of the capsule via optimization of shape parameters to segment the subject image, the strength of our approach lies in the fast mapping of cancer statistics onto the subject using shape statistics. The shape model was trained from over 38 expert segmented prostate surfaces and the atlas registration accuracy was found to be high suggesting the use of this method to perform biopsy in near real time situations with some optimization.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6812
DOIs
StatePublished - 2008
Externally publishedYes
EventImage Processing: Algorithms and Systems VI - San Jose, CA, United States
Duration: Jan 28 2008Jan 29 2008

Other

OtherImage Processing: Algorithms and Systems VI
CountryUnited States
CitySan Jose, CA
Period1/28/081/29/08

Fingerprint

Biopsy
cancer
Statistics
statistics
Ultrasonics
age factor
optimization
causes
habits
capsules
death
histories

Keywords

  • Atlas
  • Cancer
  • Prostate
  • Registration
  • Shape

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Narayanan, R., Shen, D., Davatzikos, C., David Crawford, E., Barqawi, A., Werahera, P., ... Suri, J. S. (2008). Application of statistical cancer atlas for 3D biopsy. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6812). [681216] https://doi.org/10.1117/12.766633

Application of statistical cancer atlas for 3D biopsy. / Narayanan, Ramkrishnan; Shen, Dinggang; Davatzikos, Christos; David Crawford, E.; Barqawi, Albaha; Werahera, Priya; Kumar, Dinesh; Suri, Jasjit S.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6812 2008. 681216.

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

Narayanan, R, Shen, D, Davatzikos, C, David Crawford, E, Barqawi, A, Werahera, P, Kumar, D & Suri, JS 2008, Application of statistical cancer atlas for 3D biopsy. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6812, 681216, Image Processing: Algorithms and Systems VI, San Jose, CA, United States, 1/28/08. https://doi.org/10.1117/12.766633
Narayanan R, Shen D, Davatzikos C, David Crawford E, Barqawi A, Werahera P et al. Application of statistical cancer atlas for 3D biopsy. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6812. 2008. 681216 https://doi.org/10.1117/12.766633
Narayanan, Ramkrishnan ; Shen, Dinggang ; Davatzikos, Christos ; David Crawford, E. ; Barqawi, Albaha ; Werahera, Priya ; Kumar, Dinesh ; Suri, Jasjit S. / Application of statistical cancer atlas for 3D biopsy. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6812 2008.
@inproceedings{39893583391748c2bf90b4127c5b1650,
title = "Application of statistical cancer atlas for 3D biopsy",
abstract = "Prostate cancer is the most commonly diagnosed cancer in males in the United States and the second leading cause of cancer death. While the exact cause is still under investigation, researchers agree on certain risk factors like age, family history, dietary habits, lifestyle and race. It is also widely accepted that cancer distribution within the prostate is inhomogeneous, i.e. certain regions have a higher likelihood of developing cancer. In this regard extensive work has been done to study the distribution of cancer in order to perform biopsy more effectively. Recently a statistical cancer atlas of the prostate was demonstrated along with an optimal biopsy scheme achieving a high detection rate. In this paper we discuss the complete construction and application of such an atlas that can be used in a clinical setting to effectively target high cancer zones during biopsy. The method consists of integrating intensity statistics in the form of cancer probabilities at every voxel in the image with shape statistics of the prostate in order to quickly warp the atlas onto a subject ultrasound image. While the atlas surface can be registered to a pre-segmented subject prostate surface or instead used to perform segmentation of the capsule via optimization of shape parameters to segment the subject image, the strength of our approach lies in the fast mapping of cancer statistics onto the subject using shape statistics. The shape model was trained from over 38 expert segmented prostate surfaces and the atlas registration accuracy was found to be high suggesting the use of this method to perform biopsy in near real time situations with some optimization.",
keywords = "Atlas, Cancer, Prostate, Registration, Shape",
author = "Ramkrishnan Narayanan and Dinggang Shen and Christos Davatzikos and {David Crawford}, E. and Albaha Barqawi and Priya Werahera and Dinesh Kumar and Suri, {Jasjit S.}",
year = "2008",
doi = "10.1117/12.766633",
language = "English (US)",
isbn = "9780819469847",
volume = "6812",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Application of statistical cancer atlas for 3D biopsy

AU - Narayanan, Ramkrishnan

AU - Shen, Dinggang

AU - Davatzikos, Christos

AU - David Crawford, E.

AU - Barqawi, Albaha

AU - Werahera, Priya

AU - Kumar, Dinesh

AU - Suri, Jasjit S.

PY - 2008

Y1 - 2008

N2 - Prostate cancer is the most commonly diagnosed cancer in males in the United States and the second leading cause of cancer death. While the exact cause is still under investigation, researchers agree on certain risk factors like age, family history, dietary habits, lifestyle and race. It is also widely accepted that cancer distribution within the prostate is inhomogeneous, i.e. certain regions have a higher likelihood of developing cancer. In this regard extensive work has been done to study the distribution of cancer in order to perform biopsy more effectively. Recently a statistical cancer atlas of the prostate was demonstrated along with an optimal biopsy scheme achieving a high detection rate. In this paper we discuss the complete construction and application of such an atlas that can be used in a clinical setting to effectively target high cancer zones during biopsy. The method consists of integrating intensity statistics in the form of cancer probabilities at every voxel in the image with shape statistics of the prostate in order to quickly warp the atlas onto a subject ultrasound image. While the atlas surface can be registered to a pre-segmented subject prostate surface or instead used to perform segmentation of the capsule via optimization of shape parameters to segment the subject image, the strength of our approach lies in the fast mapping of cancer statistics onto the subject using shape statistics. The shape model was trained from over 38 expert segmented prostate surfaces and the atlas registration accuracy was found to be high suggesting the use of this method to perform biopsy in near real time situations with some optimization.

AB - Prostate cancer is the most commonly diagnosed cancer in males in the United States and the second leading cause of cancer death. While the exact cause is still under investigation, researchers agree on certain risk factors like age, family history, dietary habits, lifestyle and race. It is also widely accepted that cancer distribution within the prostate is inhomogeneous, i.e. certain regions have a higher likelihood of developing cancer. In this regard extensive work has been done to study the distribution of cancer in order to perform biopsy more effectively. Recently a statistical cancer atlas of the prostate was demonstrated along with an optimal biopsy scheme achieving a high detection rate. In this paper we discuss the complete construction and application of such an atlas that can be used in a clinical setting to effectively target high cancer zones during biopsy. The method consists of integrating intensity statistics in the form of cancer probabilities at every voxel in the image with shape statistics of the prostate in order to quickly warp the atlas onto a subject ultrasound image. While the atlas surface can be registered to a pre-segmented subject prostate surface or instead used to perform segmentation of the capsule via optimization of shape parameters to segment the subject image, the strength of our approach lies in the fast mapping of cancer statistics onto the subject using shape statistics. The shape model was trained from over 38 expert segmented prostate surfaces and the atlas registration accuracy was found to be high suggesting the use of this method to perform biopsy in near real time situations with some optimization.

KW - Atlas

KW - Cancer

KW - Prostate

KW - Registration

KW - Shape

UR - http://www.scopus.com/inward/record.url?scp=43249117978&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43249117978&partnerID=8YFLogxK

U2 - 10.1117/12.766633

DO - 10.1117/12.766633

M3 - Conference contribution

AN - SCOPUS:43249117978

SN - 9780819469847

VL - 6812

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -