Evaluation of 3D multimodality image registration using ROC analysis

Kerrie S. Holton Tainter, Richard A. Robb, Udita Taneja, Joel E. Gray

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

6 Citations (Scopus)

Abstract

Receiver operating characteristic analysis has evolved as a useful method for evaluating the discriminatory capability and efficacy of visualization. The ability of such analysis to account for the variance in decision criteria of multiple observers, multiple reading, and a wide range of difficulty in detection among case studies makes ROC especially useful for interpreting the results of a viewing experiment. We are currently using ROC analysis to evaluate the effectiveness of using fused multispectral, or complementary multimodality imaging data in the diagnostic process. The use of multispectral image recordings, gathered from multiple imaging modalities, to provide advanced image visualization and quantization capabilities in evaluating medical images is an important challenge facing medical imaging scientists. Such capabilities would potentially significantly enhance the ability of clinicians to extract scientific and diagnostic information from images. a first step in the effective use of multispectral information is the spatial registration of complementary image datasets so that a point-to-point correspondence exists between them. We are developing a paradigm of measuring the accuracy of existing image registration techniques which includes the ability to relate quantitative measurements, taken from the images themselves, to the decisions made by observers about the state of registration (SOR) of the 3D images. We have used ROC analysis to evaluate the ability of observers to discriminate between correctly registered and incorrectly registered multimodality fused images. We believe this experience is original and represents the first time that ROC analysis has been used to evaluate registered/fused images. We have simulated low-resolution and high-resolution images from real patient MR images of the brain, and fused them with the original MR to produce colorwash superposition images whose exact SOR is known. We have also attempted to extend this analysis to real patient data, using magnetic resonance and single photon emission computed tomography 3D images whose SOR is estimated, but not known exactly. Results suggest that ROC analysis is useful for evaluating observer performance in detecting misregistration when viewing three orthogonal phases of colorwash superposition images, and that these results can be related to image measurements.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsHarold L. Kundel
Pages90-104
Number of pages15
Volume2436
StatePublished - 1995
EventMedical Imaging 1995: Image Perception - San Diego, CA, USA
Duration: Mar 1 1995Mar 1 1995

Other

OtherMedical Imaging 1995: Image Perception
CitySan Diego, CA, USA
Period3/1/953/1/95

Fingerprint

Image registration
Visualization
Image recording
Single photon emission computed tomography
Imaging techniques
evaluation
Optical resolving power
Medical imaging
Magnetic resonance
Image resolution
Brain
Experiments
brain

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Holton Tainter, K. S., Robb, R. A., Taneja, U., & Gray, J. E. (1995). Evaluation of 3D multimodality image registration using ROC analysis. In H. L. Kundel (Ed.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2436, pp. 90-104)

Evaluation of 3D multimodality image registration using ROC analysis. / Holton Tainter, Kerrie S.; Robb, Richard A.; Taneja, Udita; Gray, Joel E.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Harold L. Kundel. Vol. 2436 1995. p. 90-104.

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

Holton Tainter, KS, Robb, RA, Taneja, U & Gray, JE 1995, Evaluation of 3D multimodality image registration using ROC analysis. in HL Kundel (ed.), Proceedings of SPIE - The International Society for Optical Engineering. vol. 2436, pp. 90-104, Medical Imaging 1995: Image Perception, San Diego, CA, USA, 3/1/95.
Holton Tainter KS, Robb RA, Taneja U, Gray JE. Evaluation of 3D multimodality image registration using ROC analysis. In Kundel HL, editor, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2436. 1995. p. 90-104
Holton Tainter, Kerrie S. ; Robb, Richard A. ; Taneja, Udita ; Gray, Joel E. / Evaluation of 3D multimodality image registration using ROC analysis. Proceedings of SPIE - The International Society for Optical Engineering. editor / Harold L. Kundel. Vol. 2436 1995. pp. 90-104
@inproceedings{3ca6e16837474300a8830b0efd9e5e34,
title = "Evaluation of 3D multimodality image registration using ROC analysis",
abstract = "Receiver operating characteristic analysis has evolved as a useful method for evaluating the discriminatory capability and efficacy of visualization. The ability of such analysis to account for the variance in decision criteria of multiple observers, multiple reading, and a wide range of difficulty in detection among case studies makes ROC especially useful for interpreting the results of a viewing experiment. We are currently using ROC analysis to evaluate the effectiveness of using fused multispectral, or complementary multimodality imaging data in the diagnostic process. The use of multispectral image recordings, gathered from multiple imaging modalities, to provide advanced image visualization and quantization capabilities in evaluating medical images is an important challenge facing medical imaging scientists. Such capabilities would potentially significantly enhance the ability of clinicians to extract scientific and diagnostic information from images. a first step in the effective use of multispectral information is the spatial registration of complementary image datasets so that a point-to-point correspondence exists between them. We are developing a paradigm of measuring the accuracy of existing image registration techniques which includes the ability to relate quantitative measurements, taken from the images themselves, to the decisions made by observers about the state of registration (SOR) of the 3D images. We have used ROC analysis to evaluate the ability of observers to discriminate between correctly registered and incorrectly registered multimodality fused images. We believe this experience is original and represents the first time that ROC analysis has been used to evaluate registered/fused images. We have simulated low-resolution and high-resolution images from real patient MR images of the brain, and fused them with the original MR to produce colorwash superposition images whose exact SOR is known. We have also attempted to extend this analysis to real patient data, using magnetic resonance and single photon emission computed tomography 3D images whose SOR is estimated, but not known exactly. Results suggest that ROC analysis is useful for evaluating observer performance in detecting misregistration when viewing three orthogonal phases of colorwash superposition images, and that these results can be related to image measurements.",
author = "{Holton Tainter}, {Kerrie S.} and Robb, {Richard A.} and Udita Taneja and Gray, {Joel E.}",
year = "1995",
language = "English (US)",
isbn = "081941784X",
volume = "2436",
pages = "90--104",
editor = "Kundel, {Harold L.}",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Evaluation of 3D multimodality image registration using ROC analysis

AU - Holton Tainter, Kerrie S.

AU - Robb, Richard A.

AU - Taneja, Udita

AU - Gray, Joel E.

PY - 1995

Y1 - 1995

N2 - Receiver operating characteristic analysis has evolved as a useful method for evaluating the discriminatory capability and efficacy of visualization. The ability of such analysis to account for the variance in decision criteria of multiple observers, multiple reading, and a wide range of difficulty in detection among case studies makes ROC especially useful for interpreting the results of a viewing experiment. We are currently using ROC analysis to evaluate the effectiveness of using fused multispectral, or complementary multimodality imaging data in the diagnostic process. The use of multispectral image recordings, gathered from multiple imaging modalities, to provide advanced image visualization and quantization capabilities in evaluating medical images is an important challenge facing medical imaging scientists. Such capabilities would potentially significantly enhance the ability of clinicians to extract scientific and diagnostic information from images. a first step in the effective use of multispectral information is the spatial registration of complementary image datasets so that a point-to-point correspondence exists between them. We are developing a paradigm of measuring the accuracy of existing image registration techniques which includes the ability to relate quantitative measurements, taken from the images themselves, to the decisions made by observers about the state of registration (SOR) of the 3D images. We have used ROC analysis to evaluate the ability of observers to discriminate between correctly registered and incorrectly registered multimodality fused images. We believe this experience is original and represents the first time that ROC analysis has been used to evaluate registered/fused images. We have simulated low-resolution and high-resolution images from real patient MR images of the brain, and fused them with the original MR to produce colorwash superposition images whose exact SOR is known. We have also attempted to extend this analysis to real patient data, using magnetic resonance and single photon emission computed tomography 3D images whose SOR is estimated, but not known exactly. Results suggest that ROC analysis is useful for evaluating observer performance in detecting misregistration when viewing three orthogonal phases of colorwash superposition images, and that these results can be related to image measurements.

AB - Receiver operating characteristic analysis has evolved as a useful method for evaluating the discriminatory capability and efficacy of visualization. The ability of such analysis to account for the variance in decision criteria of multiple observers, multiple reading, and a wide range of difficulty in detection among case studies makes ROC especially useful for interpreting the results of a viewing experiment. We are currently using ROC analysis to evaluate the effectiveness of using fused multispectral, or complementary multimodality imaging data in the diagnostic process. The use of multispectral image recordings, gathered from multiple imaging modalities, to provide advanced image visualization and quantization capabilities in evaluating medical images is an important challenge facing medical imaging scientists. Such capabilities would potentially significantly enhance the ability of clinicians to extract scientific and diagnostic information from images. a first step in the effective use of multispectral information is the spatial registration of complementary image datasets so that a point-to-point correspondence exists between them. We are developing a paradigm of measuring the accuracy of existing image registration techniques which includes the ability to relate quantitative measurements, taken from the images themselves, to the decisions made by observers about the state of registration (SOR) of the 3D images. We have used ROC analysis to evaluate the ability of observers to discriminate between correctly registered and incorrectly registered multimodality fused images. We believe this experience is original and represents the first time that ROC analysis has been used to evaluate registered/fused images. We have simulated low-resolution and high-resolution images from real patient MR images of the brain, and fused them with the original MR to produce colorwash superposition images whose exact SOR is known. We have also attempted to extend this analysis to real patient data, using magnetic resonance and single photon emission computed tomography 3D images whose SOR is estimated, but not known exactly. Results suggest that ROC analysis is useful for evaluating observer performance in detecting misregistration when viewing three orthogonal phases of colorwash superposition images, and that these results can be related to image measurements.

UR - http://www.scopus.com/inward/record.url?scp=0029452585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029452585&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029452585

SN - 081941784X

SN - 9780819417848

VL - 2436

SP - 90

EP - 104

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

A2 - Kundel, Harold L.

ER -