Application of three-class ROC analysis to task-based image quality assessment of simultaneous dual-isotope myocardial perfusion SPECT (MPS)

IEEE Transactions on Medical Imaging

Volumn 27, Issue 11, 2008, Pages 1556-1567

  He, Xin ^a   Song, Xiyun ^a   Frey, Eric C ^b  

^a JOHNS HOPKINS UNIVERSITY SCHOOL OF MEDICINE   (United States)

^b PHILIPS HEALTHCARE   (United States)

Author keywords

Dual isotope myocardial perfusion SPECT (MPS); Simultaneous acquisition; Task based image quality assessment; Three class hotelling observer; Three class receiver operating characteristic (ROC) analysis

Indexed keywords

APPLICATIONS; CROSSTALK; DISCRIMINANT ANALYSIS; IMAGE ENHANCEMENT; IMAGING SYSTEMS; IMAGING TECHNIQUES; ISOTOPES; MAGNETOPLASMA; MEDICAL PROBLEMS; MERGERS AND ACQUISITIONS; NETWORK PROTOCOLS; TECHNETIUM;

DUAL-ISOTOPE MYOCARDIAL PERFUSION SPECT (MPS); SIMULTANEOUS ACQUISITION; TASK-BASED IMAGE QUALITY ASSESSMENT; THREE-CLASS HOTELLING OBSERVER; THREE-CLASS RECEIVER OPERATING CHARACTERISTIC (ROC) ANALYSIS;

IMAGE QUALITY;

DIAGNOSTIC AGENT; METHOXY ISOBUTYL ISONITRILE TECHNETIUM TC 99M; RADIOISOTOPE; THALLIUM;

ARTICLE; AUTOMATED PATTERN RECOGNITION; BLOOD; CLINICAL PROTOCOL; CORONARY ARTERY DISEASE; EXERCISE TEST; FEMALE; HEART; HEART SCINTISCANNING; HUMAN; IMAGE QUALITY; MALE; METHODOLOGY; PATHOPHYSIOLOGY; REST; ROC CURVE; SCINTISCANNING; SINGLE PHOTON EMISSION COMPUTER TOMOGRAPHY; VALIDATION STUDY;

CLINICAL PROTOCOLS; CORONARY ARTERY DISEASE; EXERCISE TEST; FEMALE; HEART; HUMANS; MALE; MYOCARDIAL PERFUSION IMAGING; PATTERN RECOGNITION, AUTOMATED; PHANTOMS, IMAGING; RADIOISOTOPES; RESEARCH DESIGN; REST; ROC CURVE; TECHNETIUM TC 99M SESTAMIBI; THALLIUM RADIOISOTOPES; TOMOGRAPHY, EMISSION-COMPUTED, SINGLE-PHOTON; VALIDATION STUDIES AS TOPIC;

EID: 54949103513     PISSN: 02780062     EISSN: None     Source Type: Journal    
DOI: 10.1109/TMI.2008.928921     Document Type: Article

References (52)

1. H. Kiat, G. Germano, J. Friedman, K. Vantrain, G. Silagan, F. P. Wang, J. Maddahi, and D. Berman, "Comparative feasibility of separate or simultaneous rest Tl-201 stress technetium-99m-Sestamibi dual-isotope myocardial perfusion SPECT," J. Nucl. Med., vol. 35, pp. 542-548, 1994.
2. V. J. Lowe, K. L. Greer, M. W. Hanson, R. J. Jaszczak, and R. E. Coleman, "Cardiac phantom evaluation of simultaneously acquired dual-isotope rest Tl-201 stress Tc-99m SPECT images," J. Nucl. Med., vol. 34, pp. 1998-2006, 1993.
3. S. C. Moore, C. Syravanh, and D. E. Tow, "Simultaneous SPECT imaging of Tl-201 and Tc-99m using 4 energy windows," J. Nucl. Med., vol. 34, pp. P188-P188, 1993.
4. M. Nakamura, K. Takeda, T. Ichihara, N. Motomura, H. Shimizu, Y. Saito, Y. Nomura, N. Isaka, T. Konishi, and T. Nakano, "Feasibility of simultaneous stress Tc-99m-sestamibi/rest (201)T1 dual-isotope myocardial perfusion SPECT in the detection of coronary artery disease," J. Nucl. Med., vol. 40, pp. 895-903, 1999.
5. J. A. Swets and T. G. Birdsall, "The human use of information.3. decision-making in signal-detection and recognition situations involving multiple alternatives," IRE Trans. Inf. Theory, vol. 2, pp. 138-165, 1956.
6. J. A. Swets and R. M. Pickett, Evaluation of Diagnostic Systems: Methods from Signal Detection Theory. New York: Academic, 1982.
7. X. He, C. E. Metz, B. M. W. Tsui, J. M. Links, and E. C. Frey, "Three-class ROC analysis - A decision theoretic approach under the ideal observer framework," IEEE Trans. Med. Imag., vol. 25, no. 5, pp. 571-581, May 2006.
8. X. He and E. C. Frey, "Three-class ROC analysis-The equal error utility assumption and the optimality of three-class ROC surface using the ideal observer," IEEE Trans. Med. Imag., vol. 25, no. 8, pp. 979-986, Aug. 2006.
9. X. He and E. C. Frey, "An optimal three-class linear observer derived from decision theory," IEEE Trans. Med. Imag., vol. 26, no. 1, pp. 77-83, Jan. 2007.
10. X. He and E. C. Frey, "The meaning of the volume under the threeclass ROC surface (VUS)," IEEE Trans. Med. Imag., vol. 27, no. 5, pp. 577-588, May 2008.
11. H. L. Van Trees, Detection, Estimation and Modulation Theory. New York: Wiley, 1968, pt. I.
12. C. E. Metz, The optimal decision variable: Likelihood ratio Univ. Chicago, Chicago, IL, 2000.
13. H. H. Barrett and K. J. Myers, Foundations of Image Science. New York: Wiley, 2003.
14. J. A. Hanley and B. J. McNeil, "The meaning and use of the area under a receiver operating characteristic (ROC) curve," Radiology, vol. 143, pp. 29-36, 1982.
15. J. P. Egan, Signal Detection Theory and ROC Analysis. New York: Academic, 1975.
16. D. M. Green and J. A. Swets, Signal Detection Theory and Psychophysics. Huntington, New York: Krieger, 1973.
17. L. B. Lusted, "Signal detectability and medical decision-making, " Science, vol. 171, pp. 1217-1217, 1971.
18. B. J. Mcneil, E. Keeler, and S. J. Adelstein, "Primer on certain elements of medical decision-making," New Eng. J. Med., vol. 293, pp. 211-215, 1975.
19. J. A. Swets and R. M. Pickett, Evaluation of Diagnostic System: Methods from Signal Detection Theory. New York: Academic, 1982.
20. H.-P. Chan, B. Sahiner, L. M. Hadjiiski, N. Petrick, and C. Zhou, "Design of three-class classifiers in computer-aided diagnosis: Monte Carlo simulation study," Proc. SPIE, vol. 5032, pp. 567-578, 2003.
21. S. Dreiseitl, L. Ohno-Machado, and M. Binder, "Comparing three-class diagnostic tests by three-way ROC analysis," Med. Decision Making, vol. 20, pp. 323-31, 2000.
22. D. C. Edwards, Ideal observer estimation and generalized ROC analysis for computer-aided diagnosis Univ. Chicago, Chicago, IL, 2003.
23. D. C. Edwards, L. Lan, C. E. Metz, M. L. Giger, and R. M. Nishikawa, "Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions," Med. Phys., vol. 31, pp. 81-90, 2004.
24. D. C. Edwards and C. E. Metz, "Restrictions on the three-class ideal observer's decision boundary lines," IEEE Trans. Med. Imag., vol. 24, no. 12, pp. 1566-1573, Dec. 2005.
25. D. C. Edwards and C. E. Metz, "Analysis of proposed three-class classification decision rules in terms of the ideal observer decision rule," J. Math. Psychol., vol. 50, pp. 478-487, 2006.
26. D. C. Edwards, C. E. Metz, and M. A. Kupinski, "Ideal observers and optimal ROC hypersurfaces in N-class classification," IEEE Trans. Med. Imag., vol. 23, no. 7, pp. 891-895, Jul. 2004.
27. D. C. Edwards, C. E. Metz, and R. M. Nishikawa, "The hypervolume under the ROC hypersurface of "near-guessing" and "near- perfect" observers in N-class classification tasks," IEEE Trans. Med. Imag., vol. 24, no. 3, pp. 293-299, Mar. 2005.
28. R. M. Everson and J. E. Fieldsend, "Multi-class ROC analysis from a multi-objective optimisation perspective," Pattern Recognit. Lett., vol. 27, pp. 918-927, 2006.
29. D. J. Hand and R. J. Till, "A simple generalisation of the area under the ROC curve for multiple class classification problems," Mach. Learn., vol. 45, pp. 171-186, 2001.
30. P. S. Heckerling, "Parametric three-way receiver operating characteristic surface analysis using mathematica," Med. Decision Making, vol. 21, pp. 409-417, 2001.
31. A. J. Johnson, A. J. Noga, O. Kosoy, R. S. Lanciotti, A. A. Johnson, and B. J. Biggerstaff, "Duplex microsphere-based immunoassay for detection of anti-West Nile virus and anti-St. Louis encephalitis virus immunoglobulin M antibodies," Clin, iagnostic Lab. Imrmmol., vol. 12, pp. 566-574, 2005.
32. M. F. Kijewski, R. G. Swensson, and P. F. Judy, "Analysis of rating data from multiple-alternative tasks," J. Math. Psychol., vol. 33, pp. 428-451, 1989.
33. D. Mossman, "Three-way ROCs," Med. Decision Making, vol. 19, pp. 78-89, 1999.
34. C. T. Nakas and C. T. Yiannoutsos, "Ordered multiple-class ROC analysis with continuous measurements," Stat. Med., vol. 23, pp. 3437-3449, 2004.
35. A. C. Patel and M. K. Markey, "Comparison of three-class classification performance metrics: A case study in breast cancer CAD," in SPIE Med. Imag., San Diego, CA, 2005, vol. 5749, pp. 581-589.
36. B. Sahiner, H. P. Chan, and L. M. Hadjilski, "Performance analysis of three-class classifiers: Properties of a 3-D ROC surface and the normalized volume under the surface for the ideal observer," IEEE Trans. Med. Imag., vol. 27, no. 2, pp. 215-227, Feb. 2008.
37. B. Sahiner, H.-P. Chan, and L. M. Hadjiiski, "Performance analysis of 3-class classifiers: Properties of the 3-D ROC surface and the normalized volume under the surface," in Proc. SPIE. 2006, vol. 6146, pp. 567-578.
38. B. K. Scurfield, "Multiple-event forced-choice tasks in the theory of signal detectability," J. Math. Psychol., vol. 40, pp. 253-269, 1996.
39. B. K. Scurfield, "Generalization of the theory of signal detectability to n-event m-dimensional forced-choice tasks," J. Math. Psychol., vol. 42, pp. 5-31, 1998.
40. C. J. Xiong, G. van Belle, J. P. Miller, and J. C. Moms, "Measuring and estimating diagnostic accuracy when there are three ordinal diagnostic groups," Stat. Med., vol. 25, pp. 1251-1273, 2006.
41. K. Y. Yeung, R. E. Bumgarner, and A. E. Raftery, "Bayesian model averaging: Development of an improved multi-class, gene selection and classification tool for microarray data," Bioinfomatics, vol. 21, pp. 2394-2402, 2005.
42. X. He and E. C. Frey, "The meaning of the volume under the threeclass ROC surface (VUS)," IEEE Trans. Med. Imag., vol. 27, no. 5, pp. 577-588, May 2008.
43. X. He, E. Frey, W. Segars, K. Gilland, and B. Tsui, "An improved phantom population for evaluation of myocardial perfusion SPECT imaging," J. Nucl. Med., vol. 43, pp. 9-10, 2002.
44. X. He, E. C. Frey, J. M. Links, K. L. Gilland, W. P. Segars, and B. M. W. Tsui, "A mathematical observer study for the evaluation and optimization of compensation methods for myocardial SPECT using a phantom population that realistically models patient variability," IEEE Trans. Nucl. Sci., vol. 51, no. 1, pp. 218-224, Feb. 2004.
45. W. P. Segars, B. M. Tsui, D. S. Lalush, E. C. Frey, M. A. King, and D. Manocha, "Development and application of the new dynamic nurbsbased cardiac-torso (NCAT) phantom," J. Nucl. Med., vol. 42, p. 7, 2001.
46. A. B. Barclay, R. L. Eisner, and E. V. DiBella, PET thorax model database [Online]. Available: http://www.emory.edu/CRL/abb/thoraxmodel/Contents.html
47. X. He, J. M. Links, K. L. Gilland, B. M. W. Tsui, and E. C. Frey, "Comparison of 180 degrees and 360 degrees acquisition for myocardial perfusion SPECT with compensation for attenuation, detector response, and scatter: Monte carlo and mathematical observer results," J. Nucl. Cardiol., vol. 13, pp. 345-353, 2006.
48. X. Song, E. C. Frey, W. P. Segars, and B. M. W. Tsui, "A mathematical observer study for evaluation of a model-based compensation method for crosstalk in simultaneous dual isotope SPECT," in IEEE Med. Imag. Conf., 2003, vol. 4, pp. 2521-2525.
49. SimSET Version 2.6 Univ. Washington, 2004 [Online], Available: http://depts.washington.edu/lsimsimset/htm/simset_home.html
50. X. Song, W. P. Segars, Y. Du, B. M. W. Tsui, and E. C. Frey, "Fast modelling of the collimator-detector response in monte Carlo simulation of SPECT imaging using the angular response function," Phys. Med. Biol., vol. 50, pp. 1791-1804, 2005.
51. E. C. Frey, K. L. Gilland, and B. M. Tsui, "Application of task-based measures of image quality to optimization and evaluation of threedimensional reconstruction-based compensation methods in myocardial perfusion SPECT," IEEE Trans. Med. Imag., vol. 21, no. 9, pp. 1040-1050, Sep. 2002.
52. S. Sankaran, E. C. Frey, K. L. Gilland, and B. M. W. Tsui, "Optimum compensation method and filter cutoff frequency in myocardial SPECT: A human observer study," J. Nucl. Med., vol. 43, pp. 432-438, 2002.