Abstract

This work assesses the usefulness of an objective, task-based image quality measure that is correlated with perceived image quality; the measure uses the most salient features contained within a medical image. Contributions include the development of a perceptually correlated metric that is useful for quantifying the salience of local, low-level visual cues and identifying those spatial frequencies that are most distinct and perhaps most relied upon by radiologists for decision making. A set of 40 mammograms and registered eye position data from nine observers was used to evaluate the salience metric. A parsimonious analysis-of-variance model explained the variance in the salience results. This analysis is generalized to a population of readers and cases. An analysis of salience versus time of first eye fixation shows good correlation with true positive lesions that were found by experienced readers in less than 2s.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |

  1. H. L. Kundel and G. Revesz, "Lesion conspicuity, structured noise, and film reader error," Am. J. Roentgenol. 126, 1233-1238 (1976).
  2. A. Treisman and G. Gelade, "A feature-integration theory of attention," Cogn. Psychol. 12, 97-136 (1980).
    [CrossRef] [PubMed]
  3. J. M. Wolfe, K. R. Cave, and S. L. Franzel, "An alternative to the feature integration model for visual search," J. Exp. Psychol. Hum. Percept. Perform. 15, 419-433 (1989).
    [CrossRef] [PubMed]
  4. J. M. Wolfe and G. Gancarz, "Guided search 3.0: A model of visual search catches up with Jay Enoch 40 years later," in Basic and Clinical Applications of Vision Science, V.Lakshminarayanan, ed. (Kluwer Academic, 1996), pp. 189-192.
  5. C. Koch and S. Ullman, "Shifts in selective visual attention: towards the underlying neural circuitry," Hum. Neurobiol. 4, 219-227 (1985).
  6. J. M. Wolfe, "Moving towards solutions to some enduring controversies in visual search," Trends Cogn. Sci. 7, 70-76 (2003).
    [CrossRef]
  7. A. Oliva, A. Torralba, M. S. Castelhano, and J. M. Henderson, "Top-down control of visual attention in object detection," in Proceedings of IEEE International Conference on Image Processing (IEEE, 2003), pp. 253-256.
  8. S. Palmer, Vision Science (MIT Press, 2002).
  9. L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254-1259 (1998).
    [CrossRef]
  10. L. Itti and C. Koch, "A comparison of feature combination strategies for saliency-based visual attention systems," Proc. SPIE 3644, 473-482 (1999).
    [CrossRef]
  11. D. Parkhurst, K. Law, and E. Neibur, "Modeling the role of salience in the allocation of overt visual attention," Vision Res. 42, 107-123 (2002).
    [CrossRef] [PubMed]
  12. O. Le Meur, P. Le Callet, D. Barba, D. Thoreau, and E. Francois, "From low level perception to high level perception, a coherent approach for visual attention modeling," Proc. SPIE 5292, 284-295 (2004).
    [CrossRef]
  13. R. J. Peters, A. Iyer, L. Itti, and C. Koch, "Components of bottom-up gaze allocation in natural images," Vision Res. 45, 2397-2416 (2005).
    [CrossRef] [PubMed]
  14. R. P. N. Rao, G. J. Zelinsky, M. M. Hayhoe, and D. H. Ballard, "Eye movements in iconic visual search," Vision Res. 42, 1447-1463 (2002).
    [CrossRef] [PubMed]
  15. B. W. Tatler, R. J. Baddeley, and I. D. Gilchrist, "Visual correlates of fixation selection: effects of scale and time," Vision Res. 45, 643-659 (2005).
    [CrossRef]
  16. H. L. Kundel, C. F. Nodine, and E. A. Krupkinski, "Searching for lung nodules: visual dwell indicates locations of false-positive and false negative decisions," Invest. Radiol. 24, 472-478 (1989).
    [CrossRef] [PubMed]
  17. E. A. Krupinski and R. M. Nishikawa, "Comparison of eye position data versus computer identified microcalcification clusters on mammograms," Med. Phys. 24, 17-23 (1997).
    [CrossRef] [PubMed]
  18. P. K. White, T. L. Hutson, and T. E. Hutchinson, "Modeling human eye behavior during mammographic scanning: preliminary results," IEEE Trans. Syst. Man Cybern. 27, 494-505 (1997).
    [CrossRef]
  19. C. F. Nodine, "Blinded review of retrospectively visible unreported breast cancers: an eye-position analysis," Radiology 221, 122-129 (2001).
    [CrossRef] [PubMed]
  20. L. Dempere-Marco, X.-P. Hu, S. L. S. MacDonald, S. M. Ellis, D. M. Hansell, and G.-Z. Yang, "The use of visual search for knowledge gathering in image decision support," IEEE Trans. Med. Imaging 21, 741-754 (2002).
    [CrossRef] [PubMed]
  21. X.-P. Hu, L. Dempere-Marco, and G.-Z. Yang, "Hot spot detection based on feature space representation of visual search in medical imaging," in Proceedings of IEEE Conference on Information Technology Applications in Biomedicine (IEEE, 2003), pp. 261-264.
  22. S. Samuel, H. L. Kundel, C. F. Nodine, and L. C. Toto, "Mechanism of satisfaction of search: eye position recordings in the reading of chest radiographs," Radiology 194, 895-902 (1995).
    [PubMed]
  23. E. A. Krupinski, "Medical image perception: evaluating the role of experience," Proc. SPIE 3959, 281-289 (2000).
    [CrossRef]
  24. C. Mello-Thoms, S. Dunn, C. F. Nodine, H. L. Kundel, and S. P. Weinstein, "The perception of breast cancer: what differentiates missed from reported cancers in mammography?" Acad. Radiol. 9, 1004-1012 (2002).
    [CrossRef] [PubMed]
  25. C. Mello-Thoms, S. Dunn, C. F. Nodine, and H. L. Kundel, "The perception of breast cancers--a spatial frequency analysis of what differentiates missed from reported cancers," IEEE Trans. Med. Imaging 22, 1297-1306 (2003).
    [CrossRef] [PubMed]
  26. J. Lubin, "A visual discrimination model for imaging system design and evaluation," in Vision Models for Target Detection and Recognition, E.Peli, ed. (World Scientific, 1995), pp. 245-283.
  27. S. Daly, "The visible difference predictor: an algorithm for the assessment of image fidelity," in Digital Images and Human Vision, A.B.Watson, ed. (MIT Press, 1993), pp. 179-206.
  28. P. C. Teo and D. J. Heeger, "Perceptual image distortion," in Proceedings of IEEE International Conference on Image Processing (IEEE, 1994), pp. 982-986.
  29. A. B. Watson and J. A. Solomon, "Model of visual contrast gain control and pattern masking," J. Opt. Soc. Am. A 14, 2379-2391 (1997).
    [CrossRef]
  30. W. T. Freeman and E. H. Adelson, "The design and use of steerable filters," IEEE Trans. Pattern Anal. Mach. Intell. 13, 891-906 (1991).
    [CrossRef]
  31. P. J. Burt and E. H. Adelson, "The Laplacian pyramid as a compact image code," IEEE Trans. Commun. 31, 532-540 (1983).
    [CrossRef]
  32. A. B. Watson, "The cortex transform: rapid computation of simulated neural images," Comput. Vis. Graph. Image Process. 39, 311-327 (1987).
    [CrossRef]
  33. E. Peli, "Feature detection algorithm based on a visual system model," Proc. IEEE 90, 78-93 (2002).
    [CrossRef]
  34. A. P. Bradley, "A wavelet visible difference predictor," IEEE Trans. Image Process. 8, 717-730 (1999).
    [CrossRef]
  35. J. Oh, S. I. Woolley, T. N. Arvanitis, and J. N. Townend, "A multistage perceptual quality assessment for compressed digital angiogram images," IEEE Trans. Med. Imaging 20, 1351-1361 (2001).
    [CrossRef]
  36. T. S. Lee, "Image representation using 2D Gabor wavelets," IEEE Trans. Pattern Anal. Mach. Intell. 18, 959-971 (1996).
    [CrossRef]
  37. J. G. Daugman, "Two-dimensional spectral analysis of cortical receptive field profiles," Vision Res. 20, 847-856 (1980).
    [CrossRef] [PubMed]
  38. T. S. Lee, "Representational strategy in the visual cortex," in Proceedings of IEEE International Conference on Image Processing (IEEE, 1994), pp. 590-594.
  39. S. S. Stevens, "To honor Fechner and repeal his law," Science 133, 80-86 (1961).
    [CrossRef] [PubMed]
  40. J. G. Daugman, "Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters," J. Opt. Soc. Am. A 2, 1160-1169 (1985).
    [CrossRef] [PubMed]
  41. G. M. Haley and B. S. Manjunath, "Rotation-invariant texture classification using a complete space-frequency model," IEEE Trans. Image Process. 8, 255-269 (1999).
    [CrossRef]
  42. R. Rosenholtz, "A simple saliency model predicts a number of motion popout phenomena," Vision Res. 39, 3157-3163 (1999).
    [CrossRef]
  43. J. P. Collomosse and P. M. Hall, "Painterly rendering using image salience," in Proceedings of IEEE Conference Eurographics UK (IEEE, 2002), pp. 122-128.
    [CrossRef]
  44. N. A. Macmillan and C. D. Creelman, Detection Theory: a User's Guide (Lawrence Erlbaum, 2005).
  45. M. J. Mayer and C. W. Tyler, "Invariance of the slope of the psychometric function with spatial summation," J. Opt. Soc. Am. A 3, 1166-1172 (1986).
    [CrossRef] [PubMed]
  46. H. Kundel, University of Pennsylvania, Philadelphia, Pa., 19104 (personal communication, 2003).
  47. R. G. Swensson, "Unified measurement of observer performance in detecting and localizing target objects on images," Med. Phys. 23, 1709-1725 (1996).
    [CrossRef] [PubMed]
  48. H. L. Kundel, "Visual search in medical images," in Handbook of Medical Imaging, J.Beutel, H.L.Kundel, and R.Van Metter, eds. (SPIE Press, 2000), pp. 837-858.
  49. C. A. Roe and C. E. Metz, "Variance-component modeling in the analysis of receiver operating characteristic index estimate," Acad. Radiol. 4, 587-600 (1997).
    [CrossRef] [PubMed]
  50. N. A. Obuchowski, "Multireader receiver operating characteristic studies: a comparison of study designs," Acad. Radiol. 2, 709-716 (1995).
    [CrossRef] [PubMed]
  51. S. V. Beiden, M. A. Maloof, and R. F. Wagner, "A general model for finite-sample effects in training and testing of competing classifiers," IEEE Trans. Pattern Anal. Mach. Intell. 25, 1561-1569 (2003).
    [CrossRef]

2005

R. J. Peters, A. Iyer, L. Itti, and C. Koch, "Components of bottom-up gaze allocation in natural images," Vision Res. 45, 2397-2416 (2005).
[CrossRef] [PubMed]

B. W. Tatler, R. J. Baddeley, and I. D. Gilchrist, "Visual correlates of fixation selection: effects of scale and time," Vision Res. 45, 643-659 (2005).
[CrossRef]

2004

O. Le Meur, P. Le Callet, D. Barba, D. Thoreau, and E. Francois, "From low level perception to high level perception, a coherent approach for visual attention modeling," Proc. SPIE 5292, 284-295 (2004).
[CrossRef]

2003

J. M. Wolfe, "Moving towards solutions to some enduring controversies in visual search," Trends Cogn. Sci. 7, 70-76 (2003).
[CrossRef]

C. Mello-Thoms, S. Dunn, C. F. Nodine, and H. L. Kundel, "The perception of breast cancers--a spatial frequency analysis of what differentiates missed from reported cancers," IEEE Trans. Med. Imaging 22, 1297-1306 (2003).
[CrossRef] [PubMed]

S. V. Beiden, M. A. Maloof, and R. F. Wagner, "A general model for finite-sample effects in training and testing of competing classifiers," IEEE Trans. Pattern Anal. Mach. Intell. 25, 1561-1569 (2003).
[CrossRef]

2002

E. Peli, "Feature detection algorithm based on a visual system model," Proc. IEEE 90, 78-93 (2002).
[CrossRef]

L. Dempere-Marco, X.-P. Hu, S. L. S. MacDonald, S. M. Ellis, D. M. Hansell, and G.-Z. Yang, "The use of visual search for knowledge gathering in image decision support," IEEE Trans. Med. Imaging 21, 741-754 (2002).
[CrossRef] [PubMed]

C. Mello-Thoms, S. Dunn, C. F. Nodine, H. L. Kundel, and S. P. Weinstein, "The perception of breast cancer: what differentiates missed from reported cancers in mammography?" Acad. Radiol. 9, 1004-1012 (2002).
[CrossRef] [PubMed]

D. Parkhurst, K. Law, and E. Neibur, "Modeling the role of salience in the allocation of overt visual attention," Vision Res. 42, 107-123 (2002).
[CrossRef] [PubMed]

R. P. N. Rao, G. J. Zelinsky, M. M. Hayhoe, and D. H. Ballard, "Eye movements in iconic visual search," Vision Res. 42, 1447-1463 (2002).
[CrossRef] [PubMed]

2001

C. F. Nodine, "Blinded review of retrospectively visible unreported breast cancers: an eye-position analysis," Radiology 221, 122-129 (2001).
[CrossRef] [PubMed]

J. Oh, S. I. Woolley, T. N. Arvanitis, and J. N. Townend, "A multistage perceptual quality assessment for compressed digital angiogram images," IEEE Trans. Med. Imaging 20, 1351-1361 (2001).
[CrossRef]

2000

E. A. Krupinski, "Medical image perception: evaluating the role of experience," Proc. SPIE 3959, 281-289 (2000).
[CrossRef]

1999

A. P. Bradley, "A wavelet visible difference predictor," IEEE Trans. Image Process. 8, 717-730 (1999).
[CrossRef]

L. Itti and C. Koch, "A comparison of feature combination strategies for saliency-based visual attention systems," Proc. SPIE 3644, 473-482 (1999).
[CrossRef]

G. M. Haley and B. S. Manjunath, "Rotation-invariant texture classification using a complete space-frequency model," IEEE Trans. Image Process. 8, 255-269 (1999).
[CrossRef]

R. Rosenholtz, "A simple saliency model predicts a number of motion popout phenomena," Vision Res. 39, 3157-3163 (1999).
[CrossRef]

1998

L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254-1259 (1998).
[CrossRef]

1997

E. A. Krupinski and R. M. Nishikawa, "Comparison of eye position data versus computer identified microcalcification clusters on mammograms," Med. Phys. 24, 17-23 (1997).
[CrossRef] [PubMed]

P. K. White, T. L. Hutson, and T. E. Hutchinson, "Modeling human eye behavior during mammographic scanning: preliminary results," IEEE Trans. Syst. Man Cybern. 27, 494-505 (1997).
[CrossRef]

C. A. Roe and C. E. Metz, "Variance-component modeling in the analysis of receiver operating characteristic index estimate," Acad. Radiol. 4, 587-600 (1997).
[CrossRef] [PubMed]

A. B. Watson and J. A. Solomon, "Model of visual contrast gain control and pattern masking," J. Opt. Soc. Am. A 14, 2379-2391 (1997).
[CrossRef]

1996

R. G. Swensson, "Unified measurement of observer performance in detecting and localizing target objects on images," Med. Phys. 23, 1709-1725 (1996).
[CrossRef] [PubMed]

T. S. Lee, "Image representation using 2D Gabor wavelets," IEEE Trans. Pattern Anal. Mach. Intell. 18, 959-971 (1996).
[CrossRef]

1995

N. A. Obuchowski, "Multireader receiver operating characteristic studies: a comparison of study designs," Acad. Radiol. 2, 709-716 (1995).
[CrossRef] [PubMed]

S. Samuel, H. L. Kundel, C. F. Nodine, and L. C. Toto, "Mechanism of satisfaction of search: eye position recordings in the reading of chest radiographs," Radiology 194, 895-902 (1995).
[PubMed]

1991

W. T. Freeman and E. H. Adelson, "The design and use of steerable filters," IEEE Trans. Pattern Anal. Mach. Intell. 13, 891-906 (1991).
[CrossRef]

1989

H. L. Kundel, C. F. Nodine, and E. A. Krupkinski, "Searching for lung nodules: visual dwell indicates locations of false-positive and false negative decisions," Invest. Radiol. 24, 472-478 (1989).
[CrossRef] [PubMed]

J. M. Wolfe, K. R. Cave, and S. L. Franzel, "An alternative to the feature integration model for visual search," J. Exp. Psychol. Hum. Percept. Perform. 15, 419-433 (1989).
[CrossRef] [PubMed]

1987

A. B. Watson, "The cortex transform: rapid computation of simulated neural images," Comput. Vis. Graph. Image Process. 39, 311-327 (1987).
[CrossRef]

1986

1985

1983

P. J. Burt and E. H. Adelson, "The Laplacian pyramid as a compact image code," IEEE Trans. Commun. 31, 532-540 (1983).
[CrossRef]

1980

J. G. Daugman, "Two-dimensional spectral analysis of cortical receptive field profiles," Vision Res. 20, 847-856 (1980).
[CrossRef] [PubMed]

A. Treisman and G. Gelade, "A feature-integration theory of attention," Cogn. Psychol. 12, 97-136 (1980).
[CrossRef] [PubMed]

1976

H. L. Kundel and G. Revesz, "Lesion conspicuity, structured noise, and film reader error," Am. J. Roentgenol. 126, 1233-1238 (1976).

1961

S. S. Stevens, "To honor Fechner and repeal his law," Science 133, 80-86 (1961).
[CrossRef] [PubMed]

Acad. Radiol.

C. Mello-Thoms, S. Dunn, C. F. Nodine, H. L. Kundel, and S. P. Weinstein, "The perception of breast cancer: what differentiates missed from reported cancers in mammography?" Acad. Radiol. 9, 1004-1012 (2002).
[CrossRef] [PubMed]

C. A. Roe and C. E. Metz, "Variance-component modeling in the analysis of receiver operating characteristic index estimate," Acad. Radiol. 4, 587-600 (1997).
[CrossRef] [PubMed]

N. A. Obuchowski, "Multireader receiver operating characteristic studies: a comparison of study designs," Acad. Radiol. 2, 709-716 (1995).
[CrossRef] [PubMed]

Am. J. Roentgenol.

H. L. Kundel and G. Revesz, "Lesion conspicuity, structured noise, and film reader error," Am. J. Roentgenol. 126, 1233-1238 (1976).

Cogn. Psychol.

A. Treisman and G. Gelade, "A feature-integration theory of attention," Cogn. Psychol. 12, 97-136 (1980).
[CrossRef] [PubMed]

Comput. Vis. Graph. Image Process.

A. B. Watson, "The cortex transform: rapid computation of simulated neural images," Comput. Vis. Graph. Image Process. 39, 311-327 (1987).
[CrossRef]

Hum. Neurobiol.

C. Koch and S. Ullman, "Shifts in selective visual attention: towards the underlying neural circuitry," Hum. Neurobiol. 4, 219-227 (1985).

IEEE Trans. Commun.

P. J. Burt and E. H. Adelson, "The Laplacian pyramid as a compact image code," IEEE Trans. Commun. 31, 532-540 (1983).
[CrossRef]

IEEE Trans. Image Process.

A. P. Bradley, "A wavelet visible difference predictor," IEEE Trans. Image Process. 8, 717-730 (1999).
[CrossRef]

G. M. Haley and B. S. Manjunath, "Rotation-invariant texture classification using a complete space-frequency model," IEEE Trans. Image Process. 8, 255-269 (1999).
[CrossRef]

IEEE Trans. Med. Imaging

J. Oh, S. I. Woolley, T. N. Arvanitis, and J. N. Townend, "A multistage perceptual quality assessment for compressed digital angiogram images," IEEE Trans. Med. Imaging 20, 1351-1361 (2001).
[CrossRef]

C. Mello-Thoms, S. Dunn, C. F. Nodine, and H. L. Kundel, "The perception of breast cancers--a spatial frequency analysis of what differentiates missed from reported cancers," IEEE Trans. Med. Imaging 22, 1297-1306 (2003).
[CrossRef] [PubMed]

L. Dempere-Marco, X.-P. Hu, S. L. S. MacDonald, S. M. Ellis, D. M. Hansell, and G.-Z. Yang, "The use of visual search for knowledge gathering in image decision support," IEEE Trans. Med. Imaging 21, 741-754 (2002).
[CrossRef] [PubMed]

IEEE Trans. Pattern Anal. Mach. Intell.

T. S. Lee, "Image representation using 2D Gabor wavelets," IEEE Trans. Pattern Anal. Mach. Intell. 18, 959-971 (1996).
[CrossRef]

W. T. Freeman and E. H. Adelson, "The design and use of steerable filters," IEEE Trans. Pattern Anal. Mach. Intell. 13, 891-906 (1991).
[CrossRef]

L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254-1259 (1998).
[CrossRef]

S. V. Beiden, M. A. Maloof, and R. F. Wagner, "A general model for finite-sample effects in training and testing of competing classifiers," IEEE Trans. Pattern Anal. Mach. Intell. 25, 1561-1569 (2003).
[CrossRef]

IEEE Trans. Syst. Man Cybern.

P. K. White, T. L. Hutson, and T. E. Hutchinson, "Modeling human eye behavior during mammographic scanning: preliminary results," IEEE Trans. Syst. Man Cybern. 27, 494-505 (1997).
[CrossRef]

Invest. Radiol.

H. L. Kundel, C. F. Nodine, and E. A. Krupkinski, "Searching for lung nodules: visual dwell indicates locations of false-positive and false negative decisions," Invest. Radiol. 24, 472-478 (1989).
[CrossRef] [PubMed]

J. Exp. Psychol. Hum. Percept. Perform.

J. M. Wolfe, K. R. Cave, and S. L. Franzel, "An alternative to the feature integration model for visual search," J. Exp. Psychol. Hum. Percept. Perform. 15, 419-433 (1989).
[CrossRef] [PubMed]

J. Opt. Soc. Am. A

Med. Phys.

R. G. Swensson, "Unified measurement of observer performance in detecting and localizing target objects on images," Med. Phys. 23, 1709-1725 (1996).
[CrossRef] [PubMed]

E. A. Krupinski and R. M. Nishikawa, "Comparison of eye position data versus computer identified microcalcification clusters on mammograms," Med. Phys. 24, 17-23 (1997).
[CrossRef] [PubMed]

Proc. IEEE

E. Peli, "Feature detection algorithm based on a visual system model," Proc. IEEE 90, 78-93 (2002).
[CrossRef]

Proc. SPIE

L. Itti and C. Koch, "A comparison of feature combination strategies for saliency-based visual attention systems," Proc. SPIE 3644, 473-482 (1999).
[CrossRef]

O. Le Meur, P. Le Callet, D. Barba, D. Thoreau, and E. Francois, "From low level perception to high level perception, a coherent approach for visual attention modeling," Proc. SPIE 5292, 284-295 (2004).
[CrossRef]

E. A. Krupinski, "Medical image perception: evaluating the role of experience," Proc. SPIE 3959, 281-289 (2000).
[CrossRef]

Radiology

S. Samuel, H. L. Kundel, C. F. Nodine, and L. C. Toto, "Mechanism of satisfaction of search: eye position recordings in the reading of chest radiographs," Radiology 194, 895-902 (1995).
[PubMed]

C. F. Nodine, "Blinded review of retrospectively visible unreported breast cancers: an eye-position analysis," Radiology 221, 122-129 (2001).
[CrossRef] [PubMed]

Science

S. S. Stevens, "To honor Fechner and repeal his law," Science 133, 80-86 (1961).
[CrossRef] [PubMed]

Trends Cogn. Sci.

J. M. Wolfe, "Moving towards solutions to some enduring controversies in visual search," Trends Cogn. Sci. 7, 70-76 (2003).
[CrossRef]

Vision Res.

R. J. Peters, A. Iyer, L. Itti, and C. Koch, "Components of bottom-up gaze allocation in natural images," Vision Res. 45, 2397-2416 (2005).
[CrossRef] [PubMed]

R. P. N. Rao, G. J. Zelinsky, M. M. Hayhoe, and D. H. Ballard, "Eye movements in iconic visual search," Vision Res. 42, 1447-1463 (2002).
[CrossRef] [PubMed]

B. W. Tatler, R. J. Baddeley, and I. D. Gilchrist, "Visual correlates of fixation selection: effects of scale and time," Vision Res. 45, 643-659 (2005).
[CrossRef]

D. Parkhurst, K. Law, and E. Neibur, "Modeling the role of salience in the allocation of overt visual attention," Vision Res. 42, 107-123 (2002).
[CrossRef] [PubMed]

J. G. Daugman, "Two-dimensional spectral analysis of cortical receptive field profiles," Vision Res. 20, 847-856 (1980).
[CrossRef] [PubMed]

R. Rosenholtz, "A simple saliency model predicts a number of motion popout phenomena," Vision Res. 39, 3157-3163 (1999).
[CrossRef]

Other

J. P. Collomosse and P. M. Hall, "Painterly rendering using image salience," in Proceedings of IEEE Conference Eurographics UK (IEEE, 2002), pp. 122-128.
[CrossRef]

N. A. Macmillan and C. D. Creelman, Detection Theory: a User's Guide (Lawrence Erlbaum, 2005).

H. Kundel, University of Pennsylvania, Philadelphia, Pa., 19104 (personal communication, 2003).

H. L. Kundel, "Visual search in medical images," in Handbook of Medical Imaging, J.Beutel, H.L.Kundel, and R.Van Metter, eds. (SPIE Press, 2000), pp. 837-858.

T. S. Lee, "Representational strategy in the visual cortex," in Proceedings of IEEE International Conference on Image Processing (IEEE, 1994), pp. 590-594.

X.-P. Hu, L. Dempere-Marco, and G.-Z. Yang, "Hot spot detection based on feature space representation of visual search in medical imaging," in Proceedings of IEEE Conference on Information Technology Applications in Biomedicine (IEEE, 2003), pp. 261-264.

J. Lubin, "A visual discrimination model for imaging system design and evaluation," in Vision Models for Target Detection and Recognition, E.Peli, ed. (World Scientific, 1995), pp. 245-283.

S. Daly, "The visible difference predictor: an algorithm for the assessment of image fidelity," in Digital Images and Human Vision, A.B.Watson, ed. (MIT Press, 1993), pp. 179-206.

P. C. Teo and D. J. Heeger, "Perceptual image distortion," in Proceedings of IEEE International Conference on Image Processing (IEEE, 1994), pp. 982-986.

A. Oliva, A. Torralba, M. S. Castelhano, and J. M. Henderson, "Top-down control of visual attention in object detection," in Proceedings of IEEE International Conference on Image Processing (IEEE, 2003), pp. 253-256.

S. Palmer, Vision Science (MIT Press, 2002).

J. M. Wolfe and G. Gancarz, "Guided search 3.0: A model of visual search catches up with Jay Enoch 40 years later," in Basic and Clinical Applications of Vision Science, V.Lakshminarayanan, ed. (Kluwer Academic, 1996), pp. 189-192.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (8)

Fig. 1
Fig. 1

Block diagram showing the model used to form the salience maps and scalar salience image quality measure. CSF, contrast sensitivity function.

Fig. 2
Fig. 2

Normalized nonlinear model response for an 8 ‐ bit gray-level input image.

Fig. 3
Fig. 3

Left, Gabor magnitude response with DC response. Right, Gabor magnitude response with DC response removed. Note the extended bandwidth on the right, which leads to less feature localization per channel.

Fig. 4
Fig. 4

Zone plate decomposition using Gabor filters. Top, 2D zone plate. Row 1, zone plate after filtering with channel ω 0 = 13.2   cycles deg . Row 2, zone plate after filtering with channel ω 0 = 7.9   cycles deg . Row 3, zone plate after filtering with channel ω 0 = 2.6   cycles deg . Orientations from left to right for all rows are: 0°, 36°, 90°, and 144°, respectively. Note that the aliasing present in the zone plate is a result of undersampling during reproduction.

Fig. 5
Fig. 5

Salience map examples. Left, original true positive mammogram ROI. Right, salience maps for two filter channels. This example illustrates the scale-based feature selectivity of the salience metric. Salience features associated with the lesion located in the lower right-hand corner are readily apparent in the channel 4 salience map ( ω 0 = 4.6   cycles deg ) (right). Other features are more pronounced in the channel 2 salience map ( ω 0 = 13.2   cycles deg ) (middle).

Fig. 6
Fig. 6

Mammogram showing all clusters > 0.8 s from two readers (in white). Ground truth for TP is shown in black. Arrows indicate FP clusters identified by one reader.

Fig. 7
Fig. 7

Example TP ROI (top) and four of its salience maps. Left column top row, 22.3   cycles deg ; right column, top row, 13.2   cycles deg ; left column, bottom row, 4.6   cycles deg ; right column, bottom row, 1.0   cycles deg .

Fig. 8
Fig. 8

Regression curves for the top six readers, 95% confidence intervals for top-ranked reader (dashed curves); triangles locate FPs and wrong locations for the top six readers.

Tables (3)

Tables Icon

Table 1 Statistically Different Bonferroni Simultaneous Comparisons (95% Confidence Interval) of the Salience Metric by Class Type and Reader Experience a

Tables Icon

Table 2 Bonferroni Simultaneous Comparisons for Statistically Different Filter Channels as a Function of ROI Class Type a

Tables Icon

Table 3 Time-to-First-Hit Regression Statistics and Results a

Equations (11)

Equations on this page are rendered with MathJax. Learn more.

ψ ( x , y , ω 0 , θ ) = ω 0 2 π κ exp { ω 0 2 8 κ 2 [ ( 2 x r ) 2 + y r 2 ] } × { exp [ i ω 0 ( x cos θ + y sin θ ) ] exp ( κ 2 ) } .
x r = ( x x 0 ) cos θ + ( y y 0 ) sin θ ,
y r = ( x x 0 ) sin θ + ( y y 0 ) cos θ ,
d C M ( i , j , θ m , ρ n ) = k d p ( i , j , θ m , ρ n ) β + θ , ρ d q ( i , j , θ m , ρ n ) ,
p ( x ) = 1 ( 2 π ) d 2 Σ 1 2 exp [ 1 2 ( x μ ) T Σ 1 ( x μ ) ] ,
d n ( i , j ) = [ x ( i , j ) n μ n ] T Σ n 1 [ x ( i , j ) n μ n ]
D n = [ i , j d n 2 ( i , j ) M N ] 1 2 .
F ( x ) = 1 e ( x a ) b ,
D i j l ( θ ) n = 1 M k l m = 1 M ( D i j k ) m .
D i j l ( θ ) n = [ μ + α i + β j + θ l + ( α θ ) i l + ( β θ ) j l + ε i j l ] n .
Var [ D i j l ( θ ) n ] = [ σ 2 + σ β 2 + σ θ 2 + σ α θ 2 + σ β θ 2 ] n ,

Metrics