What attracts the eye to the location of missed and reported breast cancers?

ABSTRACT

The primary detector of breast cancer is the human eye, as it examines mammograms searching for signs of the disease. Nonetheless, it has been shown that 10-30% of all cancers in the breast are not reported by the radiologist, even though most of these are visible retrospectively. Studies of eye position have shown that the eye tends to dwell in the locations of both reported and not reported cancers, indicating that the problem is not faulty visual search, but rather, that is primarily related to perceptual and decision making mechanisms. In this paper we model the areas that attracted the radiologists' visual attention when reading mammograms and that yielded a decision by the radiologist, being this decision overt or covert. We contrast the characteristics of areas that contain cancers that were reported from the ones that contain cancers that, albeit attracting attention, did not reach an internal conspicuity threshold to be reported.

REFERENCES

• 1: MARTIN, J. E., MOSKOWITZ, M. and MILBRATH, J. R. 1979. Breast cancers missed by mammography. American Journal of Roentology, 132, 737-758.
• 2: KRUPINSKI, E. A. and NODINE, C. F. 1994. Gaze duration predicts the location of missed lesions in mammography. In Digital Mammography. Elsevier Science B.V., The Netherlands.
• 3: KUNDEL, H. L, NODINE, C. F. and KRUPINSKI, E. A. 1989. Searching for lung nodules --- visual dwell indicates locations of false-positives and false-negative decisions. Investigative Radiology, 24, 472-478.
• 4: HOFFMAN, J. E. 1998. Visual attention and eye movements. In Attention (Studies in Cognition series).
• 5: KUNDEL, H. L., NODINE, C. F., TOTO, L. 1999. An eye-position study of the effects of a verbal prompt and pictorial backgrounds on the search for lung nodules in chest radiographs. In SPIE Proc Medical Imaging Conference, SPIE Press, San Diego, CA, 122-128.
• 6: NODINE, C. F., KUNDEL, H. L., LAUVER, S. C. and TOTO, L. C. 1996. The nature of expertise in searching mammograms for breast masses. In SPIE Proc Medical Imaging Conference, SPIE Press, San Diego, CA, 89-94.
• 7: KUNDEL, H. L., NODINE, C. F., THICKMAN, D., TOTO, L. 1987. Searching for lung nodules: A comparison of human performance with random and systematic scanning models. Investigative Radiology, 22, 417-422.
• 8: MALLAT, S. G. 1994. A wavelet tour of signal processing. Academic Press.
• 9: DAKIM, S. C. and HESS, R. F. 1998. Spatial-frequency tuning of visual contour integration. Journal of the Optical Society of America A, 15, 1486-1499.
• 10: MELLO-THOMS, C., DUNN, S. M., NODINE, C. F., KUNDEL, H. L., WEINSTEIN, S. P. 2001. The perception of breast cancer: what differentiates missed from reported cancers in mammography?.Academic Radiology (submitted).
• 11: HILLSTROM, A. P. 2000. Repetition effects in visual search. Perception and Psychophysics, 62, 800-817.
• 12: KUNDEL, H. L., and LAFOLLETTE, P. S. 1972. Visual search patterns and experience with radiological images. Radiology, 103, 523-526.
• 13: DE WOUWER, G. V., SCHEUNDERS, P., and VAN DYCK, D. 1999. Statistical texture characterization from discrete wavelet representations. IEEE Transactions on Image Processing, 8, 592-598.
• 14: BEX, P. J. and EDGAR, G. K. 1995. Shifts in the perceived location of a blurred edge increase with contrast. Perception and Psychophysics, 57, 1187-1189.
• 15: Dov Sagi, The psychophysics of texture segmentation, Early vision and beyond, Massachusetts Institute of Technology, Cambridge, MA, 1995
• 16: TOUSSAINT, G. T. 1978. The use of context in pattern recognition. Pattern Recognition, 10, 189-204.
• 17: NODINE, C. F., KUNDEL, H. L., and MELLO-THOMS, C. 1999. How experience and training influence mammography expertise. Academic Radiology, 6, 575-585.
• 18: RAYNER, K. 1998. Eye movements in reading and information processing: 20 years of research. Psychological Bulletin, 124, 372-422.
• 19: LOFTUS, G. R. 1981. Tachistoscopic simulations of eye fixations on pictures. Journal of Experimental Psychology: Human Learning and Memory, 7, 369-376.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Perceptual reasoning

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Texture