An analysis of perceptual errors in reading mammograms using quasi-local spatial frequency spectra

In this pilot study the authors examined areas on a mammogram that attracte d the visual attention of experienced mammographers and mammography fellows , as well as areas that were reported to contain a malignant lesion, and, b ased on their spatial frequency spectrum, they characterized these areas by the type of decision outcome that they yielded: true-positives (TP), false -positives (FP), true-negatives (TN), and false-negatives (FN). Five 2-view (craniocaudal and medial-lateral oblique) mammogram cases were examined by 8 experienced observers, and the eye position of the observers was tracked . The observers were asked to report the location and nature of any maligna nt lesions present in the case. The authors analyzed each area in which eit her the observer made a decision or in which the observer had prolonged (>1 ,000 ms) visual dwell using wavelet packets, and characterized these areas in terms of the energy contents of each spatial frequency band. It was show n that each decision outcome is characterized by a specific profile in the spatial frequency domain, and that these profiles are significantly differe nt from one another. As a consequence of these differences, the profiles ca n be used to determine which type of decision a given observer will make wh en examining the area. Computer-assisted perception correctly predicted up to 64.% of the TPs made by the observers, 77% of the FPs, and 70% of the TN s. Copyright (C) 2001 by W.B. Sounders Company.