A wavelet-based algorithm for detecting clustered microcalcifications in digital mammograms

A computerized scheme to detect clustered microcalcifications in digital ma mmograms has been developed. Detection of individual microcalcifications in regions. of interest (ROIs) was also performed. The mammograms were previo usly classified into fatty and dense, according to their breast tissue. The most appropriate wavelet basis and reconstruction levels were selected. To select the wavelet basis, 40 profiles of microcalcifications were decompos ed and reconstructed using different types of wavelet functions and differe nt combinations of wavelet coefficients. The symlets with a basis of length 8 were chosen for fatty tissue. For dense tissue, the Daubechies' wavelets with a four-element basis were employed. Two methods to detect individual microcalcifications were evaluated: (a) two-dimensional wavelet transform, and (b) one-dimensional wavelet transform. The second technique yielded the best results, and was used to detect clustered microcalcifications in the complete mammogram. When detecting individual microcalcifications by using two-dimensional wavelet transform we have obtained, for fatty ROIs, a sensi tivity of 71.11% at a false positive: rate of 7.13 per image. For dense ROI s the sensitivity was 60.76% and the false positive rate, 7.33. The areas ( Al) under the AFROC curves were 0.33+/-0.04 and 0.28+/-0.02, respectively. The one-dimensional wavelet transform method yielded 80.44% of sensitivity and 6.43 false positives per image (A(1)=0.39+/-0.03) for fatty ROIs, and 6 2.17% and 5.82 false positives per image (A(1) =0.37+/-0.02) for dense ROIs . For the detection of clusters of microcalcifications in the entire mammog ram, the sensitivity was 80.00% with 0.94 false positives per image (A(1)=0 .77+/-0.09) for fatty mammograms, and 72.85% of sensitivity at a false posi tive detection rate of 2.21 per image (A(1)=0.64+/-0.07) for dense mammogra ms. Globally, a sensitivity of 76.43% at a false positive detection rate of 1.57 per image was obtained. (C) 1999 American Association of Physicists i n Medicine. [S0094-2405(99)01407-8].