Comparative analysis of interpolation methods for bilateral asymmetry

First step in bilateral asymmetry detection in mammographic image analysis is alignment of the left and right breast. Alignment may help radiologists in their search for signs of bilateral asymmetry as well as in comparison of corresponding regions in breasts with a computer aided detection system. Different interpolation methods may be used for breast alignment. We have compared nearest neighbor interpolation, bilinear interpolation, B-spline interpolation, cubic interpolation, cubic Schaum interpolation and o-Moms interpolation and their impact on mammographic images. We evaluated interpolation quality using mathematical similarity measures such as normalized 2-D cross-correlation coefficient, peak signal to noise ratio (PSNR) and structural similarity measure (SSIM). Normalized 2-D cross-correlation coefficient and SSIM have shown best results for B-spline interpolation while PSNR measure has shown best results for nearest neighbor interpolation. According to all three used measures the worst interpolation quality has cubic interpolation with kernel size of 8 × 8.