Breast Mass Segmentation In Mammography Using Improved Dynamic Programming

The segmentation of breast mass is an important step not only in quantitative diagnosis but also in Computer-Aided Diagnosis (CAD) for the mammography. The objective of this study is to develop a reliable, reproducible and automatic segmentation method, which can provide the mass contours for quantitative analysis and also can be further utilized for feature extraction in CAD system. This automatic segmentation method is based on dynamic programming. Three features - edge strength, gray level and mass size were used to obtain the precise mass contour. To improve the segmentation accuracy, we introduced an adaptive mass radius determining method for each mass candidate instead of using the fixed radius for all masses to describe size and gray features. Besides, we proposed a boundary compensation method based on mean gray values in background avoiding contour departure of existing dynamic programming. In addition, we computed edge strength using local standard deviation, which can describe the edge information more clearly. In this study, we tested 120 mammography cases consisting of 178 mass regions of interests (ROIs). The cases were randomly selected from our cooperating hospitals in China. The golden standard was obtained by manually drawing the mass contour of each case according to the doctor's opinion. All the cases have also been segmented by our algorithm, and the mean overlap percentage between the proposed method and the golden standard was 0.70 +/- 0.15. The mean overlap percentage of our methods was improved 5 percent compared to that of existing dynamic programming. The experimental results showed that our improved dynamic programming method could segment most breast masses with good robustness to mass size, and it was especially effective for the mass close to image edge. However, for adhesive masses, the method needs to be further improved.