Single and multiscale detection of masses in digital mammograms

Scale is an important issue in the automated detection of masses in mammogr ams, due to the range of possible sizes masses can have. In this work, it w as examined if detection of masses can be done at a single scale, or whethe r it is more appropriate to use the output of the detection method at diffe rent scales in a multiscale scheme. Three different pixel-based mass-detect ion methods were used for this purpose. The first method is based an convol ution of a mammogram with the Laplacian of a Gaussian, the second method is based on correlation with a model of a mass, and the third is a new approa ch, based on statistical analysis of gradient-orientation maps. Experiments with simulated masses indicated that little can be gained by applying the methods at a number of scales. These results mere confirmed by experiments on a set of 71 cases (132 mammograms) containing a malignant tumor. The per formance of each method in a multiscale scheme was similar to the performan ce at the optimal single scale. A slight improvement was found for the corr elation method when the output of different scales was combined. This was e specially evident at low specificity levels. The correlation method and the gradient-orientation-analysis method have similar performances. A sensitiv ity of approximately 75% is reached at a level of one false positive per im age. The method based on convolution with the Laplacian of the Gaussian per formed considerably worse, in both a single and multiscale scheme.