Single and multiscale detection of masses in digital mammograms

Abstract

Scale is an important issue in the automated detection of masses in mammograms, due to the range of possible sizes masses can have. In this work, it was examined if detection of masses can be done at a single scale, or whether it is more appropriate to use the output of the detection method at different scales in a multiscale scheme. Three different pixel-based mass-detection methods were used for this purpose. The first method is based on convolution 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 approach, 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 were confirmed by experiments on a set of 71 cases (132 mammograms) containing a malignant tumor. The performance of each method in a multiscale scheme was similar to the performance at the optimal single scale. A slight improvement was found for the correlation method when the output of different scales was combined. This was especially evident at low specificity levels. The correlation method and the gradient-orientation-analysis method have similar performances. A sensitivity of approximately 75% is reached at a level of one false positive per image. The method based on convolution with the Laplacian of the Gaussian performed considerably worse, in both a single and multiscale scheme.

Abnormalities Detection in Digital Mammography Using Template Matching

“…Brake et al in 1999 [12] proposed a multi-scale approach which we use in our study. Multiple templates of different sizes are used and the correlation to each template is calculated.…”

Detection of Cancerous Masses in Mammograms by Template Matching: Optimization of Template Brightness Distribution by Means of Evolutionary Algorithm

“…For example, te Brake and Karssemeijer [15] extend the circular template to 1.3R, where R is the radius of the model of the lesion, and brightness of the ring surrounding the model is zero. A more general template using a sector-form model is considered by Hatanaka et al [16], who analyze detection of masses with a partial loss of region in the vicinity of film edge.…”

“…In that paper, tests are made on 17 mammograms containing circumscribed masses. The paper by te Brake and Karssemeijer [15] considers a larger dataset of 132 mammograms containing malignant masses. The paper is mainly concerned with comparison of single and multiscale detection of masses and concludes that multiscale gives a slight improvement.…”

Marker-Controlled Watershed for Lesion Segmentation in Mammograms

“…Figure 3 shows this process. First, a rough region of the lesion is estimated by a template matching [21][22][23] and a thresholding method. The internal and external markers are then determined by distance transformation and morphological operation, respectively.…”