Modification of Mammograms for Detection and Early Diagnosis of Breast Cancer Using Wavelet Techniques and Neural Networks
A R Zou Alghadr Asli, Z. Maghsoodzadeh · Iranian journal of electrical and computer engineering · 2006
In this paper, some modifications of mammography slides for the detection of microcalcifications are explained. This can be achieved in two steps. First, to detect the abnormal pixels, wavelet transformation and two statistical properties are used. Second, a set of ten characteristics are applied to images to cancel some erroneous pixels and resulting in a very low error percentage. Therefore, in both steps, a neural network with a hidden layer, which is trained by some vectors, is used. The results are shown in free response operating characteristics (FROC) curves. For more understanding, a typical process will be explained in the paper. It should be mentioned that the main difference of this research with previous ones, in addition to improved algorithms, is in the databases, which in our case are the images of the local patients at Dr. Faghihi hospital in Shiraz that made this research an applicable work.