Mammogram segmentation by contour searching and massive lesion classification with neural network
Francesco Fauci, S. Bagnasco, R. Bellotti, Donato Cascio, Sorin Cristian Cheran, Francesco De Carlo, Giorgio De Nunzio, Maria Evelina Fantacci, Giustina Forni, A. Lauria, E. López Torres, Rosario Magro, Giovanni Luca Masala, P. Oliva, Maurizio Quarta, G. Raso, Alessandra Retico, Sabina Tangaro · IEEE Symposium Conference Record Nuclear Science 2004. · 2005
The mammography is the most effective procedure for an early diagnosis of the breast cancer. In this paper, an algorithm for detecting massive lesions in mammographic images will be presented. The database consists of 3762 digital images acquired in several hospitals belonging to the MAGIC- 5 collaboration. A reduction of the surface under investigation is achieved, without loss of meaningful information, through segmentation of the whole image, by means of a ROI Hunter algorithm. In the following classification step, feature extraction plays a fundamental role: some features give geometrical information, other ones provide shape parameters. Once the features are computed for each ROI, they are used as inputs to a supervised neural network with momentum. The output neuron provides the probability that the ROI is pathological or not. Results are provided in terms of ROC and FROC curves; the area under the ROC curve was found to be AZ= ( 85.6 ± 0.8) %. This software is included in the CAD station actually working in the hospitals belonging to the MAGIC-5 Collaboration.