An automatic microcalcification detection system based on a hybrid neural network classifier

Abstract

A hybrid intelligent system is presented for the identification of microcalcification clusters in digital mammograms. The proposed method is based on a three-step procedure: (a) preprocessing and segmentation, (b) regions of interest (ROI) specification, and (c) feature extraction and classification. The reduction of false positive cases is performed using an intelligent system containing two subsystems: a rule-based and a neural network sub-system. In the first step of the classification schema 22 features are automatically computed which refer either to individual microcalcifications or to groups of them. Further reduction in the number of features is achieved through principal component analysis (PCA). The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve (A z ). In particular, the A z value for the Nijmegen dataset is 0.91 and for the MIAS is 0.92. The detection specificity of the two sets is 1.80 and 1.15 false positive clusters per image, at the sensitivity level higher than 0.90, respectively. #

A knowledge-based approach to assign breast cancer treatments in oncology units

“…The knowledge-based system intends to facilitate oncologists the maintenance of the knowledge base, thus guaranteeing that its content is updated and efficient decisions can be made. Some decision support systems (DSS) based on artificial intelligent techniques such as neural networks (Zhou et al, 2002), probabilistic events networks (Galán, Aguado, Diéz & Mira, 2002) or hybrid systems (Papadopoulos, Fotiadisb & Likas, 2002) have been put into oncology clinical practice. The main advantage of our knowledge-based system proposed in this paper with respect with those is the use of technologies that facilitate an easy maintenance of the knowledge base.…”

Improvement for detection of microcalcifications through clustering algorithms and artificial neural networks

“…An ANN can approximate the function of multiple inputs and outputs. As a consequence, ANNs can be used for a variety of applications, among which are classification in medical applications [3,5,23,35], descriptive modeling, clustering, function approximation, time series prediction [36] and sonar or radar detection [37]. Classification is one of the most frequently encountered decision-making tasks in human activity.…”

Simultaneous detection and segmentation for generic objects

“…More recent approaches are by Papadopoulos et al [80], Pal et al [79], Rizzi et al [91] and Yu et al [127]. Papadopoulos et al [80] improve a previous work [81] based on detecting microcalcifications using a neural network, by adding a preprocessing image enhancement step. In their work, different algorithms were tested, obtaining the best results when using the local range modification and the redundant discrete wavelet linear stretching and shrinkage enhancement algorithms.…”