Automated detection of breast tumors using the asymmetry approach
Computers and Biomedical Research
Digital Image Processing
Connections between binary, gray-scale and fuzzy mathematical morphologies
Fuzzy Sets and Systems
Morphological Image Analysis: Principles and Applications
Morphological Image Analysis: Principles and Applications
Pattern Recognition, Third Edition
Pattern Recognition, Third Edition
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
An automatic microcalcification detection system based on a hybrid neural network classifier
Artificial Intelligence in Medicine
Morphological grayscale reconstruction in image analysis: applications and efficient algorithms
IEEE Transactions on Image Processing
Integrated Computer-Aided Engineering
Expert Systems with Applications: An International Journal
Impact of multiple clusters on neural classification of ROIs in digital mammograms
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Computers and Electrical Engineering
Classification of benign and malignant masses based on Zernike moments
Computers in Biology and Medicine
Twin support vector machines and subspace learning methods for microcalcification clusters detection
Engineering Applications of Artificial Intelligence
Saliency based mass detection from screening mammograms
Signal Processing
Hi-index | 0.08 |
In this paper we propose a new algorithm for the detection of clustered microcalcifications using mathematical morphology and artificial neural networks. Mathematical morphology provides tools for the extraction of microcalcifications even if the microcalcifications are located on a non-uniform background. Considering each mammogram as a topographic representation, each microcalcification appears as an elevation constituting a regional maximum. Morphological filters are applied, in order to remove: (a) noise and (b) regional maxima that do not correspond to calcifications. Each candidate object is marked as such, using a binary image. The original mammogram is used for the final feature extraction step. For the classification step we employ neural network classifiers. We review the performance of two multi-layer perceptrons (MLP) and two radial basis function neural networks (RBFNN) with different number of hidden nodes. The MLP with ten hidden nodes achieved the best classification score with a true positive detection rate of 94.7% and 0.27 false positives per image.