Enhancement of CAD system for breast cancers by improvement of classifiers

Abstract

SUMMARYIn this paper, we propose a method to improve the accuracy of classifiers by replacing the connection between the output layer and the immediately preceding hidden layer with an optimal linear transformer. This approach is intended to improve the performance of a breast cancer image diagnosis assistance system. The proposed classifier is composed of a three-layer MLP (multilayer perceptron) and a Mahalanobis classifier. The MLP has only one output unit, and produces output for two categories. If it is assumed that the value from the hidden layer immediately preceding the output layer forms a multivariable normal distribution for each class, that is, a Gaussian distribution, then the optimal linear transformer is a classifier based on the generalized Mahalanobis distance. Thus, the optimal classification is realized in the MLP after learning in which the generalized Mahalanobis distance with the hidden layer immediately preceding the output layer as the input is examined, and classification is performed on the basis of the likelihood. The proposed breast cancer image diagnosis assistance system, the system using only the conventional Mahalanobis classifier, and the system using only the conventional MLP classifier are compared. The best results are given by the proposed method, and it is shown that the performance of the breast image diagnosis assistance system can be improved.

Development of a computer-aided classification system for cancer detection from digital mammograms

“…A fuzzy technique in conjunction with three features was used to detect a microcalcification pattern and a neural network to classify it into benign or malignant. Hagihara et al [10] presented a CAD for breast cancers by improvement of classifiers, used 5 features related to the concurrency matrix, 3 features related to the density histogram, and one feature related to the shape of the extracted region. Furuya et al [11] improvement of performance to discriminate malignant tumors from normal tissue on mammograms by feature selection and evaluation of features selection criteria, and used four types features, first-order statistics features, second-order statistic (cooccurrence) features, density features, and shape features.…”