Improving the performance of neural network in differentiation of breast tumors using wavelet transformation on dynamic MRI

Background: A computer aided diagnosis system was established using the wavelet transform and neural network to differentiate malignant from benign in a group of patients with histo-pathologically proved breast lesions based on the data derived independ­ently from time-intensity profile. Materials and Methods: The per­formance of the artificial neural network (ANN) was evaluated using a database with 105 patients' records each of which consisted of 8 quantitative parameters mostly derived from time-intensity profile using wavelet transform. These findings were encoded as features for a three-layered neural network to predict the outcome of biopsy. The network was trained and tested using the jack­knife method and its performance was then compared to that of the radiologists in terms of sensitiv­ity, specificity and accuracy using receiver operating characteristic curve (ROC) analysis. Results: The network was able to classify correctly the 84 original cases and yielded a comparable diagnostic accuracy (80%), compared to that of the radiologist (85%) by per­forming a constructive association between extracted quantitative data and correspond­ing pathological results (r=0.63, p<0.001). Conclusion: An ANN supported by wavelet transform can be trained to differentiate malignant from benign breast tumors with a reason­able degree of accuracy.