Abstract
Automated and accurate classiflcation of magnetic resonance (MR) brain images is a hot topic in the fleld of neuroimaging. Recently many difierent and innovative methods have been proposed to improve upon this technology. In this study, we presented a hybrid method based on forward neural network (FNN) to classify an MR brain image as normal or abnormal. The method flrst employed a discrete wavelet transform to extract features from images, and then applied the technique of principle component analysis (PCA) to reduce the size of the features. The reduced features were sent to an FNN, of which the parameters were optimized via an improved artiflcial bee colony (ABC) algorithm based on both fltness scaling and chaotic theory. We referred to the improved algorithm as scaled chaotic artiflcial bee colony (SCABC). Moreover, the K-fold stratifled cross validation was employed to avoid overfltting. In the experiment, we applied the proposed method on the data set of T2-weighted MRI images consisting of 66 brain images (18 normal and 48 abnormal). The proposed SCABC was compared with traditional training methods such as BP, momentum BP, genetic algorithm, elite genetic algorithm with migration, simulated annealing, and ABC. Each algorithm was run 20times to reduce randomness. The results show that our SCABC can obtain the least mean MSE and 100% classiflcation accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have