MAGNETIC RESONANCE BRAIN IMAGE CLASSIFICATION BY AN IMPROVED ARTIFICIAL BEE COLONY ALGORITHM
MAGNETIC RESONANCE BRAIN IMAGE CLASSIFICATION BY AN IMPROVED ARTIFICIAL BEE COLONY ALGORITHM
复制标题
DOI：
10.2528/pier11031709
复制
发表时间：
2011-01-01
影响因子：
6.7
通讯作者：
Wang, S.
中科院分区：
文献类型：
--
作者：
Zhang, Y.;Wu, L.;Wang, S.
脑磁共振图像的自动准确分类是神经影像学领域的研究热点。最近，已经提出了许多不同的和创新的方法来改进该技术。在这项研究中，我们提出了一种混合方法的基础上向前神经网络（FNN）的MR脑图像分类为正常或异常。该方法首先采用离散小波变换提取图像特征，然后应用主成分分析（PCA）技术减少特征的大小。将约简后的特征送入模糊神经网络，采用基于适应度尺度和混沌理论的改进人工蜂群算法对模糊神经网络的参数进行优化。我们称之为规模混沌人工蜂群（SCABC）的改进算法。此外，K-折叠分层交叉验证，以避免过度拟合。在实验中，我们应用所提出的方法对T2加权MRI图像的数据集，包括66个脑图像（18个正常和48个异常）。将该算法与传统的BP算法、动量BP算法、遗传算法、带迁移的精英遗传算法、模拟退火算法和ABC算法进行了比较。每个算法运行20次以减少随机性。实验结果表明，该方法可以获得最小的均方误差和100%的分类准确率。
Automated and accurate classification of magnetic resonance (MR) brain images is a hot topic in the field of neuroimaging. Recently many different 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 first 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 artificial bee colony (ABC) algorithm based on both fitness scaling and chaotic theory. We referred to the improved algorithm as scaled chaotic artificial bee colony (SCABC). Moreover, the K-fold stratified cross validation was employed to avoid overfitting. 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 20 times to reduce randomness. The results show that our SCABC can obtain the least mean MSE and 100% classification accuracy.