Lu Siyuan, Qiu Xin, Shi Jianping, Li Na, Lu Zhi-Hai, Chen Peng, Yang Meng-Meng, Liu Fang-Yuan, Jia Wen-Juan, Zhang Yudong
School of Psychology & School of Computer Science and Technology, Nanjing Normal University,. China.
CNS Neurol Disord Drug Targets. 2017;16(1):23-29. doi: 10.2174/1871527315666161019153259.
It is beneficial to classify brain images as healthy or pathological automatically, because 3D brain images can generate so much information which is time consuming and tedious for manual analysis. Among various 3D brain imaging techniques, magnetic resonance (MR) imaging is the most suitable for brain, and it is now widely applied in hospitals, because it is helpful in the four ways of diagnosis, prognosis, pre-surgical, and postsurgical procedures. There are automatic detection methods; however they suffer from low accuracy.
Therefore, we proposed a novel approach which employed 2D discrete wavelet transform (DWT), and calculated the entropies of the subbands as features. Then, a bat algorithm optimized extreme learning machine (BA-ELM) was trained to identify pathological brains from healthy controls. A 10x10-fold cross validation was performed to evaluate the out-of-sample performance.
The method achieved a sensitivity of 99.04%, a specificity of 93.89%, and an overall accuracy of 98.33% over 132 MR brain images.
The experimental results suggest that the proposed approach is accurate and robust in pathological brain detection.
自动将脑部图像分类为健康或病变状态是有益的，因为三维脑部图像会产生大量信息，人工分析既耗时又繁琐。在各种三维脑成像技术中，磁共振成像最适合用于脑部，目前已在医院中广泛应用，因为它在诊断、预后、术前和术后程序这四个方面都有帮助。虽然存在自动检测方法，但它们的准确率较低。
因此，我们提出了一种新颖的方法，该方法采用二维离散小波变换（DWT），并计算子带的熵作为特征。然后，训练一种蝙蝠算法优化的极限学习机（BA-ELM）来从健康对照中识别病变脑。进行了10×10倍交叉验证以评估样本外性能。
该方法在132幅磁共振脑图像上实现了99.04%的灵敏度、93.89%的特异性和98.33%的总体准确率。
实验结果表明，所提出的方法在病变脑检测中准确且稳健。
