基于特征级融合神经网络磁共振成像前列腺肿瘤CAD模型.docVIP

基于特征级融合神经网络磁共振成像前列腺肿瘤CAD模型 　　摘要：针对磁共振成像（MRI）前列腺肿瘤感兴趣区域（ROI）在高维特征表示下存在特征相关和维数灾难问题，提出了一种基于主成分分析（PCA）的特征级融合神经网络（NN）的MRI前列腺肿瘤CAD模型。首先提取MRI前列腺肿瘤ROI的6维几何特征、6维统计特征、7维Hu不变矩特征、56维灰度共生矩阵的纹理特征、3维Tamura纹理特征和24维频域特征，得到102维特征矢量；然后通过PCA进行特征级融合得到累计贡献率达到89.62%的8维变换特征，降低特征矢量的维数；再次利用经典的神经网络（四种训练算法BFGS拟牛顿算法、BP算法、最速梯度下降算法和LevenbergMarquardt算法）作为分类器进行分类识别；最后以180幅前列腺患者的MRI图像为原始数据，采用基于特征级融合神经网络（NN）的计算机辅助诊断模型对前列腺肿瘤进行辅助诊断。实验结果表明：经过特征级融合的神经网络识别前列腺良恶性肿瘤的能力至少提高10%左右，这种特征级融合策略是有效的，一定程度上提高了特征之间的不相关性。 　　Tamura为人名 　　关键词：前列腺肿瘤；计算机辅助诊断；主成分分析；神经网络；特征级融合 　　中图分类号： R445.2；TP391.4 　　文献标志码：A 　　Abstract： Focusing on the issue that feature relevancy and dimension disaster problem in highdimensional representation of Magnetic Resonance Imaging （MRI） prostate tumor Region of Interesting （ROI）， a prostate tumor CAD model was proposed based on Neural Network （NN） with Principal Component Analysis （PCA） featurelevel fusion in MRI. Firstly， 102 dimension features were extracted form MRI prostate tumor ROI， including 6 dimension geometry features， 6 dimension statistical features， 7 dimension Hu invariant moment features， 56 dimension GLCM texture features， 3 dimension Tamura texture features and 24 dimension frequency features. Secondly， 8 dimension features with cumulative contribution rate of 89.62% were obtained by using PCA in featurelevel fusion， reducing the dimension of the feature vectors. Thirdly， the classical NN， which used BroydenFletcherGoldfarbShanno （BFGS）， BackPropagation （BP） and Gradient Descent （GD）， LevenbergMarquardt as the training algorithm， was regarded as classifier to classify the features. Finally， 180 MRI images of prostate patients were used as original data， and the prostate tumor CAD model based on NN with featurelevel fusion was utilized to diagnose. The experimental results illustrate that the ability to identify benign and malignant prostate tumor of neural network with PCA featurelevel fusion is improved at least 10%， and the featurelevel fusion strategy is effective， whic