基于卷积神经网络的肝部组织切片分类的研究

Classification of Liver Tissue Sections Based on Convolutional Neural Network

肝部组织切片分类时,传统机器学习方法都是通过提取图像特征来进行识别和预测,由于需要人工提取,具有一定的复杂度,因此识别率较低。为此,利用基于深度学习的卷积神经网络方法来识别分类。对在Keras框架下的Inception V3模型进行改进,将样本图像作为输入数据,通过卷积神经网络训练验证即可得到实验结果,省去繁琐的特征提取环节。实验结果表明,此方法识别率高于当前的传统方法,并且方便快捷。

When liver tissue slices are classified, the traditional machine learning methods are extracted by the image feature to identify and predict. Because of the need to manually extract features, extraction has a certain degree of complexity and it will lead to the recognition rate of liver tissue sections is low. In this article, we use the convolution neural network method which based on depth learning to classify. Under the framework of Keras, the modified Inception V3 model is used to input the sample image as input data, and the experimental results can be obtained by convolution neural network. There is no complicated lea ture extraction part and the results show that the recognition rate of this method is higher than the tradi tional method.