多卷积神经网络在医学图像分类中的应用研究  

Fusion of Multiple Convolutional Neural Networks for Medical Image Classification

作　　者：蒋健 钦旗 张海波[1] 郭文平[1] JIANG Jian;QIN Qi;ZHANG Haibo;GUO Wenping(School of Electronics and Information Engineering,Taizhou University,Taizhou,China,318000)

机构地区：[1]台州学院电子与信息工程学院,浙江台州318000

出　　处：《福建电脑》2022年第6期50-52,共3页Journal of Fujian Computer

基　　金：台州市大学生科技创新项目深度学习算法在新冠肺炎图像分类中的比较研究和台州市科技计划项目基于深度学习的皮肤病辅助诊疗系统关键技术研究(No.2003gy12)资助。

摘　　要：针对卷积神经网络分类准确率不够高的问题,本文提出多卷积神经网络融合算法用于医学图像分类。首先在训练集上优化ResNet和DenseNet网络,再采用加权平均方法对ResNet和DenseNet的预测结果进行融合。在ISIC2017和COVID19两个数据集上的实验结果表明,本文提出的方法相比于VGGNet、ResNet、DenseNet等单卷积神经网络,具有更高的分类准确率和稳定性。Aiming at the problem that the classification accuracy of convolutional neural network is not high enough,a multi-convolutional neural network fusion algorithm is proposed for medical image classification.First,the ResNet and DenseNet networks are optimized on the training set,and then the weighted average method is used to fuse the prediction results of ResNet and DenseNet.The experimental results on the ISIC2017 and COVID19 datasets show that the method proposed in this paper has higher classification accuracy and stability than single convolutional neural networks such as VGGNet,ResNet,and DenseNet.

关 键 词：医学图像 深度学习 卷积神经网络 ResNet DenseNet 

分 类 号：G206[文化科学—传播学]