摘要
针对乳腺癌病理图像样本数量少、设计特征费时、检测分类的准确性不高等问题,提出一种基于深度学习和迁移学习结合的乳腺癌图像分类模型算法,本算法基于深度神经网络DenseNet结构,通过引入注意力机制构建网络模型,对增强后的数据集使用多级迁移学习进行训练。实验结果表明,在测试集中该算法检测的有效率在83.5%以上,分类的准确率较先前的模型有大幅提升,可以应用到医疗乳腺癌检测任务中。
Aiming at the problem of small sample size, time-consuming design features and low accuracy of detection and classification, a breast cancer image classification algorithm based on deep learning and transfer learning is proposed. The algorithm is based on the deep neural network DenseNet structure, and constructs the network model by introducing attention mechanism. The enhanced data set is trained by multilevel transfer learning. The experimental results show that the efficiency of the algorithm is over 83.5% in the test set, and the accuracy of classification is much higher than that of the previous model, which can be applied to the medical breast cancer detection task.
出处
《数据挖掘》
2022年第2期192-202,共11页
Hans Journal of Data Mining
