摘要
乳腺癌位居女性恶性肿瘤第一位,严重威胁广大女性的生命健康。考虑到现有的癌症诊断缺少更深层次的亚型分型和融合深度学习方法进行诊断,因此提出一种基于随机森林和深度神经网络的乳腺癌亚型诊断方法。该方法首先使用随机森林算法筛选与乳腺癌关联的重要基因,再通过构建深度神经网络分类模型对乳腺癌亚型进行预测。与传统模型相比,该方法能更精确预测乳腺癌亚型,为乳腺癌高效诊断诊断提供了新的思路。
Breast cancer is the first malignant tumor in women,which seriously threatens the life and health of women.Considering that the existing diagnosis lacks cancer subtype analysis and combining deep learning models for diagnosis,therefore,a breast cancer subtype diagnostic model based on random forest and deep neural network is proposed in this paper.The method first uses a random forest algorithm to select important genes which associated with breast cancer,and then builds a deep neural network classification model to predict breast cancer subtypes.Compared with traditional models,this method can predict breast cancer subtypes more accurately and provide a new idea for breast cancer diagnosis efficiently.
出处
《工业控制计算机》
2021年第7期80-81,85,共3页
Industrial Control Computer
基金
佛山职业技术学院科研一般项目(KY2020Y06)
广东省普通高校“人工智能”重点领域专项课题(2019KZDZX1029)。
关键词
随机森林
深度神经网络
乳腺癌
基因
random forest
deep neural network
breast cancer
gene
