卷积神经网络在早期肺癌诊疗方面的应用进展

Advances in the application of convolutional neural network in the diagnosis and treatment of early lung cancer

近年来卷积神经网络(convolutional neural network,CNN)在辅助分析肺癌方面表现出良好的应用前景和研究价值。CNN可以从图像数据中自主学习以提取特定的与临床相关的特征。本文对构建CNN通过输入CT图像进行端到端分析,从而在术前预测肺癌风险和临床治疗效果;以及通过输入肺结节组织切片图像进行术后病理学分析作一综述。

In recent years,convolutional neural network(CNN)has exhibited its promising prospect and research value in assisting the analysis of lung cancer.The CNN can automatically learn from the images to extract specific clinically relevant features.This review summarized the construction of CNN by inputting CT images for end-to-end analysis to predict lung cancer risk and the efficacy of clinical treatment,as well as the application of CNN for analyzing pathological slides of resected pulmonary nodules via inputting histopathologic images.