摘要
鼻咽癌是一类高发的恶性肿瘤,实现其快速诊断具有重要意义。该文提出了一种基于深度卷积神经网络(DCNN)的病理图像数据肿瘤区域自动检测和诊断方法。通过在病理切片像素20000*20000中检测和定位出像素大小为256*256的肿瘤区域。
Nasopharyngeal carcinoma is a kind of high incidence malignant tumor. It is of great significance to realize its rapid diag-nosis. In this paper, an automatic detection and diagnosis method based on deep convolution neural network(DCNN) is presented.The tumor area with a pixel size of 256 * 256 was detected and located in the pathological section with a pixel size of 20000 *20000. Shallow features of patches at different resolutions are extracted by the VGG-16 network(10 x, 20 x) model. The features areinputted into the second half of the Inception-V3 network and fused with the features of the 40 x patch extracted by the Inception-V3, to establish a nasopharyngeal carcinoma fusion diagnosis model based on pathological image, which can improve the analyzingperformance and reduce the false positive rate in the mechanism. The actual data processing results show that the detection accura-cy for nasopharyngeal carcinoma reached 91.5%, and the accuracy of diagnosis is greatly improved.
出处
《电脑知识与技术》
2018年第5Z期183-185,共3页
Computer Knowledge and Technology
基金
山东省科学院创新工程专项资助
山东省重点研发计划"面向基层医疗的低成本云健康检测设备研发与综合医疗云服务平台建设"(项目编号:2015GGH309003)
关键词
鼻咽癌诊断
深度卷积网络
特征融合
多尺度分析
学习算法
diagnosis of nasopharyngeal carcinoma
deep convolution network
feature fusion
multiscale analysis
learning algorithm
