摘要
目的提出一种基于U-Net的乳腺癌淋巴结病理切片中的细胞检测方法,用以辅助医生进行乳腺癌细胞筛查。方法基于U-Net网络,利用医生预先标注的数据集训练模型,用以实现最终的细胞检测。结果针对癌细胞检测的结果准确率大于99%。结论基于U-Net的乳腺癌病理切片中癌细胞检测方法可以极大程度提升医生在病理切片中癌细胞筛查的效率,同时还可以对疑似癌细胞目标进行判断。
Objective To establish a U-Net-based method for the detection of cancer cells in lymph node pathological sections of breast cancer. Methods Based on the U-Net network,the training model of data set pre-labeled by physicians was used for final cell detection. Results This method for cancer cell detection had an accuracy of more than 99%. Conclusion The UNet-based method for the detection of cancer cells in pathological sections of breast cancer can greatly improve the efficiency of cancer cell screening in pathological sections and help with the judgment of suspected cancer cells.
作者
韩泓泽
魏宾
隋栋
李帅
HAN Hongze;WEI Bin;SUI Dong;LI Shuai(Beihang University Computer Science, Beijing 100083, China)
出处
《精准医学杂志》
2018年第6期471-473,477,共4页
Journal of Precision Medicine
基金
国家自然科学基金面上项目(61672077)
国家重点研发计划资助(2017YFF0106407)
2017国家自然科学基金青年基金项目(61702026)
关键词
乳腺肿瘤
病理学
细胞系
肿瘤
神经网络(计算机)
图像处理
计算机辅助
机器学习
Breast neoplasms
Pathology
Cell line, tumor
Neural networks (computer)
Image processing, compu- ter- assisted
Machine learning
