Multitask Classification of Breast Cancer Pathological Images Using SE-DenseNet
摘要： 本文采用密集连接的卷积网络(DenseNet)结构，吸收SeNet，对一组苏木精和伊红(H&E)染色乳腺组织学显微镜 Camelyon16 进行多任务分类。全幻灯片图像（WSI）通常存储在多分辨率金字塔中，我们的数据集包含Camelyon16 在*5、*20、*40，三倍放大率下的patches。 我们的多任务是通过连接同一网络末端的两个分类器来识别patches的放大率并区分提取的pat
相关文章
- 1. Grand Challenge on Breast Cancer Histology Images
- 2. Deep Learning Assessment of Tumor Proliferation in Breast Cancer Histological Images
- 3. 论文阅读《Deep Learning Assessment of Tumor Proliferation in Breast Cancer Histological Images》
- 4. Sequential modeling of deep features for breast cancer histopathological image classification 论文阅读
- 5. Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks
- 6. 论文笔记 / Deep features for breast cancer histopathological image classification
- 7. Learning classification
- 8. 论文笔记：End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design
- 9. Lung Cancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet
- 10. 2 ways of using Naive Bayes classification for numeric attributes
- 更多相关文章...
- • Docker images 命令 - Docker命令大全
- • XSLT
- • Docker 清理命令
- • RxJava操作符（六）Utility
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Grand Challenge on Breast Cancer Histology Images
- 2. Deep Learning Assessment of Tumor Proliferation in Breast Cancer Histological Images
- 3. 论文阅读《Deep Learning Assessment of Tumor Proliferation in Breast Cancer Histological Images》
- 4. Sequential modeling of deep features for breast cancer histopathological image classification 论文阅读
- 5. Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks
- 6. 论文笔记 / Deep features for breast cancer histopathological image classification
- 7. Learning classification
- 8. 论文笔记：End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design
- 9. Lung Cancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet
- 10. 2 ways of using Naive Bayes classification for numeric attributes