Transfer Learning from Nucleus Detection to Classification in Histopathology Images
Transfer Learning from Nucleus Detection to Classification in Histopathology Images
复制标题
从细胞核检测到组织病理学图像分类的迁移学习
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yao Nie
中科院分区：
文献类型：
--
作者：
Safoora Yousefi;Yao Nie
尽管最近取得了重大成功，但由于难以提供细胞级监督，现代计算机视觉技术（如卷积神经网络（CNN））应用于组织病理学图像中的细胞级预测问题是昂贵的。这项工作探讨了对象检测CNN（Faster R-CNN）学习的特征对组织病理学图像中细胞核分类的可转移性。我们使用在小的注释块上训练的类不可知模型检测这些图像中的细胞核，并使用检测到的细胞核的CNN表示对它们进行聚类和分类。我们表明，使用小的训练数据集，所提出的管道可以实现上级细胞核检测和分类性能，并很好地推广到看不见的染色类型。
Despite significant recent success, modern computer vision techniques such as Convolutional Neural Networks (CNNs) are expensive to apply to cell-level prediction problems in histopathology images due to difficulties in providing cell-level supervision. This work explores the transferability of features learned by an object detection CNN (Faster R-CNN) to nucleus classification in histopathology images. We detect nuclei in these images using class-agnostic models trained on small annotated patches, and use the CNN representations of detected nuclei to cluster and classify them. We show that with a small training dataset, the proposed pipeline can achieve superior nucleus detection and classification performance, and generalizes well to unseen stain types.