期刊
MEDICAL IMAGE ANALYSIS
卷 68, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.media.2020.101890
关键词
Computational pathology; Semantic segmentation; Multi-resolution; Deep learning
类别
资金
- European Union [825292]
- Radboud Institute of Health Sciences (RIHS), Nijmegen, The Netherlands
- Alpe dHuZes/Dutch Cancer Society Fund [KUN 2014-7032]
HookNet is a semantic segmentation model for histopathology whole-slide images that combines context and details via multiple branches of encoder-decoder convolutional neural networks. The advantages of using HookNet in two histopathology image segmentation tasks are demonstrated, and the model has been made publicly available by releasing the source code and web-based applications.
We propose HookNet, a semantic segmentation model for histopathology whole-slide images, which combines context and details via multiple branches of encoder-decoder convolutional neural networks. Concentric patches at multiple resolutions with different fields of view, feed different branches of HookNet, and intermediate representations are combined via a hooking mechanism. We describe a framework to design and train HookNet for achieving high-resolution semantic segmentation and introduce constraints to guarantee pixel-wise alignment in feature maps during hooking. We show the advantages of using HookNet in two histopathology image segmentation tasks where tissue type prediction accuracy strongly depends on contextual information, namely (1) multi-class tissue segmentation in breast cancer and, (2) segmentation of tertiary lymphoid structures and germinal centers in lung cancer. We show the superiority of HookNet when compared with single-resolution U-Net models working at different resolutions as well as with a recently published multi-resolution model for histopathology image segmentation. We have made HookNet publicly available by releasing the source coder as well as in the form of web-based applications) :3 based on the grand-challenge.org platform. (C) 2020 The Authors. Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据