生物标记物发现方法 基于深度学习与医学知识图谱约束的多尺度生物标记物发现技术
Introduction
这是一个基于深度学习的多尺度医学影像分割模型,一种自适应尺度卷积神经网络。该模型在端到端训练中引入了3层卷积结构,以自适应地学习图像中每个像素最优的膨胀参数。这种像素级的膨胀参数使得模型能够获得最佳的感受野,从而可以在相应的尺度下提取具有不同大小的物体的信息。
Publications
ASCNET: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning
Cite thisCited by 2 (Google Schoolar as of June 2, 2021)
Credits
- MoZhang zhangmo007@pku.edu.cn Contributor
Center for Data Science, Peking University, China
- Jie Zhao jiezhao@pku.edu.cn Contributor
Center for Data Science, Peking University, China
- Xiang Li xli60@mgh.harvard.edu Contributor
Radiology, Massachusetts General Hospital, United States of America
Community Ratings
Usability | Efficiency | Reliability | Rated By |
---|---|---|---|
0 user | |||
Sign in to rate |
Summary
Accession | BT007198 |
---|---|
Tool Type | Application |
Category | Image analysis |
Platforms | Linux/Unix |
Technologies | Python3 |
User Interface | Terminal Command Line |
Latest Release | 1.0 (June 2, 2021) |
Download Count | 35 |
Submitted By | bin dong |
Fundings
This work was supported by National Key R&D Program of China (No.2018YFC0910700);