Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
andrewsher 4fe3716ee4 | 2 years ago | |
---|---|---|
.gitignore | 2 years ago | |
FSM.py | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
data.py | 2 years ago | |
loss.py | 2 years ago | |
model.py | 2 years ago | |
utils.py | 2 years ago |
github版本:https://github.com/Andrewsher/X-Net
Kehan Qi, Hao Yang, Cheng Li, Zaiyi Liu, Meiyun Wang, Qiegen Liu, and Shanshan Wang
采用X-Net实现对ATLAS数据集的图像分割
Dice | IoU | Precision | Recall | Number of Parameters |
---|---|---|---|---|
0.4867 | 0.3723 | 0.6000 | 0.4752 | 15.1M |
数据集:ATLAS数据集[1],包含229个case,采用5折交叉验证。数据采用这里所示的方法进行预处理得到h5文件。
[1] Liew, Sook-Lei, et al. "A large, open source dataset of stroke anatomical brain images and manual lesion segmentations." Scientific data 5 (2018): 180011.
类别 | 名称 | 版本 |
---|---|---|
os | ubuntu | 16.04 |
深度学习框架 | Keras | 2.2.4 |
深度学习框架 | tensorflow | 1.14.0 |
机器学习库 | scikit-learn | 0.19.1 |
python函数库 | pandas | 0.20.3 |
处理h5文件的库 | h5py | 2.7.0 |
名称 | 说明 |
---|---|
输入 | 单通道灰度图,值域为0-1,大小为224x192。 |
输出 | 标签。0表示背景,1表示病变 |
在main.py中修改与超参数相关的行(即第16-20行),然后在命令行中执行如下的命令:
python main.py
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies (MICCAI 2019)
Python
MIT
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》