Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Tong Zhang 121b9ff3cf | 1 year ago | |
---|---|---|
data | 3 years ago | |
experiments/miccai 2021 | 2 years ago | |
images | 3 years ago | |
models | 3 years ago | |
readme | 1 year ago | |
scripts | 2 years ago | |
src | 2 years ago | |
.gitignore | 3 years ago | |
LICENSE | 3 years ago | |
NOTICE | 3 years ago | |
README.md | 1 year ago | |
requirements.txt | 2 years ago | |
tags | 2 years ago |
This repo contains the official PyTorch implemetation for EllipseNet.
Please refer to https://git.openi.org.cn/OpenMedIA/EllipseFit.Mindspore for a MindSpore version. Please be noted that the MindSpore version is not an Ellipse Detection Framework but using a 2D Unet to train a segmentation network and then using ellipses to fit the segmentation results.
Please refer to INSTALL.md for installation instructions.
Methods | Setting | DiceT | DiceC | Diceall | Pavg |
---|---|---|---|---|---|
EllipseNet (exp6) | only IoU loss | 0.8813 | 0.8520 | 0.8666 | 0.8855 |
EllipseNet (exp1) | w/o IoU loss | 0.9338 | 0.9108 | 0.9224 | 0.8841 |
EllipseNet (exp3) | w/ IoU loss | 0.9430 | 0.9224 | 0.9336 | 0.8949 |
Prepare the elliptical dataset in coco-format. An example script is given in scripts/prepare_label.ipynb. We provide scripts for all the experiments in the experiments folder.
Usage:
chmod +x experiments/miccai21/*.sh
./experiments/miccai21/exp3_base_theta5_iou.sh
If you need the docker for reproduction, please contact via email. We will provide the docker image.
EllipseNet itself is released under the MIT License (refer to the LICENSE file for details).
Portions of the code are borrowed from CenterNet, Rotated_IoU, human-pose-estimation.pytorch (image transform, resnet), CornerNet (hourglassnet, loss functions), dla (DLA network), DCNv2 (deformable convolutions), tf-faster-rcnn (Pascal VOC evaluation) and kitti_eval (KITTI dataset evaluation). Please refer to the original License of these projects (See NOTICE).
If you find this project useful for your research, please cit our work use the following BibTeX entry.
@inproceedings{chen2021ellipsenet,
title={Ellipsenet: Anchor-free ellipse detection for automatic cardiac biometrics in fetal echocardiography},
author={Chen, Jiancong and Zhang, Yingying and Wang, Jingyi and Zhou, Xiaoxue and He, Yihua and Zhang, Tong},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={218--227},
year={2021},
organization={Springer}
}
If you have any questions about this paper, welcome to email to zhangt02@pcl.ac.cn
旋转椭圆检测,可实现超声心动图四腔心切面的自动测量,包括心胸比和心轴,为医生提供先天性心脏病的诊断提供AI统计参考。
Jupyter Notebook Python C++ C Cuda other
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》