Refined-Segmentation-R-CNN
Refined-Segmentation-R-CNN copied to clipboard
YalongLiu
A Deep Learning method to segment punctate white matter lesions (PWMLs); Brain tumor segmentation;
Refined Segmentation R-CNN
Accepted by MICCAI2019.
Liu, Yalong, Jie Li, Ying Wang, Miaomiao Wang, Xianjun Li, Zhicheng Jiao, Jian Yang, and Xingbo Gao. "Refined Segmentation R-CNN: A Two-Stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants." In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 193-201. Springer, Cham, 2019.
--A Deep Learning method to segment punctate white matter lesions (PWMLs); Brain tumor segmentation.
By: Yalong Liu1, Jie Li1, Ying Wang1, Miaomiao Wang2, Xianjun Li2, Zhicheng Jiao3, Jian Yang2, Xingbo Gao1
- Lab of Video and Image Processing Systems, School of Electronic Engineering, Xidian University, Xi’an 710071, China
- Department of Radiology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi’an 710061, China
- University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
This repository includes:
1.T1WI of 10 patients for test(Full dataset is not allowed to be made public; Warning:The provided test data is only used to test the code. Please use your own data to train a normal model.)
2.Full code for model training and inference
3.The link of pre-trained weights on google drive
Requirements
Python 3.6.3
Tensorflow-gpu 1.12.0
CUDA 9.0
Getting Started
1.Download the repositories and weights(GoogleDrive or Anonfiles or BaiduYun).
2.Choose a mode in the main.py('inference' or 'training').
3.(optional)Change parameters in configs.py according to the comment in the file.
4.python ./main.py
Enjoy!
Acknowledgment
This repo borrows tons of code from
matterport/Mask_RCNN
Results
Performance:
| Index | --------Original MRI-------- | ---------SOTA---------- | -----Mask R-CNN------ | -----Our Method-------- |
|---|
| 8/77 |  |
|---|---|
| 79/67 |  |
| 82/67 |  |
| 83/48 |  |
| 83/54 |  |
| 83/80 |  |
Citation
If you use Refined Segmentation R-CNN in your research, please cite the paper(MICCAI2019-Springer) or (Arxiv):
Liu, Yalong, Jie Li, Ying Wang, Miaomiao Wang, Xianjun Li, Zhicheng Jiao, Jian Yang, and Xingbo Gao. "Refined Segmentation R-CNN: A Two-Stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants." In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 193-201. Springer, Cham, 2019.
For more information about me, please refer to my personal website
YalongLiu