M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus Images
This repo is the official implementation of paper "M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus Images".
Environment
This code is based on mmsegmentation.
- pytorch=1.6.0
- mmsegmentation=0.8.0
- mmcv=1.2.0
conda create -n m2mrf python=3.7 -y
conda activate m2mrf
conda install pytorch=1.6.0 torchvision cudatoolkit=10.2 -c pytorch -y
pip install mmcv-full==1.2.0 -f https://download.openmmlab.com/mmcv/dist/cu102/torch1.6.0/index.html -i https://pypi.douban.com/simple/
pip install opencv-python
pip install scipy
pip install tensorboard tensorboardX
pip install sklearn
pip install terminaltables
pip install matplotlib
cd M2MRF-Lesion-Segmentation
chmod u+x tools/*
pip install -e .
Training and testing
# prepare dataset
python tools/prepare_labels.py
python tools/augment.py
# train
CUDA_VISIBLE_DEVICES=0,1,2,3 PORT=12345 tools/dist_train.sh configs/_m2mrf_idrid/fcn_hr48-M2MRF-C_40k_idrid_bdice.py 4
# test
CUDA_VISIBLE_DEVICES=0,1,2,3 PORT=12345 tools/dist_test.sh configs/_m2mrf_idrid/fcn_hr48-M2MRF-C_40k_idrid_bdice.py /path/to/fcn_hr48-M2MRF-C_40k_idrid_bdice_iter_40000.pth 4 --eval mIoU
Results and models
We evaluate our method on IDRiD and DDR.
IDRiD
| method | mIOU | mAUPR | download |
|---|---|---|---|
| M2MRF-A | 49.86 | 67.15 | config | model |
| M2MRF-B | 49.33 | 66.71 | config | model |
| M2MRF-C | 50.17 | 67.55 | config | model |
| M2MRF-D | 49.96 | 67.32 | config | model |
DDR
| method | mIOU | mAUPR | download |
|---|---|---|---|
| M2MRF-A | 31.47 | 49.56 | config | model |
| M2MRF-B | 30.56 | 49.86 | config | model |
| M2MRF-C | 30.39 | 49.20 | config | model |
| M2MRF-D | 30.76 | 49.47 | config | model |
In the paper, we reported average performance over three repetitions, but our code only reported the best one among them.
Citation
If you find this code useful in your research, please consider cite:
@misc{liu2021m2mrf,
title={M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus Images},
author={Qing Liu and Haotian Liu and Wei Ke and Yixiong Liang},
year={2021},
eprint={2111.00193},
archivePrefix={arXiv},
primaryClass={eess.IV}
}
373 Dec 20, 2022
6 Mar 30, 2022
3.5k Jan 8, 2023
5 Dec 26, 2022
38 Jan 6, 2023
34 Dec 27, 2022
2 Jul 6, 2022
49 Sep 21, 2022
2 Nov 14, 2022
![[my-result] description](https://avatars.githubusercontent.com/u/109494250?v=4)
1 Oct 10, 2021
13 Dec 2, 2022
22 Oct 21, 2022
3 Nov 30, 2021
116 Dec 30, 2022
104 Jan 1, 2023
310 Dec 28, 2022
1 Jan 25, 2022
1k Dec 30, 2022
125 Jan 4, 2023