xmed-lab / oeem Goto Github PK

Yi Li*, Yiduo Yu*, Yiwen Zou*, Tianqi Xiang, Xiaomeng Li, "Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images", MICCAI 2022 (Accepted). [paper]

This framework is designed for histology images, containing two stages. The first classification stage generates pseudo-masks for pathes. And the segmentation stage uses OEEM to mitigate the noise in pseudo-masks dynamically.

This code has been tested with Python 3.7, PyTorch 1.10.2, CUDA 11.3 mmseg 0.8.0 and mmcv 1.4.0 on Ubuntu 20.04.

Download resources (dataset, weights) with extract code snb3, then link to codes.

git clone https://github.com/XMed-Lab/OEEM.git
cd OEEM
ln -s OEEM_resources/glas_cls classification/glas
ln -s OEEM_resources/glas_seg segmentation/glas
ln -s OEEM_resources/weights classification/weights
ln -s OEEM_resources/weights segmentation/weights

Install library dependencies

pip install -r requirements.txt

Install mmsegentation.

cd segmentation
pip install -U openmim
mim install mmcv-full==1.4.0
pip install -v -e .

Train classification model.

python classification/train.py -d 0 -m res38d

Generate pseudo-mask (WSI size). The output will be in [model_name]_best_train_pseudo_mask folder.

python classification/prepare_seg_inputs.py -d 0 -ckpt res38d_best

Split WSI pseudo-mask to patches for segmentation.

python segmentation/tools/crop_img_and_gt.py segmentation/glas/images classification/res38d_best_train_pseudo_mask segmentation/glas

Train segmentation model.

cd segmentation
bash tools/dist_train.sh configs/pspnet_oeem/pspnet_wres38-d8_10k_histo.py 1 runs/oeem

Test segmentation model.

cd segmentation
bash tools/dist_test.sh configs/pspnet_oeem/pspnet_wres38-d8_10k_histo_test.py runs/oeem/[name of best ckpt] 1

Merge patches and evaluation.

python tools/merge_patches.py glas/test_patches glas/test_wsi 2
python tools/count_miou.py glas/test_wsi glas/gt_val 2

Results compared with WSSS for natural images:

@misc{https://doi.org/10.48550/arxiv.2206.06665,
  doi = {10.48550/ARXIV.2206.06665},
  url = {https://arxiv.org/abs/2206.06665},
  author = {Li, Yi and Yu, Yiduo and Zou, Yiwen and Xiang, Tianqi and Li, Xiaomeng},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}

This repository is released under MIT License (see LICENSE file for details).