wurenkai/mhorunet

[BSPC] The official code for "MHorUNet: High-order spatial interaction UNet for skin lesion segmentation".

MHorUNet

MHorUNet:High-order Spatial Interaction UNet for Skin Lesion Segmentation [paper link]

Renkai Wu, Pengchen Liang, Xuan Huang, Liu Shi, Yuandong Gu, Haiqin Zhu*, Qing Chang*

0. Main Environments

• python 3.8
• pytorch 1.8.0
• torchvision 0.9.0

1. Prepare the dataset.

1- Download the ISIC 2017 train dataset from this link and extract both training dataset and ground truth folders inside the /data/dataset_isic17/.
2- Run Prepare_ISIC2017.py for data preparation and dividing data to train,validation and test sets.

Notice: For training and evaluating on ISIC 2018 and pH2 follow the bellow steps: :
1- Download the ISIC 2018 train dataset from this link and extract both training dataset and ground truth folders inside the /data/dataset_isic18/.
then Run Prepare_ISIC2018.py for data preparation and dividing data to train,validation and test sets.
2- Download the ph2 dataset from this link and extract it then Run Prepare_PH2_test.py for data preperation and dividing data to train,validation and test sets.

2. Train the MHorUNet.

python train.py

• After trianing, you could obtain the outputs in './results/'

3. Test the MHorUNet. First, in the test.py file, you should change the address of the checkpoint in 'resume_model' and fill in the location of the test data in 'data_path'.

python test.py

• After testing, you could obtain the outputs in './results/'

Citation

If you find this repository helpful, please consider citing:

@article{wu2024mhorunet,
  title={MHorUNet: High-order spatial interaction UNet for skin lesion segmentation},
  author={Wu, Renkai and Liang, Pengchen and Huang, Xuan and Shi, Liu and Gu, Yuandong and Zhu, Haiqin and Chang, Qing},
  journal={Biomedical Signal Processing and Control},
  volume={88},
  pages={105517},
  year={2024},
  publisher={Elsevier}
}

References

• HorNet
• MALUNet

---

mhorunet's Issues

some questions

您好，我在运行您的代码时遇到了一些问题，还烦请您百忙之中能帮我看一下。
'''
img = sc.imread(Tr_list[idx])
img = np.double(sc.imresize(img, [height, width, channels], interp='bilinear', mode = 'RGB'))
'''

img = Image.open(Tr_list[idx]).convert('RGB')
img = img.resize((height, width), resample=Image.BILINEAR)
img = np.array(img)

Data_train[idx, :, :, :] = img

在使用您的上面这段代码时，因为报错sc操作有问题，因此我换成了下面的代码。但是在训练时，它生成的混淆矩阵是这样的confusion_matrix: [[1309771 949]
[ 0 0]]，这看起来不太对。烦请您帮忙看一下