Deep frequency re-calibration U-Net (FRCU-Net) for medical image segmentation. This method aims to represent an object in
terms of frequency to reduce the effect of texture bias, consequntly resultign in a better generalization performance. Following approach implements the idea of Laplacian pyramid in the bottleneck layer of the U-shaped structure and adaptively re-calibrate the frequency representations to encode shape and texture information. The method is evaluated on five datasets ISIC 2017, ISIC 2018, the PH2, lung segmentation, and SegPC 2021 challenge datasets. If this code helps with your research please consider citing the following paper:
R. Azad, Afshin Bozorgpour, M. Asadi, Dorit Merhof and Sergio Escalera "Deep Frequency Re-calibration U-Net for Medical Image Segmentation", ICCV, 2021, download link.
- October 10, 2021: Initial release of the code along with trained weights for Skin lesion segmentation on ISIC 2017, ISIC 2018 and PH2.
This code has been implemented in python language using Keras libarary with tensorflow backend and tested in ubuntu OS, though should be compatible with related environment. following Environement and Library needed to run the code:
- Python 3
- Keras 2.2.0
- tensorflow 1.13.1
For training deep model and evaluating on each data set 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 dataset_isic18.
2- Run Prepare_ISIC2018.py for data preperation and dividing data to train,validation and test sets.
3- Run Train_Skin_Lesion_Segmentation.py for training the model using trainng and validation sets. The model will be train for 100 epochs and it will save the best weights for the valiation set.
4- For performance calculation and producing segmentation result, run Evaluate_Skin.py. It will represent performance measures and will saves related results in output folder.
Notice:
For training and evaluating on ISIC 2017 and ph2 follow the bellow steps: :
ISIC 2017- Download the ISIC 2017 train dataset from this link and extract both training dataset and ground truth folders inside the dataset_isic18\7.
then Run Prepare_ISIC2017.py for data preperation and dividing data to train,validation and test sets.
ph2- Download the ph2 dataset from this link and extract it then Run Prepare_ph2.py for data preperation and dividing data to train,validation and test sets.
Follow step 3 and 4 for model traing and performance estimation. For ph2 dataset you need to first train the model with ISIC 2018 data set and then fine-tune the trained model using ph2 dataset.
| Methods | Year | F1-scores | Sensivity | Specificaty | Accuracy | PC | JS |
|---|---|---|---|---|---|---|---|
| Ronneberger and etc. all U-net | 2015 | 0.647 | 0.708 | 0.964 | 0.890 | 0.779 | 0.549 |
| Alom et. all Recurrent Residual U-net | 2018 | 0.679 | 0.792 | 0.928 | 0.880 | 0.741 | 0.581 |
| Oktay et. all Attention U-net | 2018 | 0.665 | 0.717 | 0.967 | 0.897 | 0.787 | 0.566 |
| Alom et. all R2U-Net | 2018 | 0.691 | 0.726 | 0.971 | 0.904 | 0.822 | 0.592 |
| Azad et. all BCDU-Net | 2019 | 0.847 | 0.783 | 0.980 | 0.936 | 0.922 | 0.936 |
| Asadi et. all MCGU-Net | 2020 | 0.895 | 0.848 | 0.986 | 0.955 | 0.947 | 0.955 |
| Azad et. all Attention Deeplabv3p | 2021 | 0.927 | 0.915 | 0.986 | 0.973 | .. | 0.973 |
will be updated
will be updated.
All implementation done by Reza Azad. For any query please contact us for more information.
rezazad68@gmail.com