Official repository for: BCF-Mamba: Boundary-Aware Contextual CNN–Mamba for Ultrasound Image Segmentation
The source code will be released to the public in the near future.
If you have any questions, please contact: chen_wenqin2002@163.com
(1)BUSI: W. Al-Dhabyani., Dataset of breast ultrasound images, Data Br. 28 (2020) 104863.
(2)Dataset B: M. H. Yap et al., Breast ultrasound region of interest detection and lesion localisation, Artif. Intell. Med., vol. 107, no. August 2019, p. 101880, 2020.
(3)STU: Z. Zhuang, N. Li, A. N. Joseph Raj, V. G. V Mahesh, and S. Qiu, “An RDAU-NET model for lesion segmentation in breast ultrasound images,” PLoS One, vol. 14, no. 8, p. e0221535, 2019.
(4)DDTI: L. Pedraza, C. Vargas, F. Narvaez, O. Duran, E. Munoz, and E. Romero, “An open access thyroid ultrasound image database,” in 10th International symposium on medical information processing and analysis, vol. 9287, pp. 188–193, SPIE, 2015.
- BUSI
- Dataset B
- STU
- DDTI
- SZU-BCH-TUS983
Step-1: Create a new conda environment & install requirements
conda create -n bcmamba python=3.10
conda activate bcmamba
cd selective_scan
pip install .
pip install torch==2.3.0 torchvision==0.18.0 torchaudio==2.3.0 (cuda 11.8)
pip install causal-conv1d==1.4.0
pip install mamba-ssm==2.2.4
pip install torchinfo timm numbaImageNet pretrained model:
We use the ImageNet pretrained VMamba-Tiny model from VMamba. You need to download the model checkpoint and put it into pretrained_ckpt/vmamba_tiny_e292.pth
We use the ImageNet pretrained ConvNeXt-T model from ConvNeXt. You need to download the model checkpoint and put it into pretrained_ckpt/convnext_tiny_1k_224_ema.pth
wget https://github.com/MzeroMiko/VMamba/releases/download/%2320240218/vssmtiny_dp01_ckpt_epoch_292.pth
mv vssmtiny_dp01_ckpt_epoch_292.pth data/pretrained/vmamba/vmamba_tiny_e292.pth
We thank the authors of Mamba, VMamba, Swin-UMamba and Swin-Unet for making their valuable code & data publicly available.