A robust deep learning framework for segmentation of 2D echocardiography.
We used the Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) dataset available here.
Models used
- UNet(UNet)
- Recurrent U-Net (R2UNet)
- Attention U-Net (Attn_Unet)
- Residual Unet (ResUnet)
- ASPP UNet
- HMEDN
- TC-SegNet (model = ResUnetPlusPlus_Path)
Pre Processing
Segmentation Output
