Beckschen/TransUNet
A transformer-based neural network for medical image segmentation tasks.
Not currently ranked — collecting fresh signals.
star history
TransUNet combines Vision Transformers with U-Net architecture to perform medical image segmentation. The model uses pre-trained ViT encoders and introduces transformer layers for enhanced feature extraction. It supports both 2D and 3D medical imaging data and has achieved state-of-the-art results on multiple medical imaging benchmarks including BTCV and BraTS challenges.
Frequently asked
- What is Beckschen/TransUNet?
- A transformer-based neural network for medical image segmentation tasks.
- Is TransUNet open source?
- Yes — Beckschen/TransUNet is open source, released under the Apache-2.0 license.
- What language is TransUNet written in?
- Beckschen/TransUNet is primarily written in Python.
- How popular is TransUNet?
- Beckschen/TransUNet has 3.2k stars on GitHub.
- Where can I find TransUNet?
- Beckschen/TransUNet is on GitHub at https://github.com/Beckschen/TransUNet.