Skip to content

Releases: PengchengShi1220/NexToU

NexToU v1.2

16 Jun 15:02
@PengchengShi1220 PengchengShi1220
v1.2.0
039a186
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
NexToU v1.2 Latest
Latest

NexToU v1.2: Upgraded with get_3d_sincos_pos_embed_from_grid for divisible by 2, ensuring the initial feature number can be 32 to align with the default of the nnUNet framework. Built on nnU-Net V2 (v2.2).

Assets 4
Loading

NexToU v1.1

29 Mar 17:19
@PengchengShi1220 PengchengShi1220
v1.1.0
2d376e7
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
NexToU v1.1

NexToU v1.1, upgraded with residual convolutional layers, built on the nnU-Net V2 (v2.0).

Assets 4
Loading

NexToU v1.0

26 Mar 05:57
@PengchengShi1220 PengchengShi1220
v1.0.0
084b605
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
NexToU v1.0

Introducing our latest version of NexToU, built on the nnU-Net V2 (v2.0), and featuring enhanced stages in both encoder and decoder. NexToU includes:

  • Pool GNN and SwinGNN Modules: Specifically designed for capturing global and local topological representations in 2D/3D medical images.
  • Binary Topological Interaction (BTI) Module: Efficiently processes topological interactions between different anatomical structures.
Assets 4
Loading