3D Anisotropic Hybrid Network (AH-Net) Pytorch Implementation

Skip to content Dismiss alert {{ message }} lsqshr / AH-Net Public

• Notifications You must be signed in to change notification settings
• Fork 11
• Star 52

The Pytorch implementation of the 3D Anisotropic Hybrid Network described in the paper "3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes"

arxiv.org/abs/1711.08580 52 stars 11 forks Branches Tags Activity Star Notifications You must be signed in to change notification settings

• Code
• Issues 4
• Pull requests
• Actions
• Projects
• Security
• Insights

Additional navigation options

lsqshr/AH-Net  masterBranchesTagsGo to fileCodeOpen more actions menu

Folders and files

Name		Name	Last commit message	Last commit date
Latest commit   History 7 Commits7 Commits
README.md		README.md
net2d.py		net2d.py
net3d.py		net3d.py
View all files

Repository files navigation

• README

3D Anisotropic Hybrid Network (AH-Net) Pytorch Implementation

The Pytorch implementation of the 3D Anisotropic Hybrid Network (AH-Net) that transfers convolutional features learned from 2D images to 3D anisotropic volumes. Such a transfer inherits the desired strong generalization capability for within-slice information while naturally exploiting between-slice information for more effective modelling. We experiment with the proposed 3D AH-Net on two different medical image analysis tasks, namely lesion detection from a Digital Breast Tomosynthesis volume, and liver and liver tumor segmentation from a Computed Tomography volume and obtain the state-of-the-art results.

For more details, please refer to the paper: Siqi Liu, Daguang Xu, S. Kevin Zhou, Thomas Mertelmeier, Julia Wicklein, Anna Jerebko, Sasa Grbic, Olivier Pauly, Weidong Cai, Dorin Comaniciu 3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes arXiv:1711.08580 [cs.CV]. A shorter version was presented in MICCAI18: https://link.springer.com/chapter/10.1007/978-3-030-00934-2_94

We only host the example network implementations here for brevity. To train a model for 3D medical images:

1. Pretrain the 2D model from net2d.FCN or net2d.MCFCN. This 2D FCN model is initialised with the Pytorch officially released ResNet50.
2. Copy the trained 2D model to the 3D AH-Net as

net = AHNet(num_classes=2) net.copy_from(model2d)

3. Train the AH-Net model as a 3D fully convolutional network

Note: The impelementation of the 2D network here is adapted from: https://github.com/ycszen/pytorch-segmentation/blob/master/gcn.py

About

The Pytorch implementation of the 3D Anisotropic Hybrid Network described in the paper "3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes"

arxiv.org/abs/1711.08580

Resources

Readme

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

52 stars

Watchers

2 watching

Forks

11 forks Report repository

Releases

No releases published

Packages

No packages published

Languages

• Python 100.0%

You can’t perform that action at this time.