Implementation of Y-Net

NifTK / NiftyNet

[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy

http://niftynet.io

Apache License 2.0

1.37k stars 406 forks source link

Implementation of Y-Net #251

Open josemariamoreira opened 6 years ago

josemariamoreira commented 6 years ago

The implementation will be based on "Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images" by Mehta et al. (2018).

The new features that will be required for it to work are:

Efficient spatial pyramid (ESP) layer
inspired on Pyramid spatial pooling (PSP) layer decoding block
allow pre-defined gradients to be silent in part of the training
uses csv_reader for classification

fepegar commented 6 years ago

What is the purpose of this issue?

danieltudosiu commented 6 years ago

I know that for every new feature for which we need a branch we need to create an issue and name the branch based on the issue number. Did I get it wrong :-?

fepegar commented 6 years ago

Thanks for adding some info :+1:

ericspod commented 5 years ago

@danieltudosiu Is this in-progress still? I don't see a 251 branch.

danieltudosiu commented 5 years ago

@josemariamoreira Did implement a Y-Net as far as I am aware.