Stack Overflow
Stack Overflow

Questions tagged [niftynet]

NiftyNet is a TensorFlow-based open-source convolutional neural networks (CNNs) platform for research in medical image analysis and image-guided therapy.

NiftyNet is a TensorFlow-based open-source convolutional neural networks (CNNs) platform for research in medical image analysis and image-guided therapy.

The code is available via GitLab, or you can quickly get started with the PyPI module available here.

Features

NiftyNet currently supports medical image segmentation and generative adversarial networks. NiftyNet is not intended for clinical use. Other features of NiftyNet include:

  • Easy-to-customise interfaces of network components
  • Sharing networks and pre-trained models
  • Support for 2-D, 2.5-D, 3-D, 4-D inputs
  • Efficient discriminative training with multiple-GPU support
  • Implementation of recent networks (HighRes3DNet, 3D U-net, V-net, DeepMedic)
  • Comprehensive evaluation metrics for medical image segmentation

NiftyNet is released under the Apache License, Version 2.0. Please see the LICENSE file in the NiftyNet source code repository for details.

If you use NiftyNet in your work, please cite Gibson, Li et al. 2017. The NiftyNet platform originated in software developed for Li et. al. 2017.

55 questions
11
votes
1 answer

Changing CNN to work with 3D convolutions

I am working with code from here (paper here) that creates a GAN. I am trying to apply this to a new domain, switching from their application on MNIST to 3D brain MRI images. My issue is in the defining of the GAN itself. For example, their code…
Kyranstar
  • 1,650
  • 2
  • 14
  • 35
4
votes
1 answer

Classification with NiftyNet

I am trying to run classification using NiftyNet. I wanted to run training and I have a training set with images and a class assigned to them, like image1 -> cancer and image2 -> no cancer. Basically I have no masks and it seems that if I want to…
user2610908
  • 43
  • 2
4
votes
1 answer

How do I implement transfer learning in NiftyNet?

I'd like to perform some transfer learning using the NiftyNet stack, as my dataset of labeled images is rather small. In TensorFlow, this is possible--I can load a variety of pre-trained networks and directly work with their layers. To fine-tune…
Max Zhou
  • 41
  • 2
3
votes
1 answer

Understanding input shape (spatial_window_size) for Niftynet

I am using Niftynet for medical image segmentation. I have seen a great tutorial on spatial_window_shape parameter constraints here https://nbviewer.jupyter.org/gist/fepegar/1fb865494cb44ac043c3189ec415d411. But I wonder how to choose between…
manza
  • 322
  • 1
  • 11
3
votes
1 answer

Generalized Dice Loss: None-gradient when implemented in keras

I'm trying to implement the Generalized Dice Loss as implemented in NiftyNet, in a different convnet written in Keras (TF backend). def generalised_dice_loss(prediction, ground_truth, weight_map=None, …
DaanK
  • 31
  • 2
3
votes
2 answers

Error while trying to run NiftyNet quick start command

I'm trying out NiftyNet and got stuck at the first step. Trying to run the quickstart command python net_download.py dense_vnet_abdominal_ct_model_zoo python net_segment.py inference -c …
bsp2020
  • 31
  • 1
2
votes
1 answer

Threshold Otsu: AttributeError: 'AxesSubplot' object has no attribute 'ravel'

I loaded nifty files(These were as well converted from .pack CT scans). My goal is to use the threashold otsu algorithm to mask it from the background and compare the two images. When I try to plot I get the error AttributeError: 'AxesSubplot'…
ama
  • 53
  • 1
  • 7
2
votes
1 answer

ImportError: cannot import name '_get_logger' Niftynet

I'm trying to run Niftynet on my PC. but it keeps showing this error. I had a CPU version for tensorflow and it worked. After that I installed tensorflow-gpu and now it stopped working. Please do note that import tensorflow as tf works fine so I'm…
Manaf
  • 33
  • 9
2
votes
1 answer

python niftynet illegal instruction core dumped

I am trying the Quickstart commands on niftynet's website. As I run net_download dense_vnet_abdominal_ct_model_zoo I get Illegal instruction (core dumped). Does someone have a solution? Thanks.
Sai Sindhura Tipirneni
  • 121
  • 1
  • 7
2
votes
2 answers

NiftyNet 'evaluation' action output is incorrect

I'm trying to use the new 'evaluation' action after inference to generate some metrics for my output. However, the .csv files just show scores of '0' for average_distance and '1' for Jaccard and Dice for each of my data volumes. I can't seem to find…
Ginesu_Kun
  • 31
  • 1
1
vote
0 answers

GAN conditioning input in NiftyNet

I'm trying to implement a Conditional GAN in NiftyNet. I have a collection of 3D images in Nifti format, each of a specific class. The class should be the conditioning input for the GAN. So far I have managed to make it work, but it's kind of a…
javierbg
  • 185
  • 2
  • 12
1
vote
0 answers

Cannot serialize protocol buffer of type tensorflow.GraphDef as the serialized size 3459900923bytes would be larger than the limit (2147483647 bytes)

We are attempting to train a network of knee MRI through Niftynet. We have a spatial window_size = (400,400,400) with pixdim = (0.4,0.4,0.4). When we run these images with a lower window size (for example 160,160,160) - there is no problem and it…
Carl Kulseng
  • 11
  • 5
1
vote
1 answer

ImportError: cannot import name '_get_logger'

I'm trying to run Niftynet on my PC. but it keeps showing this error. CPU version for tensorflow INFO:tensorflow:TensorFlow version 1.13.1 Do i need to install the tensorflow-gpu?? ~/mlproject/test1/lib/python3.6/site-packages/niftynet/io/misc_io.py…
Sid
  • 11
  • 3
1
vote
0 answers

How do I convert Niftynet models into .pb format

I would like to use models in Niftynet zoo in tensorflowjs. When I download models from Niftynet zoo they are in checkpoint format (ckpt). However, tensorflowjs expects the models to be in pb format. Also, checkpoint format does not contain graph…
anupam
  • 91
  • 1
  • 10
1
vote
1 answer

How does Niftynet handle multiple-gpu training

I'm using Niftynet to train a CNN using 2 GPUs. As I understand, each GPU is trained independently as I get two loss values per iteration. Are the results of both GPUs combined at inference time? I used to believe that using multiple-gpus reduces…
anlarro
  • 25
  • 5
1
2 3 4