Coder Social home page Coder Social logo

sergivalverde / cnn-ms-lesion-segmentation Goto Github PK

View Code? Open in Web Editor NEW
42.0 42.0 24.0 4.89 MB

MS lesion segmentation using cascaded 3D convolutional neural networks

License: GNU General Public License v3.0

Python 80.92% Jupyter Notebook 19.08%

cnn-ms-lesion-segmentation's Introduction

cnn-ms-lesion-segmentation's People

Contributors

sergivalverde avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

cnn-ms-lesion-segmentation's Issues

FileNotFoundError ,How i get it *.nii.gz?

---> cnn1 loading training data
Traceback (most recent call last):
File "train_leave_one_out.py", line 79, in
model = train_cascaded_model(model, train_x_data, train_y_data, options)
File "C:\Users\MAGARA\Downloads\Compressed\cnn-ms-lesion-segmentation-master\base.py", line 35, in train_cascaded_model
X, Y = load_training_data(train_x_data, train_y_data, options)
File "C:\Users\MAGARA\Downloads\Compressed\cnn-ms-lesion-segmentation-master\base.py", line 134, in load_training_data
x_patches, y_patches = load_train_patches(x_data, y_data, selected_voxels, options['patch_size'])
File "C:\Users\MAGARA\Downloads\Compressed\cnn-ms-lesion-segmentation-master\base.py", line 205, in load_train_patches
lesion_masks = [load_nii(name).get_data().astype(dtype=np.bool) for name in y_data]
File "C:\Users\MAGARA\Anaconda2\lib\site-packages\nibabel\loadsave.py", line 40, in load
raise FileNotFoundError("No such file: '%s'" % filename)
nibabel.py3k.FileNotFoundError: No such file: 'C:\Users\MAGARA\Downloads\Compressed\cnn-ms-lesion-segmentation-master\VH_all\im3\lesion_bin.nii.gz'

MemoryError

Dear professor:
I use your kears "cnn-ms-lesion-sg", my computer :NVIDIA-GT1070 8GB ,32GB RAM, cpu i7 6700.
In test, I use 5 group images as train and 5 group images as test. When epoch finish than DEBUG will memoryerror, I don't why ,can you help me ? thanks
3

requirements.txt errors

Hello,

I was not able to simply run pip install on the requirements file because some versions were not found. Maybe they have been updated or changed and thus not available anymore?

I have now latest version for Lasagne, etc. However, as you may expect, some issues come out. It says that theano.sandobox... gives error. I'm not really capable to find out where and what to change to make it work. Any idea what to do? Thank you very much in advance.

MemoryError

Dear professor:
I use your kears "cnn-ms-lesion-sg", my computer :NVIDIA-GT1070 8GB ,32GB RAM, cpu i7 6700.
In test, I use 5 group images as train and 5 group images as test. When epoch finish than DEBUG will memoryerror, I don't why ,can you help me ? thanks
3

I have a problem with filetypes

Hi @sergivalverde

I want to get data to use to run the program. I use data from MICCAI2008 (filetype *.nhdr). But the filetype does not match the specified code (filetype *.nii.gz). Where can I get it?
If you know, please answer me.

Thank you

config.py

Hello Sergi,

could you please confirm us the parameters setting (e.g. modalities, epochs, batch size,...) to reproduce the MICCAI 2016 data challenge results (15 patients)? We are using the keras version of your method.

Many thanks!

I can't get a good result

Dear professor, when I use CHB and UNC data training , I can't get a good result .
about data pre-processing , I use BET skull-stripped ,but no N3 intensity normalized and smoothing ,also no resampled to 256256256 , then i train it , so because pre-processing and other?
Can you give me a suggestion.

pickle isse - NameError: global name 'pickle' is not defined

Hi,
anyone ended up with a problem of this sort - NameError: global name 'pickle' is not defined
See below for details:

model = train_cascaded_model(model, train_x_data, train_y_data, options)
File "/udd/fgalassi/base.py", line 38, in train_cascaded_model
model[0].fit(X, Y)
File "/udd/fgalassi/myenv/lib/python2.7/site-packages/nolearn/lasagne/base.py", line 700, in fit
self.train_loop(X, y, epochs=epochs)
File "/udd/fgalassi/myenv/lib/python2.7/site-packages/nolearn/lasagne/base.py", line 839, in train_loop
func(self, self.train_history_)
File "/udd/fgalassi/myenv/lib/python2.7/site-packages/nolearn_utils/hooks.py", line 60, in call
pickle.dump(train_history, f, -1)
NameError: global name 'pickle' is not defined

Thank you!

program

Dear Dr. Sergi Valverde, I download your program, my environment is ubuntu 16.04, but I use jupyter notebook cell example_1.pynb always error. I also install requirements.txt , can your help me. Thank you very much.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.