search

ginobilinie / medSynthesis

medical image synthesis with GAN framework based on tensorflow (we also have a better version in pytorch: https://github.com/ginobilinie/medSynthesisV1)
MIT License
72 stars 24 forks source link

Dataset #7

Closed tianlili1 closed 4 years ago

tianlili1 commented 5 years ago

Hi，I have read your article, the method proposed is very good, but there are a lot of problems when running the code, I hope you can help me, I have got access to the ADNI database, but I don't know how to download the required data set, can you share the data set you use with me?

ginobilinie commented 5 years ago

For the code, I suggest you use the pytorch version (this TF version is written more than two years ago and a lot of functions have not been updated to the latest api):

https://github.com/ginobilinie/medSynthesisV1

For the data, I have no permission to share the data (I just have permission to use it). I'm very sorry for it.

tianlili1 commented 5 years ago

Ok,Thank you for your repley.I will use the pytorch version.If I have a problem that I don’t understand, I hope you can help me with it.

ginobilinie commented 5 years ago

Sure.

tianlili1 commented 5 years ago

Hi! I'm back again. In the paper you mentioned random forests to synthesize images. I have also seen this paper using random forest composite images. Do you have its source code? If so, can you share it with me at 770133167@qq.com? Thank you!

ginobilinie commented 5 years ago

you should ask the first author of that paper for the code. I cannot share other guys' code without their permission.

lyc-lang commented 4 years ago

Hi, I have applied for and obtained access to ADNI data set. I don't know how to get the two datasets used in the paper to evaluate the model. Could you please send me a link，thanks！

lyc-lang commented 4 years ago

Or could you share the training data set? This is my email: mirror_whut@qq.com

rogertrullo commented 4 years ago

Hi @lyc-lang the dataset used in the paper is private containing medical information and as such we cannot share it publicly.