The input data size in the code is different from that in the paper

[cool-sheep]

Dear author, your data is different from the data in the original paper. Have you done anything else?

[McSpooder]

Hi cool-sheep,
Yes the data is different to the paper in terms of the dimensions of the input MRIs. The authors of the Cambridge paper registered their own MRIs at a higher resolution. The MRIs that were used with this code were registered at a resolution of 110x110x110. The network reflects this change in order to support an input of such size. You can download the entire dataset that I used from my drive.

[cool-sheep]

Thank you very much for sharing. This code gives me a lot of inspiration. Now it has run successfully! In addition, I also want to try data preprocessing by myself. If it's convenient for you, can you share the unprocessed data? (I am a graduate student from China. It is difficult to download ADNI data directly due to Internet reasons)

[yujianzhong3257298]

Dear author,when I Run "python camull_cli.py",I can't find this fold

conn = sqlite3.connect("..\weights\neural-network.db")
sqlite3.OperationalError: unable to open database file

can you help me?

[yujianzhong3257298]

非常感谢您的分享。这段代码给了我很多启发。现在它已经成功运行了！另外，我也想自己尝试一下数据预处理。如果方便的话，可以分享一下未处理的数据吗？（我是中国的研究生。由于网络原因，直接下载ADNI数据比较困难）

你好，我也是中国的研究生，这个下载下载下来没有权重文件怎么解决的啊，谢谢啦

[McSpooder]

Thank you very much for sharing. This code gives me a lot of inspiration. Now it has run successfully! In addition, I also want to try data preprocessing by myself. If it's convenient for you, can you share the unprocessed data? (I am a graduate student from China. It is difficult to download ADNI data directly due to Internet reasons)

Hi, I've recently re registered for the ADNI site. I found a way to retrieve the the unprocessed image data but I'm having difficulties automating the process. It takes too long to do it manually for the 1000 images. Are you still following this project? If so I can give it another go tomorrow.

[HelenaLJQ]

Hello, author, can I see your complete paper on this project?

[HelenaLJQ]

你好，我也是中国的研究生，可以探讨一下么

[HelenaLJQ]

你好，我也是中国的研究生，可以问问嘛？

[HelenaLJQ]

Can I see the full version of your paper?

[McSpooder]

Can I see the full version of your paper?

paper

[HelenaLJQ]

You mentioned this paper in your introduction and it is based on TensorFlow. However, your project code is based on Pytorch, so I would like to ask if there is a corresponding paper for your Pytorch version? Also, in this framework, your data input is 110 × one hundred and ten × 110, but the size in the original paper is not the same. What work have you done in data preprocessing? Sorry again, I am a second year graduate student from China and would like to develop an Alzheimer's disease classification and prediction model based on your project. Therefore, I have a lot of questions and I apologize for any inconvenience caused. It would be even better if we could leave a contact information. This is my phone number. You can add my WeChat account at 18941052185

[HelenaLJQ]

You mentioned this paper in your introduction and it is based on TensorFlow. However, your project code is based on Pytorch, so I would like to ask if there is a corresponding paper for your Pytorch version? Also, in this framework, your data input is 110 × one hundred and ten × 110, but the size in the original paper is not the same. What work have you done in data preprocessing? Sorry again, I am a second year graduate student from China and would like to develop an Alzheimer's disease classification and prediction model based on your project. Therefore, I have a lot of questions and I apologize for any inconvenience caused. It would be even better if we could leave a contact information. This is my phone number. You can add my WeChat account at 18941052185

[McSpooder]

Hi,

The research paper wasn't copied exactly. The data is of different dimension and so are the filters in the network. The MRI data is of size 110x110x110. The MRI scans were in the nifty format and were obtained from ADNI by using the filters
described in (Appendix B.1) of my dissertation. Also, the data was registered to the Colin27 template and skull
stripped. I didn't pre-process the data it was already pre-processed when downloading from ADNI. If you want to copy the project you must just present the data in the same dimension or else it won't work. Otherwise you will need to change the size of the filters of the neural network. You can contact me on my email: hextra@live.com

[HelenaLJQ]

Thank you very much for your reply. I have saved your email information. After reading your paper, I will contact you again. Thank you again

[McSpooder]

Okay, no problem