File Exchange

image thumbnail

Pre-trained 3D ResNet-18

version 1.0.2 (44.7 MB) by Amir Ebrahimi
Pre-trained Neural Network Toolbox Model for 3D ResNet-18 Network

49 Downloads

Updated 26 Feb 2021

View Version History

View License

To transfer the learnable parameters from pre-trained 2D ResNet-18 (ImageNet) to 3D one, we duplicated 2D filters (copying them repeatedly) through the third dimension. This is possible since a video or a 3D image can be converted into a sequence of image slices. In the training process, we expect that the 3D ResNet-18 learns patterns in each frame. This model has 34 million learnable parameters.

simply, call "resnet18TL3Dfunction()" function.

Cite As

Ebrahimi, Amir, et al. “Introducing Transfer Learning to 3D ResNet-18 for Alzheimer’s Disease Detection on MRI Images.” 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), IEEE, 2020, doi:10.1109/ivcnz51579.2020.9290616.

View more styles

Comments and Ratings (15)

Amir Ebrahimi

@Juuso korhonen,
I used spm12 and MNI template in it too.

Juuso Korhonen

@Amir Ebrahimi,
That sounds great! I'll try to be on the lookout. Which MNI template by the way did you use in your research? I was thinking of using the MNI152 for registration and normalization of the OASIS3 volumes with the spm12.

Amir Ebrahimi

@juuso korhonen,
Hi, definitely! I am uploading my codes one by one. Could you allow me 2-3 weeks and then check my profile? However, you can easily apply my models in MATLAB file exchange.

Juuso Korhonen

Hi, could you share the model trained with the ADNI data perhaps? I would want to test it on OASIS data.

cui

@Amir Ebrahimi:
Use "groupNormalizationLayer" instead or simply remove "crossChannelNormalizationLayer" because it does not affect network performance.

Amir Ebrahimi

@cui, nice job. How did you replace cross channel normalisation layer?

cui

@Amir Ebrahimi:
Refer to your program, I rewrote the general 3d cnn!
https://ww2.mathworks.cn/matlabcentral/fileexchange/87594-3d-convolutional-neural-network?s_tid=srchtitle

Amir Ebrahimi

@cui
Sorry for the inconvenience. Since I connected the project to GitHub, the whole file is gone. I contacted MathWorks support to fix the issue. Anyway, you can download the file in "version history". Please tell me if you still have any issue.

cui

@Amir Ebrahimi:
hi, where is "resnet18TL3Dfunction()" function ? Don't see any code?

Amir Ebrahimi

@cui Yes, definitely. You just need to adjust the first and the last layers.

cui

Can video behavior analysis be done?

Amir Ebrahimi

@Esra, no worries
The output argument of ResNet-18 3d function is a layergraph itself. so you do not need to use layerGraph function. Use the output argument of resnet18TL3Dfunction() directly for training.

Esra Kaya

Thanks for sharing but I get this error using it
"Error using trainNetwork (line 170)
Layers argument must be an array of layers or a layer graph."

How can I fix it?

Amir Ebrahimi

@LS The paper is about 2D CNN+ LSTM. You can simply extract features from CNNs with "activations" function and then train an LSTM model. More info: https://au.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html

Lin

Would you have plan to share the model for combination 3D Resnet-18 and LSTM as used on your paper?

MATLAB Release Compatibility
Created with R2020b
Compatible with R2019b and later releases
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!