To transfer the learnable parameters from pre-trained 2D ResNet-101 (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-101 learns patterns in each frame. This model has 87 million learnable parameters.
simply, call "resnet101TL3Dfunction()" function.
引用格式
Ebrahimi, Amir, et al. “Convolutional Neural Networks for Alzheimer’s Disease Detection on MRI Images.” Journal of Medical Imaging, vol. 8, no. 02, SPIE-Intl Soc Optical Eng, Apr. 2021, doi:10.1117/1.jmi.8.2.024503.
查看更多格式
| MLA |
Ebrahimi, Amir, et al. “Convolutional Neural Networks for Alzheimer’s Disease Detection on MRI Images.” Journal of Medical Imaging, vol. 8, no. 02, SPIE-Intl Soc Optical Eng, Apr. 2021, doi:10.1117/1.jmi.8.2.024503.
|
| APA |
Ebrahimi, A., Luo, S., & Alzheimer’s Disease Neuroimaging Initiative, for the. (2021). Convolutional neural networks for Alzheimer’s disease detection on MRI images. Journal of Medical Imaging, 8(02). SPIE-Intl Soc Optical Eng. Retrieved from https://doi.org/10.1117%2F1.jmi.8.2.024503
|
| BibTeX |
@article{Ebrahimi_2021,
doi = {10.1117/1.jmi.8.2.024503},
url = {https://doi.org/10.1117%2F1.jmi.8.2.024503},
year = 2021,
month = {apr},
publisher = {{SPIE}-Intl Soc Optical Eng},
volume = {8},
number = {02},
author = {Amir Ebrahimi and Suhuai Luo and for the Alzheimer's Disease Neuroimaging Initiative},
title = {Convolutional neural networks for Alzheimer's disease detection on {MRI} images},
journal = {Journal of Medical Imaging}
}
|
