- 3D CNN are difficult to train due to high computation times. And retraining models can be exhausting.
- To train 3D CNN, amount of labelled-data required is very high and is not suitable if the sample size is small.
3D Discrete Wavelet Transformation
- Chaplot, S., Patnaik, L. M., & Jagannathan, N. R. (2006). Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomedical signal processing and control, 1(1), 86-92.