I am working on a project involving survival analysis using time and event data. I plan to apply a $3$D CNN model for image analysis and use pycox for survival predictions. However, I am unsure how to properly design the $3$D CNN architecture for this specific task. Additionally, I would like to calculate both the C$-$index and Integrated Brier Score $($IBS$)$ to evaluate the model. Could you please guide me through the steps of setting up the model architecture and calculating these metrics using pycox? Any advice on best practices for preprocessing the data and optimizing the model would also be greatly appreciated.