I'm trying to train a convolution network for segmenting biomedical images U-net to segment parts of a magnetic resonance image (MRI) reconstruction; a 3D stack of 2D slices.

What is the best way to use this the multiple slices from an MRI as an input, an example tensor can have the shape [30, 256, 256] I've seen people that turn the MRI instance into a numpy array [30 * 256 * 256], but I am not sure if this loses information.

My initial idea was to use each slice as an image 30 x [1, 256, 256]

What is the most recommended way to achieve this?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.