if I just want to generate thin slice CTs，how can I do?

[joelive]

Just remove the SCALING_FACTOR for x and y, and keep the SCALING_FACTOR for z, Will it work if I just want to generate thin slice CTs?
lr_image = tf.image.resize(blurred_image, [x//SCALING_FACTOR, y//SCALING_FACTOR], method=interpolation_method).numpy()
lr_image = np.rot90(lr_image, axes=(1,2))
lr_image = tf.image.resize(lr_image, [x//SCALING_FACTOR, z//SCALING_FACTOR], method=interpolation_method).numpy()
ups_lr_image = tf.image.resize(lr_image, [x//SCALING_FACTOR, z], method=interpolation_method).numpy()
ups_lr_image = np.rot90(ups_lr_image, axes=(1,2))

[omagdy]

Hi @joelive

Im not sure I understand your question particularly what you mean by thin slices. Do you want to train the model for upscaling a 3d image only on the X and Y axes and leave the Z axis as it is (i.e no upscaling on the Z dimension) ?

If thats the case then you should still do scaling on the X and Y while removing the scaling from Z. This way the high and low resolution versions of the same image will only differ in the X and Y dimension (based on the scaling factor) while they will still have the value in the Z dimension.

Let me know if you still need clarification.