help required for training dataset using unet

I am trying to implement U-NET segmentation on 3Dircadb dataset.

The data set contains

i) Original LiverCT dataset

II) Masks of Liver CT dataset

lll) Labels of Liver CT dataset

my questios is

i) To train the unet algorithm what dataset i want to use

ii) How to identify labeled organ from label dataset

Even in the LITS dataset we have

i) original CT images

ii) maks of thr CT images

how to train unet using above dataset

am already using below options part in the training code

options = trainingOptions('sgdm', ...

'Momentum',0.5, ...

'InitialLearnRate',8e-4, ...

'L2Regularization',0.0005, ...

'MaxEpochs',50, ...

'MiniBatchSize',8, ...

'Shuffle','every-epoch', ...

'CheckpointPath', tempdir, ...

'VerboseFrequency',2, ...

'Plots','training-progress');

but am not able to segment the liver from original image so please help me if i want to update any extra information in the training part