search

Deep-MI / FatSegNet

Deep CNN for Abdominal Adipose Tissue Segmentation on Dixon MRI
Apache License 2.0
22 stars 12 forks source link

normalization for intensity range #9

Closed stebo85 closed 3 years ago

stebo85 commented 3 years ago

Dear FatSegNet developers,

I am trying to apply FatSegNet to Dixon data acquired with a similar protocol to your training data, but running the network on the raw intensity range leads to sub-optimal results: image image

I tried to manually find an intensity shift where the predictions don't fail and it seems that this works better: image

image

What normalization technique did you use and what was your intensity range of the training data of the models provided?

santiestrada32 commented 3 years ago

For this version, we didn't do any normalization technique. For future releases, we intend to normalize the input as we saw this has limited the implementation of our method in other datasets.