lab-midas/med_segmentation

Which model in ModelSet.py is the DCNet model

dmus opened this issue · 1 comments

dmus commented

Hi, thanks for sharing this work. I cloned this repository and read the paper "Fully automated and standardized segmentation of adipose tissue compartments via deep learning in 3D whole-body MRI of epidemiological cohort studies". Now I am wondering which of the models in ModelSet.py are used in the paper. Which one corresponds to the proposed DCNet and which one corresponds to the reference UNet?

Hi, the models used in the paper are a combination of MRGE and DCNet which in the implemented framework is the "premodel_MRGE". The reference UNet model is denoted as "premodel_UNet". You can check the config files in config/pretrained_model to see the various parametrizations for the conducted experiments in the paper.