Why the study?
Fast and reliable automated segmentation of adipose tissue into subcutaneous and visceral compartments from whole-body MRI is required for correct identification and phenotyping of individuals at increased risk for metabolic diseases.
Does a 3D densely connected convolutional neural network (DCNet) improve automated adipose tissue segmentation in whole-body MRI compared to 3D U-Net?
Does a 3D densely connected convolutional neural network (DCNet) improve automated adipose tissue segmentation in whole-body MRI compared to 3D U-Net?
A 3D densely connected convolutional neural network enables fast, reliable, and fully automated segmentation of subcutaneous and visceral adipose tissue from whole-body MRI across different epidemiologic cohorts.
No takes yet. Share an insight, caveat, or question.
Supports large-scale adipose quantification in cohorts; leaves open prospective validation before clinical cardiovascular risk use.
Küstner et al. (2020) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: