Automatic Epicardial Adipose Tissue Segmentation in CT Using 3D U-Net
A lightweight, compact 3D U-Net trained on 146 calcium-scoring CT scans from the PESA (Progression of Early Subclinical Atherosclerosis) CNIC–SANTANDER study, stratified by EAT volume to ensure representation across the full spectrum of adiposity.
José Antonio Rangel, Ravi Vazirani, Morena Raiola et al.
· 0 citations