Stanford University / Cedars-Sinai Medical Center (Ouyang Lab)
Measures interventricular septum thickness, LV internal diameter, and posterior wall thickness from PLAX echocardiogram videos, then classifies the underlying cause of left ventricular hypertrophy as either cardiac amyloidosis or hypertrophic cardiomyopathy. Combines an atrous-convolution 2D CNN for wall-thickness segmentation with a 3D residual CNN for etiology classification. Trained on 28,201 videos across Stanford, Cedars-Sinai, and the Unity Imaging Collaborative. Developed by Stanford University.
Architecture
Hybrid
Atrous-convolution 2D CNN for PLAX wall-thickness (IVS/LVID/LVPW) segmentation + 3D residual CNN for LVH-etiology (amyloidosis/HCM) classification
Framework
PyTorch
Added to catalog
2026-07-10
Research use only
License for model weights only. Associated code may be licensed seperately, check code source for specific terms.
EchoNet-LVH dataset
28,201 PLAX/A4C echo videos from Stanford Health Care, Cedars-Sinai Medical Center, and the Unity Imaging Collaborative. Source reports age, sex, and race/ethnicity breakdowns.
Intraventricular septum (IVS) thickness
LV internal diameter (LVID)
LV posterior wall (LVPW) thickness
Cardiac amyloidosis classification
Hypertrophic cardiomyopathy classification
Multi-class classification of the underlying cause of left ventricular hypertrophy (cardiac amyloidosis vs. hypertrophic cardiomyopathy vs. other)