Model Weights
645 Accesses
CardioEcho-Realtime Point-of-Care Model
License
Apache 2.0
Data / File Format
TensorRT / CoreML (45 MB)
Access Dataset & Model Weights
Free for non-commercial academic research under Apache 2.0 license terms.
Asset Summary & Description
Lightweight 60 FPS mobile neural network for real-time ejection fraction quantification on point-of-care ultrasound devices.
Data Specifications & Benchmark Metrics
Model Checkpoint Specs:
- Size: 45 MB footprint.
- Target Devices: iPad Pro, NVidia Jetson Nano, Android NPU.
- Accuracy: 94.2% Dice coefficient on 4-chamber cardiac view segmentation.
BibTeX Citation:
@dataset{medvisai_cardioecho-realtime-point-of-care-model,
title={ CardioEcho-Realtime Point-of-Care Model },
author={MedVis AI Research Laboratory Team},
year={2026},
url={ https://github.com/medvisai/cardiovision-net/releases/tag/v2.1 }
}