NV-Raw2Insights-US Simulations is a simulated full synthetic aperture ultrasound dataset for training neural networks. The dataset provides raw baseband IQ channel data from a 180-element linear array over heterogeneous tissue phantoms containing cysts. It was authored by NVIDIA and last updated on HuggingFace in April 2026.
Use Cases
- Training neural networks for sound speed estimation based on simulated FSA ultrasound data.
- Evaluating phase aberration correction algorithms using raw baseband IQ channel data.
- Developing tissue segmentation models from simulated acquisitions of heterogeneous phantoms.
Strengths
- Dataset is simulated for specific tasks like sound speed estimation and phase aberration correction.
- Provides raw baseband IQ channel data alongside processed outputs, likely offering a complete pipeline for model development.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
Provenance
- Source
- NVIDIA
- Collection Method
- Simulated full synthetic aperture ultrasound acquisitions.
- Freshness
- Last updated 2026-04-21 21:12:07; freshness should be verified.