Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
To mitigate grating-lobe artifacts caused by sparse data acquisition in power-constrained portable ultrasound, the authors design an end-to-end deep learning framework for sparse-to-dense radio-frequency (RF) data interpolation. The model leverages hybrid supervision combining RF- and downstream beamforming-domain losses stabilized by an exponential moving average (EMA), paired with a random-skip masking strategy to handle varying sparsity profiles. Across diverse decimation factors ranging from $\times 2$ to $\times 13$, the unified model preserves acoustic phase fidelity and consistently sustains a post-beamforming mean SSIM of ~0.95.
Decimating ultrasound RF channels by up to $13\times$ no longer destroys beamforming contrast, as coupling acoustic-domain losses with dynamic channel masking preserves phase coherence at a 0.95 SSIM.
Ultrasound imaging increasingly targets portable, point-of-care, and wearable settings where constraints on power, bandwidth, and hardware complexity often necessitate sparse data acquisition in spatiotemporal scanning. However, image reconstruction using the sparse data can introduce insufficient phase information in coherent beamforming process, resulting in grating-lobe artifacts that degrade imaging contrast resolution. We present a physics-guided, data-driven framework for sparse-to-dense radio-frequency (RF) reconstruction that aligns training with downstream image formation. Our approach trains an end-to-end interpolation network using a hybrid supervision scheme that combines an RF-domain and a beamforming-domain loss with exponential moving average (EMA) to stabilize the multi-objective training. To improve generalization under variable acquisition layouts, we also introduce a random-skip masking strategy that varies sparsity patterns during training so a single model can handle diverse decimation factors and irregular channel configurations. We evaluate the framework on a held-out test set using the mean structural similarity index measure (SSIM) between reconstructed and ground-truth beamformed images. Across decimation factors $\times 2$ to $\times 13$, the best-performing configuration maintains mean SSIM around 0.95. Overall, the results show consistent gains in RF reconstruction and post-beamforming image quality across diverse acquisition conditions. This approach enables robust, high-quality ultrasound imaging at resource-constrained settings by allowing more sparse scanning in spatiotemporal domain.