Reproduce “Physics-Guided Multi-Objective Deep Learning for Ultrasound RF Data Interpolation in Resource-Constrained Imaging” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Luoyuan Zhang, Yiyang You, Ananya Tandri, Yinan Feng, Hyunwoo Song, Jeeun Kang, Youzuo Lin
The authors develop an ultrasound RF interpolator trained to match both fully sampled channel data and the beamformed image produced by differentiable delay-and-sum processing. In simulated tests, beamforming-domain supervision improved mean SSIM by a reported 2.23% over the no-beamforming-loss baseline, and the best configuration maintained mean SSIM around 0.95 across decimation factors ×2–×13. These results do not establish clinical readiness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.