Reproduce “Speckle Noise Reduction in Ultrasound Images using Denoising Auto-encoder with Skip Connection” 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
Suraj Bhute, Subhamoy Mandal, Debashree Guha
The authors test a skip-connected autoencoder for denoising artificially corrupted breast-ultrasound images. The network reconstructs a clean image from a noisy input while links pass encoder features to the decoder, which the authors propose may preserve information. At noise variance 0.7, it outperforms the same autoencoder without skips on PSNR, SSIM, and MSE; this is not clinical evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.