Biomedical video denoising using supervised manifold learning

This paper presents algorithms for biomedical video denoising using real-valued side information. In certain clinical settings, side information correlated to the underlying motion under imaging is available and can be used to infer motion and act as a global constraint for image denoising. Our methods assume the input data are noisy samples that lie on or near an image manifold parameterized by the associated side information and cast denoising as a supervised manifold learning problem. We demonstrate real-world use on echocardiography data and associated electrocardiogram (ECG) signals.