Denoising of Time-Density Data in Digital Subtraction Angiography

In this paper we present methods for removing the noise from a time sequence of digitally subtracted x-ray angiographic images. By observing the contrast agent propagation profile in a region of the angiogram one can estimate the time of arrival of that agent. Due to the large level of noise, it is difficult to detect the moment of the contrast agent arrival accurately. Hence denoising is required. Two methods are presented. The first one is based on 1D Wiener filtering of the time data. Wiener filter was chosen because it presents the optimal linear filter in the least-squares sense. The other method is based on 3D wavelet denoising via wavelet shrinkage technique, which is a nonlinear method. Since it is based on 3D wavelet basis it can perform denoising simultaneously in the spatial as well as in the time dimension of the image sequence. Wavelet based denoising proved to be superior but computationally more demanding. The experiments were performed on a sequence of cerebral angiograms.