Image processing

An imaging method and apparatus wherein an MRI or other scanner (A) generates image data d(x,y) which has a Gaussian noise distribution for reconstruction by an imager into an electronic image representation comprising an array of pixel values [p(i,j)] which may have a Gaussian or Rayleigh noise distribution. An image processing circuit replaces each image pixel vlaue [P(i,j)] from an image reconstruction means (32) with an improved pixel value p*(i,j) defined as follows: P*(i,j) = G (i,j)[P(i,j) - @(i,j)]+@(i,j) - @, where G(i,j) is a weighting function uniquely defined for each pixel (i,j), @ is the mean of pixel values of neighboring pixels and @ is the mean image noise. The weighting function is based on an image data noise variance and a pixel value variance V(i,j) corresponding to the same pixel. The data noise variance is derived by comparing a data value difference between each data value d(x,y) and its neighboring data values in a data memory (30). The smallest data value difference is indicative of the image noise variance. Each pixel variance is indicative of the difference between a corresponding pixel value and the neighboring pixel values. Preferably, the weighting function is: For a Gaussian image noise distribution: For a Rayleigh image noise distribution: o