DNA microarrays have demonstrated an excellent poten- tial in correlating specific gene expression profiles to spe- cific conditions. However, they are affected by inherent noise. This paper presents a two-stage approach for noise removal that processes the additive and the multiplicative noise component. The proposed approach first decomposes the signal by a multiresolution transform and then accounts for both the multiscale correlation of the subband decom- positions and their heavy-tailed statistics. Real microarray images have been processed by the proposed method and its improved performance is shown through quantitative mea- sures and qualitative visual evaluation.