The conventional noise-reduction filters tend to blur the edge information while noise is reduced. To address this issue, we developed a supervised nonlinear filter based on an artificial neural network (ANN), called a “neural filter,” for reduction of noise in images. The neural filter is trained with input images and the corresponding teaching images. To reduce noise in images, we created noisy images from original noiseless images by adding noise. We used the noisy images as the input images and the corresponding noiseless images as the teaching images for the neural filter. After training, the neural filter provided images with less noise when it was applied to non-training noisy images. The noise in the input images was reduced while the edge information was maintained. Thus, the neural filter would be useful for reduction of noise in images.