Removing noise from radiological image using multineural network filter

In this paper, a new type of multineural networks filter (MNNF) is presented that is trained for restoration and enhancement of the digital radiological images. In medical radiographics, noise has been categorized as quantum mottle, which is related to the incident X-ray exposure and artificial noise, which is caused by the grid etc. MNNF consists of several neural network filters (NNFs). A novel analysis method is proposed for making clear the characteristics of the trained MNNF. In the proposed method, a characteristics judgement system is presented to decide which NNF is executed through the standard deviation value of input region. The new approach is tested on 9 clinical medical X-ray images and 5 synthesized noisy X-ray images. In all cases, the proposed MNNF produces better results in terms of peak signal to noise ratio (PSNR), mean-to-standard-deviation ratio (MSR) and contrast to noise ratio (CNR) measures than the original NNF, linear inverse filter and nonlinear median filter