Contrast enhancement in wavelet domain for graph-based segmentation in medical imaging

Despite increased image quality including medical imaging, image segmentation continues to represent a major bottle-neck in practical applications due to noise and lack of contrast. In this paper, we present a new methodology to segment low contrast medical images. There are two stages to this approach, 1) a contrast enhancement stage, that uses stochastic resonance theory applied in a wavelet domain, is performed by utilizing the noise present in medical data, and 2) a new weighting function is proposed for traditional graph-based approaches. Both qualitative and quantitative evaluation performed on publicly available databases of two imaging modalities reflect the potential of the proposed method.