Described herein is an approach to identify a presence (or absence) of a tissue disease based on a quantification of a roughness of a surface of the tissue represented in imaging data. The approach includes an image data processor (120) with a surface roughness quantifier (206) that generates a metric that quantifies a roughness of a surface of a tissue of interest in 3D image data based on a surface model adapted to the tissue of interest in the 3D image data and a decision component (208) that generates a value signal indicating a presence or an absence of disease in the tissue of interest based on the metric.