A noninvasive, quantitative imaging technique is presented for detecting and diagnosing liver disease, such as cirrhosis. The technique includes: capturing scan data from a subject using computed tomography or another type of imaging method and extracting image data representing the liver from the scan data. Various measures of the liver may be obtained from image data and then used to compute random variables of a statistical model, where the model is predictive of a medical condition of the liver and comprised of random variables that are indicative of at least one of a shape or texture of the liver. Output from the statistical model provides an indication of an undesirable condition of the liver.
