A statistical method for automatic labeling of tissues in medical images

A statistically based segmentation method was applied to the recognition of organs in abdominal CT scans. To incorporate prior knowledge of anatomical structure, a stochastic model was used that represented abdominal geometry in three dimensions. Properties of each tissue class with respect to X-ray imaging were modeled by mean grey-value distributions. Twelve different tissues were labeled simultaneously. Deterministic maximization of the a posteriori distribution as well as stochastic optimization by simulated annealing were both applied. Mean segmentation results were determined for a set of 18 scan sequences, using a set of reference contours designated by a radiologist as ground truth. Results appeared to be somewhat better using simulated annealing. The proposed segmentation method, which is fast and fully automatic, seems sufficiently accurate for many clinical applications, such as determination of relative organ volumes.