As an example of noisy dynamic image processing, the paper presents a plan-guided analysis system of cineangiograms, X-ray motion pictures of a beating heart in which X-ray opaque dye is injected through a catheter. A task of the system is the detection of both the internal and external surfaces of the left ventricular chamber and the measurement of the spatial and temporal change in thickness of the heart wall, which gives us important measures of various heart diseases. The features of the system are as follows: 1) sophisticated edge detectors to detect boundary points having low contrast in noisy pictures, 2) an efficient search method for finding smooth boundaries of heart wall accurately using an improved optimization method, and 3) use of the plan to guide the above two processes so that the cineangiogram can be analyzed efficiently and reliably. Experiments have been carried out, and the results obtained so far show very good agreement with boundaries detected by radiologists.