A display device displays a first medical image to a user. Touchless sensor technology detects user actions. The touchless sensor technology includes at least one sensor that does not rely on physical touch to detect the user actions. An image processor that compares detected user actions with currently valid user action within a list of currently valid user actions for the first medical image to determine when a detected user action matches a currently valid user action from the currently valid user actions contained in the list. A medical image processing engine uses metadata identifying the first medical image and an action identifier for a currently valid user action that is matched by the detected user action to generate a second medical image based on the metadata and the action identifier. Thee display device displays the second medical image to the user.