Normally, surgeon may review patients investigation and images before operation. However, during surgery, there is a need for surgeons to navigate through the computer system for more patients’ details to get the surgery done successfully in higher possibilities. Constraints happened on the navigation through the computer system. During the surgery, surgeons are unable to manage both computer system and operation at the same time. Due to this constraints, this project is to research the opportunity to enable the surgeons to control the system through voice commands. Eventually there are some limitations for speech recognition engine, where.the engine is depending upon constraints placed on speaker, speaking situation and message context. For the image processing part, it has some limitations as well. The medical images might have unnecessary information on it. We need to perform filtering and segmentation to filter out this unnecessary information, without sacrifying the time consume for the system to process image after receives voice commands.