Liver stereoscopic visualisation by using Hopfield neural nets

Three dimensional visualisation techniques have been used as a powerful tool in surgical and therapeutic applications. Due to large medical data, huge computations are necessary on 3D visualisation, especially for a real-time system. Many existing methods are sequential, which are too slow to be practical in real applications. In our previous work, we showed boundary detection and feature points extraction by using Hopfield networks. In this paper, a new feature points matching method for 3D surfaces using a Hopfield neural network is proposed. Taking advantage of parallel and energy convergence capabilities in the Hopfield networks, this method is faster and more stable for feature points matching. Stereoscopic visualisation is the display result of our system. With stereoscopic visualisation, the 3D liver used in the experiment can leap out of the screen in true 3D stereoscopic depth. This increases a doctor's ability to analyse complex graphics.