Efficient modelling and simulation of soft tissue deformation using mass-spring systems Alpaslan Duysak a, * , Jian J. Zhang a , V. Ilankovan b a National Centre for Computer Animation, Bournemouth University, Poole, Dorset BH12 5BB, Bournemouth, UK b Poole Hospital, Poole, BH15 2JB, UK Received 12 March 2003; received in revised form 12 March 2003; accepted 20 March 2003 Abstract In this paper, we use a mass-spring system to simulate facial soft tissue deformation resulting from the bone realignment at the lower jaw area. Since the materials concerned often exhibit significant nonlinearity, correct simulation parameters are needed to capture the nonlinear characteristics in order to achieve satisfying simulation accuracy. We propose a neural network identification method that takes mass-spring structure into account and uses only two neural networks to identify these parameters, which are usually nonlinear functions. An adaptive learning rate formula is also introduced to improve the simulation accuracy and convergence speed. D 2003 Elsevier Science B.V. and CARS. All rights reserved. Keywords: Mass-spring simulation; Neural network parameter identification; Craniofacial surgery 1. Introduction Achieving physically realistic deformation in real-time is of great interest to many medical simulation and visualisation applications. Two main approaches are widely used in the modelling of complex nonlinearly deformable objects: Finite Element Modelling (FEM) and Mass Spring Systems (MSS). The advantage of the FEM models is their unsurpassed computational accuracy compared with other simulation methods [1]. The downside of this method, however, is its substantial computational cost. The MSS, on the 0531-5131/03 D 2003 Elsevier Science B.V. and CARS. All rights reserved. doi:10.1016/S0531-5131(03)00423-0 * Corresponding author. Tel.: +44-1202-595329; fax: +44-1202-595099. E-mail addresses: aduysak@bournemouth.ac.uk (A. Duysak), jzhang@bournemouth.ac.uk (J.J. Zhang), vIlankovan@aol.com (V. Ilankovan). International Congress Series 1256 (2003) 337 – 342