Improved Accuracy of an Ultrasonic Based Neuro-Navigation System Using Neural Networks

This paper presents the design and development of an ultrasonic based neuronavigation system to be used for real time surgery. The system formulation, hardware and a neural network model is presented that improves the accuracy of the system considerably. 1D, 2D and 3D results from the neural network model are presented along with designs for the physical and electronic hardware. The 3D system presented in this paper eliminates the space intensive camera, has an accuracy better than 1.0 mm in the operating range of about 20–40 cm, makes the system independent of line-of-sight occlusion problems, and is expected to pave the way for accurate fusion models of the future that may account for brain shifts during surgery. The results show that the performance of the proposed system provides many advantages over existing neuro-navigation systems without compromising on the accuracy