Experimental new automatic tools for robotic stereotactic neurosurgery: towards "no hands" procedure of leads implantation into a brain target.

The use of robotics in neurosurgery and, particularly, in stereotactic neurosurgery, is becoming more and more adopted because of the great advantages that it offers. Robotic manipulators easily allow to achieve great precision, reliability, and rapidity in the positioning of surgical instruments or devices in the brain. The aim of this work was to experimentally verify a fully automatic "no hands" surgical procedure. The integration of neuroimaging to data for planning the surgery, followed by application of new specific surgical tools, permitted the realization of a fully automated robotic implantation of leads in brain targets. An anthropomorphic commercial manipulator was utilized. In a preliminary phase, a software to plan surgery was developed, and the surgical tools were tested first during a simulation and then on a skull mock-up. In such a way, several tools were developed and tested, and the basis for an innovative surgical procedure arose. The final experimentation was carried out on anesthetized "large white" pigs. The determination of stereotactic parameters for the correct planning to reach the intended target was performed with the same technique currently employed in human stereotactic neurosurgery, and the robotic system revealed to be reliable and precise in reaching the target. The results of this work strengthen the possibility that a neurosurgeon may be substituted by a machine, and may represent the beginning of a new approach in the current clinical practice. Moreover, this possibility may have a great impact not only on stereotactic functional procedures but also on the entire domain of neurosurgery.

A comparison between HMLP and HRBF for attitude control.

In this paper the problem of controlling the attitude of a rigid body, such as a Spacecraft, in three-dimensional space is approached by introducing two new control strategies developed in hypercomplex algebra. The proposed approaches are based on two parallel controllers, both derived in quaternion algebra. The first is a feedback controller of the proportional derivative (PD) type, while the second is a feedforward controller, which is implemented either by means of a hypercomplex multilayer perceptron (HMLP) neural network or by means of a hypercomplex radial basis function (HRBF) neural network. Several simulations show the performance of the two approaches. The results are also compared with a classical PD controller and with an adaptive controller, showing the improvements obtained by using neural networks, especially when an external disturbance acts on the rigid body. In particular the HMLP network gave better results when considering trajectories not presented during the learning phase.

Multilayer Perceptrons to Approximate Quaternion Valued Functions.

In this paper a new type of multilayer feedforward neural network is introduced. Such a structure, called hypercomplex multilayer perceptron (HMLP), is developed in quaternion algebra and allows quaternionic input and output signals to be dealt with, requiring a lower number of neurons than the real MLP, thus providing a reduced computational complexity. The structure introduced represents a generalization of the multilayer perceptron in the complex space (CMLP) reported in the literature. The fundamental result reported in the paper is a new density theorem which makes HMLPs universal interpolators of quaternion valued continuous functions. Moreover the proof of the density theorem can be restricted in order to formulate a density theorem in the complex space. Due to the identity between the quaternion and the four-dimensional real space, such a structure is also useful to approximate multidimensional real valued functions with a lower number of real parameters, decreasing the probability of being trapped in local minima during the learning phase. A numerical example is also reported in order to show the efficiency of the proposed structure. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.