Modelling the indentation force response of non-uniform soft tissue using a recurrent neural network

A scaled recurrent neural network (RNN) model is developed which accurately predicts the force response from the indentation of a non-uniform soft tissue sample. The model consists of two components. The RNN is used to predict the force response of indentation using data from a reference tissue sample. A two-parameter component then scales the neural networks predictions relative to previously determined properties of the test sample. This component is based on a strain inverse model of force, which is used to account for the non-uniformity of the tissue between the test and reference data. Experimental force measurements were performed on a highly non-uniform soft tissue analogue to develop and validate the model. Using the visco-elastic Hunt-Crossley model as a benchmark, the developed model provides significantly better prediction. Future research will investigate applying this model to surgical simulations and verifying its application to different biological tissues.