Non-invasive temperature prediction of in vitro therapeutic ultrasound signals using neural networks

Teixeira, C. A.; Ruano, Antonio; Ruano, M. Graça; Pereira, W. C. A.; Negreira, C.

http://hdl.handle.net/10400.1/2251

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Teixeira 2006.pdf		332.53 KB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

In this paper, a novel black-box modelling scheme applied to non-invasive temperature prediction in a homogeneous medium subjected to therapeutic ultrasound is presented. It is assumed that the temperature in a point of the medium is non-linearly related to some spectral features and one temporal feature, extracted from the collected RF-lines. The black-box models used are radial basis functions neural networks (RBFNNs), where the best-fitted models were selected from the space of model structures using a genetic multiobjective strategy. The best-fitted predictive model presents a maximum absolute error less than 0.4 C in a prediction horizon of approximately 2 h, in an unseen data sequence. This work demonstrates that this type of black-box model is well-suited for punctual and noninvasive temperature estimation, achieving, for a single point estimation, better results than the ones presented in the literature, encouraging research on multi-point non-invasive temperature estimation.

Keywords

Ultrasound Hyperthermia Neural network

URI

http://hdl.handle.net/10400.1/2251

Citation

Teixeira, C. A.; Ruano, A. E.; Ruano, M. Graça; Pereira, W. C. A.; Negreira, C. Non-invasive temperature prediction of in vitro therapeutic ultrasound signals using neural networks, Medical & Biological Engineering & Computing, 44, 1-2, 111-116, 2006.