Automatic tuning of respiratory model for patient-based simulation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Standard Standard

Automatic tuning of respiratory model for patient-based simulation. / Vidal, F. P.; Villard, P.-F.; Lutton, É.

International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013). Brussels, Belgium, 2013. p. 225-231.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

HarvardHarvard

Vidal, FP, Villard, P-F & Lutton, É 2013, Automatic tuning of respiratory model for patient-based simulation. in International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013). Brussels, Belgium, pp. 225-231, International Conference on Medical Imaging Using Bio-Inspired and Soft Computing, Brussels, Belgium, 15/05/13.

APA

Vidal, F. P., Villard, P-F., & Lutton, É. (2013). Automatic tuning of respiratory model for patient-based simulation. In International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013) (pp. 225-231). Brussels, Belgium.

CBE

Vidal FP, Villard P-F, Lutton É. 2013. Automatic tuning of respiratory model for patient-based simulation. In International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013). Brussels, Belgium. pp. 225-231.

MLA

Vidal, F. P., P.-F. Villard and É. Lutton "Automatic tuning of respiratory model for patient-based simulation". International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013). Brussels, Belgium. 2013, 225-231.

VancouverVancouver

Vidal FP, Villard P-F, Lutton É. Automatic tuning of respiratory model for patient-based simulation. In International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013). Brussels, Belgium. 2013. p. 225-231

Author

Vidal, F. P. ; Villard, P.-F. ; Lutton, É. / Automatic tuning of respiratory model for patient-based simulation. International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013). Brussels, Belgium, 2013. pp. 225-231

RIS

TY - GEN

T1 - Automatic tuning of respiratory model for patient-based simulation

AU - Vidal, F. P.

AU - Villard, P.-F.

AU - Lutton, É.

PY - 2013/5/1

Y1 - 2013/5/1

N2 - This paper is an overview of a method recently published in a biomedical journal (IEEE Transactions on Biomedical Engineering, http://tbme.embs.org). The method is based on an optimisation technique called ``evolutionary strategy'' and it has been designed to estimate the parameters of a complex 15-D respiration model. This model is adaptable to account for patient's specificities. The aim of the optimisation algorithm is to finely tune the model so that it accurately fits real patient datasets. The final results can then be embedded, for example, in high fidelity simulations of the human physiology. Our algorithm is fully automatic and adaptive. A compound fitness function has been designed to take into account for various quantities that have to be minimised (here topological errors of the liver and the diaphragm geometries). The performance our implementation is compared with two traditional methods (downhill simplex and conjugate gradient descent), a random search and a basic real-valued genetic algorithm. It shows that our evolutionary scheme provides results that are significantly more stable and accurate than the other tested methods. The approach is relatively generic and can be easily adapted to other complex parametrisation problems when ground truth data is available.

AB - This paper is an overview of a method recently published in a biomedical journal (IEEE Transactions on Biomedical Engineering, http://tbme.embs.org). The method is based on an optimisation technique called ``evolutionary strategy'' and it has been designed to estimate the parameters of a complex 15-D respiration model. This model is adaptable to account for patient's specificities. The aim of the optimisation algorithm is to finely tune the model so that it accurately fits real patient datasets. The final results can then be embedded, for example, in high fidelity simulations of the human physiology. Our algorithm is fully automatic and adaptive. A compound fitness function has been designed to take into account for various quantities that have to be minimised (here topological errors of the liver and the diaphragm geometries). The performance our implementation is compared with two traditional methods (downhill simplex and conjugate gradient descent), a random search and a basic real-valued genetic algorithm. It shows that our evolutionary scheme provides results that are significantly more stable and accurate than the other tested methods. The approach is relatively generic and can be easily adapted to other complex parametrisation problems when ground truth data is available.

KW - Evolutionary computation, inverse problems, medical simulation, adaptive algorithm

M3 - Conference contribution

SP - 225

EP - 231

BT - International Conference on Medical Imaging Using Bio-Inspired and Soft Computing (MIBISOC2013)

CY - Brussels, Belgium

ER -