Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles

Ghaleb A. Husseini, Farouq S. Mjalli, William G. Pitt, Nabil M. Abdel-Jabbar

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

Abstract

We have been developing a drug delivery system that uses Pluronic P105 micelles to sequester a chemotherapeutic drug - namely, Doxorubicin (Dox) - until it reaches the cancer site. Ultrasound is then applied to release the drug directly to the tumor and in the process minimize the adverse side effects of chemotherapy on non-tumor tissues. Here, we present an artificial neural network (ANN) model that attempts to model the dynamic release of Dox from P105 micelles under different ultrasonic power intensities at two frequencies. The developed ANN model is then utilized to optimize the ultrasound application to achieve a target drug release at the tumor site via an ANN-based model predictive control. The parameters of the controller are then tuned to achieve good reference signal tracking. We were successful in designing and testing a controller capable of adjusting the ultrasound frequency, intensity, and pulse length to sustain constant Dox release.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Modelling and Simulation
Pages320-325
Number of pages6
Publication statusPublished - 2009
Event20th IASTED International Conference on Modelling and Simulation, MS 2009 - Banff, AB, Canada
Duration: Jul 6 2009Jul 8 2009

Other

Other20th IASTED International Conference on Modelling and Simulation, MS 2009
CountryCanada
CityBanff, AB
Period7/6/097/8/09

Fingerprint

Micelles
Ultrasound
Artificial Neural Network
Drugs
Ultrasonics
Optimise
Neural networks
Neural Network Model
Tumor
Controller
Tumors
Drug Delivery
Chemotherapy
Model Predictive Control
Controllers
Cancer
Model predictive control
Minimise
Testing
Target

Keywords

  • Artificial neural network
  • Continuous and pulsed ultrasound
  • Doxorubicin
  • Drug release
  • Model predictive control
  • Polymeric micelles

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modelling and Simulation

Cite this

Husseini, G. A., Mjalli, F. S., Pitt, W. G., & Abdel-Jabbar, N. M. (2009). Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles. In Proceedings of the IASTED International Conference on Modelling and Simulation (pp. 320-325)

Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles. / Husseini, Ghaleb A.; Mjalli, Farouq S.; Pitt, William G.; Abdel-Jabbar, Nabil M.

Proceedings of the IASTED International Conference on Modelling and Simulation. 2009. p. 320-325.

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

Husseini, GA, Mjalli, FS, Pitt, WG & Abdel-Jabbar, NM 2009, Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles. in Proceedings of the IASTED International Conference on Modelling and Simulation. pp. 320-325, 20th IASTED International Conference on Modelling and Simulation, MS 2009, Banff, AB, Canada, 7/6/09.
Husseini GA, Mjalli FS, Pitt WG, Abdel-Jabbar NM. Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles. In Proceedings of the IASTED International Conference on Modelling and Simulation. 2009. p. 320-325
Husseini, Ghaleb A. ; Mjalli, Farouq S. ; Pitt, William G. ; Abdel-Jabbar, Nabil M. / Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles. Proceedings of the IASTED International Conference on Modelling and Simulation. 2009. pp. 320-325
@inproceedings{4142db0194094c6b9eb417defa2af8d4,
title = "Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles",
abstract = "We have been developing a drug delivery system that uses Pluronic P105 micelles to sequester a chemotherapeutic drug - namely, Doxorubicin (Dox) - until it reaches the cancer site. Ultrasound is then applied to release the drug directly to the tumor and in the process minimize the adverse side effects of chemotherapy on non-tumor tissues. Here, we present an artificial neural network (ANN) model that attempts to model the dynamic release of Dox from P105 micelles under different ultrasonic power intensities at two frequencies. The developed ANN model is then utilized to optimize the ultrasound application to achieve a target drug release at the tumor site via an ANN-based model predictive control. The parameters of the controller are then tuned to achieve good reference signal tracking. We were successful in designing and testing a controller capable of adjusting the ultrasound frequency, intensity, and pulse length to sustain constant Dox release.",
keywords = "Artificial neural network, Continuous and pulsed ultrasound, Doxorubicin, Drug release, Model predictive control, Polymeric micelles",
author = "Husseini, {Ghaleb A.} and Mjalli, {Farouq S.} and Pitt, {William G.} and Abdel-Jabbar, {Nabil M.}",
year = "2009",
language = "English",
isbn = "9780889867994",
pages = "320--325",
booktitle = "Proceedings of the IASTED International Conference on Modelling and Simulation",

}

TY - GEN

T1 - Using ANN and MPC to optimize acoustically assisted Doxorubicin release from micelles

AU - Husseini, Ghaleb A.

AU - Mjalli, Farouq S.

AU - Pitt, William G.

AU - Abdel-Jabbar, Nabil M.

PY - 2009

Y1 - 2009

N2 - We have been developing a drug delivery system that uses Pluronic P105 micelles to sequester a chemotherapeutic drug - namely, Doxorubicin (Dox) - until it reaches the cancer site. Ultrasound is then applied to release the drug directly to the tumor and in the process minimize the adverse side effects of chemotherapy on non-tumor tissues. Here, we present an artificial neural network (ANN) model that attempts to model the dynamic release of Dox from P105 micelles under different ultrasonic power intensities at two frequencies. The developed ANN model is then utilized to optimize the ultrasound application to achieve a target drug release at the tumor site via an ANN-based model predictive control. The parameters of the controller are then tuned to achieve good reference signal tracking. We were successful in designing and testing a controller capable of adjusting the ultrasound frequency, intensity, and pulse length to sustain constant Dox release.

AB - We have been developing a drug delivery system that uses Pluronic P105 micelles to sequester a chemotherapeutic drug - namely, Doxorubicin (Dox) - until it reaches the cancer site. Ultrasound is then applied to release the drug directly to the tumor and in the process minimize the adverse side effects of chemotherapy on non-tumor tissues. Here, we present an artificial neural network (ANN) model that attempts to model the dynamic release of Dox from P105 micelles under different ultrasonic power intensities at two frequencies. The developed ANN model is then utilized to optimize the ultrasound application to achieve a target drug release at the tumor site via an ANN-based model predictive control. The parameters of the controller are then tuned to achieve good reference signal tracking. We were successful in designing and testing a controller capable of adjusting the ultrasound frequency, intensity, and pulse length to sustain constant Dox release.

KW - Artificial neural network

KW - Continuous and pulsed ultrasound

KW - Doxorubicin

KW - Drug release

KW - Model predictive control

KW - Polymeric micelles

UR - http://www.scopus.com/inward/record.url?scp=74549208031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74549208031&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780889867994

SP - 320

EP - 325

BT - Proceedings of the IASTED International Conference on Modelling and Simulation

ER -