A framework for predicting three-dimensional prostate deformation in real time

Alex Jahya, Mark Herink, Sarthak Misra

Research output: Contribution to journalArticleAcademicpeer-review

12 Citations (Scopus)

Abstract

Background Surgical simulation systems can be used to estimate soft tissue deformation during pre- and intra-operative planning. Such systems require a model that can accurately predict the deformation in real time. In this study, we present a back-propagation neural network for predicting three-dimensional (3D) deformation of a phantom that incorporates the anatomy of the male pelvic region, i.e. the prostate and surrounding structures that support it. Method In the experiments and simulations, a needle guide is used to deform the rectal wall. The neural network predicts the deformation based on the relation between the undeformed and deformed shapes of the phantom. Training data are generated using a validated finite element (FE) model of the prostate and its surrounding structures. The FE model is developed from anatomically accurate magnetic resonance (MR) images. An ultrasound-based acoustic radiation force impulse imaging technique is used to measure in situ the shear wave velocity in soft tissue. The velocity is utilized to calculate the elasticities of the phantom. In the simulation study, the displacement and angle of the needle guide are varied. The neural network then predicts 3D phantom deformation for a given input displacement. Results The results of the simulation study show that the maximum absolute linear and angular errors of the nodal displacement and orientation between neural network and FE predicted deformation are 0.03 mm and 0.01, respectively. Conclusions This study shows that a back-propagation neural network can be used to predict prostate deformation. Further, it is also demonstrated that a combination of ultrasound data, MR images and a neural network can be used as a framework for accurately predicting 3D prostate deformation in real time
Original languageUndefined
Pages (from-to)e52-e60
Number of pages9
JournalInternational Journal of Medical Robotics and Computer Assisted Surgery
Volume9
Issue number4
DOIs
Publication statusPublished - 12 Dec 2013

Keywords

  • back-propagation algorithm
  • EWI-23318
  • Prostate
  • Ultrasound
  • Real Time
  • IR-85841
  • Biopsy
  • Fnite element
  • Neural network
  • Needle insertion
  • METIS-296416
  • surgical simulation system

Cite this

@article{37957a0e08974d34b1b85855488f52fb,
title = "A framework for predicting three-dimensional prostate deformation in real time",
abstract = "Background Surgical simulation systems can be used to estimate soft tissue deformation during pre- and intra-operative planning. Such systems require a model that can accurately predict the deformation in real time. In this study, we present a back-propagation neural network for predicting three-dimensional (3D) deformation of a phantom that incorporates the anatomy of the male pelvic region, i.e. the prostate and surrounding structures that support it. Method In the experiments and simulations, a needle guide is used to deform the rectal wall. The neural network predicts the deformation based on the relation between the undeformed and deformed shapes of the phantom. Training data are generated using a validated finite element (FE) model of the prostate and its surrounding structures. The FE model is developed from anatomically accurate magnetic resonance (MR) images. An ultrasound-based acoustic radiation force impulse imaging technique is used to measure in situ the shear wave velocity in soft tissue. The velocity is utilized to calculate the elasticities of the phantom. In the simulation study, the displacement and angle of the needle guide are varied. The neural network then predicts 3D phantom deformation for a given input displacement. Results The results of the simulation study show that the maximum absolute linear and angular errors of the nodal displacement and orientation between neural network and FE predicted deformation are 0.03 mm and 0.01, respectively. Conclusions This study shows that a back-propagation neural network can be used to predict prostate deformation. Further, it is also demonstrated that a combination of ultrasound data, MR images and a neural network can be used as a framework for accurately predicting 3D prostate deformation in real time",
keywords = "back-propagation algorithm, EWI-23318, Prostate, Ultrasound, Real Time, IR-85841, Biopsy, Fnite element, Neural network, Needle insertion, METIS-296416, surgical simulation system",
author = "Alex Jahya and Mark Herink and Sarthak Misra",
note = "eemcs-eprint-23318",
year = "2013",
month = "12",
day = "12",
doi = "10.1002/rcs.1493",
language = "Undefined",
volume = "9",
pages = "e52--e60",
journal = "International Journal of Medical Robotics and Computer Assisted Surgery",
issn = "1478-5951",
publisher = "Wiley",
number = "4",

}

A framework for predicting three-dimensional prostate deformation in real time. / Jahya, Alex; Herink, Mark; Misra, Sarthak.

In: International Journal of Medical Robotics and Computer Assisted Surgery, Vol. 9, No. 4, 12.12.2013, p. e52-e60.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A framework for predicting three-dimensional prostate deformation in real time

AU - Jahya, Alex

AU - Herink, Mark

AU - Misra, Sarthak

N1 - eemcs-eprint-23318

PY - 2013/12/12

Y1 - 2013/12/12

N2 - Background Surgical simulation systems can be used to estimate soft tissue deformation during pre- and intra-operative planning. Such systems require a model that can accurately predict the deformation in real time. In this study, we present a back-propagation neural network for predicting three-dimensional (3D) deformation of a phantom that incorporates the anatomy of the male pelvic region, i.e. the prostate and surrounding structures that support it. Method In the experiments and simulations, a needle guide is used to deform the rectal wall. The neural network predicts the deformation based on the relation between the undeformed and deformed shapes of the phantom. Training data are generated using a validated finite element (FE) model of the prostate and its surrounding structures. The FE model is developed from anatomically accurate magnetic resonance (MR) images. An ultrasound-based acoustic radiation force impulse imaging technique is used to measure in situ the shear wave velocity in soft tissue. The velocity is utilized to calculate the elasticities of the phantom. In the simulation study, the displacement and angle of the needle guide are varied. The neural network then predicts 3D phantom deformation for a given input displacement. Results The results of the simulation study show that the maximum absolute linear and angular errors of the nodal displacement and orientation between neural network and FE predicted deformation are 0.03 mm and 0.01, respectively. Conclusions This study shows that a back-propagation neural network can be used to predict prostate deformation. Further, it is also demonstrated that a combination of ultrasound data, MR images and a neural network can be used as a framework for accurately predicting 3D prostate deformation in real time

AB - Background Surgical simulation systems can be used to estimate soft tissue deformation during pre- and intra-operative planning. Such systems require a model that can accurately predict the deformation in real time. In this study, we present a back-propagation neural network for predicting three-dimensional (3D) deformation of a phantom that incorporates the anatomy of the male pelvic region, i.e. the prostate and surrounding structures that support it. Method In the experiments and simulations, a needle guide is used to deform the rectal wall. The neural network predicts the deformation based on the relation between the undeformed and deformed shapes of the phantom. Training data are generated using a validated finite element (FE) model of the prostate and its surrounding structures. The FE model is developed from anatomically accurate magnetic resonance (MR) images. An ultrasound-based acoustic radiation force impulse imaging technique is used to measure in situ the shear wave velocity in soft tissue. The velocity is utilized to calculate the elasticities of the phantom. In the simulation study, the displacement and angle of the needle guide are varied. The neural network then predicts 3D phantom deformation for a given input displacement. Results The results of the simulation study show that the maximum absolute linear and angular errors of the nodal displacement and orientation between neural network and FE predicted deformation are 0.03 mm and 0.01, respectively. Conclusions This study shows that a back-propagation neural network can be used to predict prostate deformation. Further, it is also demonstrated that a combination of ultrasound data, MR images and a neural network can be used as a framework for accurately predicting 3D prostate deformation in real time

KW - back-propagation algorithm

KW - EWI-23318

KW - Prostate

KW - Ultrasound

KW - Real Time

KW - IR-85841

KW - Biopsy

KW - Fnite element

KW - Neural network

KW - Needle insertion

KW - METIS-296416

KW - surgical simulation system

U2 - 10.1002/rcs.1493

DO - 10.1002/rcs.1493

M3 - Article

VL - 9

SP - e52-e60

JO - International Journal of Medical Robotics and Computer Assisted Surgery

JF - International Journal of Medical Robotics and Computer Assisted Surgery

SN - 1478-5951

IS - 4

ER -