Feasibility of using neural networks to estimate minimum tumour temperature and perfusion values

D. L. Mcgee, Hal S Tharp, R. B. Roemer

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We examine the ability of neural networks to estimate the tissue perfusion values present and the minimum temperature in numerically calculated (Pennes, Bioheat Transfer Equation) steady-state hyperthermia temperature fields based on a limited number of measured temperatures within this field A hierarchical system of neural networks consisting of a first layer of pattern recognizing neural networks and a second layer of hypersurface reconstructing neural networks is shown to be capable of estimating these variables within a selected error tolerance. The results indicate that estimating the minimum tumour temperature directly with the system of neural networks may be more effective than using the indirect method of numerically recreating a temperature field with perfusion estimates and then obtaining the minimum tumour temperature from the estimated temperature field. Additional results indicate that if the locations of the measured temperatures within the temperature field are selected appropriately, the hierarchical system of neural networks can tolerate a moderate level of model mismatch. This model mismatch can come from errors in modelling the tumour boundaries, the sensor locations, or the magnitude of the power deposition. This paper is not intended to assess or demonstrate clinical applicability but to be a first step in investigating the feasibility of neural networks for parameter estimation related to hyperthermia studies.

Original languageEnglish (US)
Pages (from-to)675-689
Number of pages15
JournalInternational Journal of Hyperthermia
Volume10
Issue number5
DOIs
StatePublished - 1994

Fingerprint

Perfusion
Temperature
Neoplasms
Fever

ASJC Scopus subject areas

  • Cancer Research
  • Physiology
  • Radiological and Ultrasound Technology
  • Physiology (medical)

Cite this

Feasibility of using neural networks to estimate minimum tumour temperature and perfusion values. / Mcgee, D. L.; Tharp, Hal S; Roemer, R. B.

In: International Journal of Hyperthermia, Vol. 10, No. 5, 1994, p. 675-689.

Research output: Contribution to journalArticle

@article{f615b36f70464724b36abdcf1d81a5ea,
title = "Feasibility of using neural networks to estimate minimum tumour temperature and perfusion values",
abstract = "We examine the ability of neural networks to estimate the tissue perfusion values present and the minimum temperature in numerically calculated (Pennes, Bioheat Transfer Equation) steady-state hyperthermia temperature fields based on a limited number of measured temperatures within this field A hierarchical system of neural networks consisting of a first layer of pattern recognizing neural networks and a second layer of hypersurface reconstructing neural networks is shown to be capable of estimating these variables within a selected error tolerance. The results indicate that estimating the minimum tumour temperature directly with the system of neural networks may be more effective than using the indirect method of numerically recreating a temperature field with perfusion estimates and then obtaining the minimum tumour temperature from the estimated temperature field. Additional results indicate that if the locations of the measured temperatures within the temperature field are selected appropriately, the hierarchical system of neural networks can tolerate a moderate level of model mismatch. This model mismatch can come from errors in modelling the tumour boundaries, the sensor locations, or the magnitude of the power deposition. This paper is not intended to assess or demonstrate clinical applicability but to be a first step in investigating the feasibility of neural networks for parameter estimation related to hyperthermia studies.",
author = "Mcgee, {D. L.} and Tharp, {Hal S} and Roemer, {R. B.}",
year = "1994",
doi = "10.3109/02656739409022447",
language = "English (US)",
volume = "10",
pages = "675--689",
journal = "International Journal of Hyperthermia",
issn = "0265-6736",
publisher = "Informa Healthcare",
number = "5",

}

TY - JOUR

T1 - Feasibility of using neural networks to estimate minimum tumour temperature and perfusion values

AU - Mcgee, D. L.

AU - Tharp, Hal S

AU - Roemer, R. B.

PY - 1994

Y1 - 1994

N2 - We examine the ability of neural networks to estimate the tissue perfusion values present and the minimum temperature in numerically calculated (Pennes, Bioheat Transfer Equation) steady-state hyperthermia temperature fields based on a limited number of measured temperatures within this field A hierarchical system of neural networks consisting of a first layer of pattern recognizing neural networks and a second layer of hypersurface reconstructing neural networks is shown to be capable of estimating these variables within a selected error tolerance. The results indicate that estimating the minimum tumour temperature directly with the system of neural networks may be more effective than using the indirect method of numerically recreating a temperature field with perfusion estimates and then obtaining the minimum tumour temperature from the estimated temperature field. Additional results indicate that if the locations of the measured temperatures within the temperature field are selected appropriately, the hierarchical system of neural networks can tolerate a moderate level of model mismatch. This model mismatch can come from errors in modelling the tumour boundaries, the sensor locations, or the magnitude of the power deposition. This paper is not intended to assess or demonstrate clinical applicability but to be a first step in investigating the feasibility of neural networks for parameter estimation related to hyperthermia studies.

AB - We examine the ability of neural networks to estimate the tissue perfusion values present and the minimum temperature in numerically calculated (Pennes, Bioheat Transfer Equation) steady-state hyperthermia temperature fields based on a limited number of measured temperatures within this field A hierarchical system of neural networks consisting of a first layer of pattern recognizing neural networks and a second layer of hypersurface reconstructing neural networks is shown to be capable of estimating these variables within a selected error tolerance. The results indicate that estimating the minimum tumour temperature directly with the system of neural networks may be more effective than using the indirect method of numerically recreating a temperature field with perfusion estimates and then obtaining the minimum tumour temperature from the estimated temperature field. Additional results indicate that if the locations of the measured temperatures within the temperature field are selected appropriately, the hierarchical system of neural networks can tolerate a moderate level of model mismatch. This model mismatch can come from errors in modelling the tumour boundaries, the sensor locations, or the magnitude of the power deposition. This paper is not intended to assess or demonstrate clinical applicability but to be a first step in investigating the feasibility of neural networks for parameter estimation related to hyperthermia studies.

UR - http://www.scopus.com/inward/record.url?scp=0028059172&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028059172&partnerID=8YFLogxK

U2 - 10.3109/02656739409022447

DO - 10.3109/02656739409022447

M3 - Article

C2 - 7806924

AN - SCOPUS:0028059172

VL - 10

SP - 675

EP - 689

JO - International Journal of Hyperthermia

JF - International Journal of Hyperthermia

SN - 0265-6736

IS - 5

ER -