Adaptive Mathematical Model of Tumor Response to Radiotherapy Based on CBCT Data

A. Belfatto, M. Riboldi, Delia Ciardo, Agnese Cecconi, Roberta Lazzari, Barbara Alicja Jereczek, Roberto Orecchia, G. Baroni, P. Cerveri

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Mathematical modeling of tumor response to radiotherapy has the potential of enhancing the quality of the treatment plan, which can be even tailored on an individual basis. Lack of extensive in vivo validation has prevented, however, reliable clinical translation of modeling outcomes. Image-guided radiotherapy is a consolidated treatment modality based on computed tomographic (CT) imaging for tumor delineation and volumetric cone beam CT data for periodic checks during treatment. In this study, a macroscopic model of tumor growth and radiation response is proposed, being able to adapt along the treatment course as volumetric tumor data become available. Model parameter learning was based on cone beam CT images in 13 uterine cervical cancer patients, subdivided into three groups (G1, G2, G3) according to tumor type and treatment. Three group-specific parameter sets (PS1, PS2, and PS3) on one general parameter set (PSa) were applied. The corresponding average model fitting errors were 14%, 18%, 13%, and 21%, respectively. The model adaptation testing was performed using volume data of three patients, other than the ones involved in the parameter learning. The extrapolation performance of the general model was improved, while comparable prediction errors were found for the group-specific approach. This suggests that an online parameter tuning can overcome the limitations of a suboptimal patient stratification, which appeared otherwise a critical issue.

Original languageEnglish
Article number7153523
Pages (from-to)802-809
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume20
Issue number3
DOIs
Publication statusPublished - May 1 2016

Fingerprint

Radiotherapy
Tumors
Theoretical Models
Mathematical models
Neoplasms
Cones
Learning
Image-Guided Radiotherapy
Therapeutics
Extrapolation
Uterine Cervical Neoplasms
Tuning
Radiation
Imaging techniques
Testing
Growth

Keywords

  • Image-guided radiotherapy (IGRT)
  • mathematical model
  • parameter adaptation
  • radiation therapy
  • tumor growth

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Adaptive Mathematical Model of Tumor Response to Radiotherapy Based on CBCT Data. / Belfatto, A.; Riboldi, M.; Ciardo, Delia; Cecconi, Agnese; Lazzari, Roberta; Jereczek, Barbara Alicja; Orecchia, Roberto; Baroni, G.; Cerveri, P.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 20, No. 3, 7153523, 01.05.2016, p. 802-809.

Research output: Contribution to journalArticle

@article{80504d50b17442818e854dcc7d2059b3,
title = "Adaptive Mathematical Model of Tumor Response to Radiotherapy Based on CBCT Data",
abstract = "Mathematical modeling of tumor response to radiotherapy has the potential of enhancing the quality of the treatment plan, which can be even tailored on an individual basis. Lack of extensive in vivo validation has prevented, however, reliable clinical translation of modeling outcomes. Image-guided radiotherapy is a consolidated treatment modality based on computed tomographic (CT) imaging for tumor delineation and volumetric cone beam CT data for periodic checks during treatment. In this study, a macroscopic model of tumor growth and radiation response is proposed, being able to adapt along the treatment course as volumetric tumor data become available. Model parameter learning was based on cone beam CT images in 13 uterine cervical cancer patients, subdivided into three groups (G1, G2, G3) according to tumor type and treatment. Three group-specific parameter sets (PS1, PS2, and PS3) on one general parameter set (PSa) were applied. The corresponding average model fitting errors were 14{\%}, 18{\%}, 13{\%}, and 21{\%}, respectively. The model adaptation testing was performed using volume data of three patients, other than the ones involved in the parameter learning. The extrapolation performance of the general model was improved, while comparable prediction errors were found for the group-specific approach. This suggests that an online parameter tuning can overcome the limitations of a suboptimal patient stratification, which appeared otherwise a critical issue.",
keywords = "Image-guided radiotherapy (IGRT), mathematical model, parameter adaptation, radiation therapy, tumor growth",
author = "A. Belfatto and M. Riboldi and Delia Ciardo and Agnese Cecconi and Roberta Lazzari and Jereczek, {Barbara Alicja} and Roberto Orecchia and G. Baroni and P. Cerveri",
year = "2016",
month = "5",
day = "1",
doi = "10.1109/JBHI.2015.2453437",
language = "English",
volume = "20",
pages = "802--809",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Adaptive Mathematical Model of Tumor Response to Radiotherapy Based on CBCT Data

AU - Belfatto, A.

AU - Riboldi, M.

AU - Ciardo, Delia

AU - Cecconi, Agnese

AU - Lazzari, Roberta

AU - Jereczek, Barbara Alicja

AU - Orecchia, Roberto

AU - Baroni, G.

AU - Cerveri, P.

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Mathematical modeling of tumor response to radiotherapy has the potential of enhancing the quality of the treatment plan, which can be even tailored on an individual basis. Lack of extensive in vivo validation has prevented, however, reliable clinical translation of modeling outcomes. Image-guided radiotherapy is a consolidated treatment modality based on computed tomographic (CT) imaging for tumor delineation and volumetric cone beam CT data for periodic checks during treatment. In this study, a macroscopic model of tumor growth and radiation response is proposed, being able to adapt along the treatment course as volumetric tumor data become available. Model parameter learning was based on cone beam CT images in 13 uterine cervical cancer patients, subdivided into three groups (G1, G2, G3) according to tumor type and treatment. Three group-specific parameter sets (PS1, PS2, and PS3) on one general parameter set (PSa) were applied. The corresponding average model fitting errors were 14%, 18%, 13%, and 21%, respectively. The model adaptation testing was performed using volume data of three patients, other than the ones involved in the parameter learning. The extrapolation performance of the general model was improved, while comparable prediction errors were found for the group-specific approach. This suggests that an online parameter tuning can overcome the limitations of a suboptimal patient stratification, which appeared otherwise a critical issue.

AB - Mathematical modeling of tumor response to radiotherapy has the potential of enhancing the quality of the treatment plan, which can be even tailored on an individual basis. Lack of extensive in vivo validation has prevented, however, reliable clinical translation of modeling outcomes. Image-guided radiotherapy is a consolidated treatment modality based on computed tomographic (CT) imaging for tumor delineation and volumetric cone beam CT data for periodic checks during treatment. In this study, a macroscopic model of tumor growth and radiation response is proposed, being able to adapt along the treatment course as volumetric tumor data become available. Model parameter learning was based on cone beam CT images in 13 uterine cervical cancer patients, subdivided into three groups (G1, G2, G3) according to tumor type and treatment. Three group-specific parameter sets (PS1, PS2, and PS3) on one general parameter set (PSa) were applied. The corresponding average model fitting errors were 14%, 18%, 13%, and 21%, respectively. The model adaptation testing was performed using volume data of three patients, other than the ones involved in the parameter learning. The extrapolation performance of the general model was improved, while comparable prediction errors were found for the group-specific approach. This suggests that an online parameter tuning can overcome the limitations of a suboptimal patient stratification, which appeared otherwise a critical issue.

KW - Image-guided radiotherapy (IGRT)

KW - mathematical model

KW - parameter adaptation

KW - radiation therapy

KW - tumor growth

UR - http://www.scopus.com/inward/record.url?scp=84969765350&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969765350&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2015.2453437

DO - 10.1109/JBHI.2015.2453437

M3 - Article

AN - SCOPUS:84969765350

VL - 20

SP - 802

EP - 809

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 3

M1 - 7153523

ER -