Tumor radio-sensitivity assessment by means of volume data and magnetic resonance indices measured on prostate tumor bearing rats

Antonella Belfatto, Derek A. White, Ralph P. Mason, Zhang Zhang, Strahinja Stojadinovic, Guido Baroni, Pietro Cerveri

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Purpose: Radiation therapy is one of the most common treatments in the fight against prostate cancer, since it is used to control the tumor (early stages), to slow its progression, and even to control pain (metastasis). Although many factors (e.g., tumor oxygenation) are known to influence treatment efficacy, radiotherapy doses and fractionation schedules are often prescribed according to the principle "one-fits-all," with little personalization. Therefore, the authors aim at predicting the outcome of radiation therapy a priori starting from morphologic and functional information to move a step forward in the treatment customization. Methods: The authors propose a two-step protocol to predict the effects of radiation therapy on individual basis. First, one macroscopic mathematical model of tumor evolution was trained on tumor volume progression, measured by caliper, of eighteen Dunning R3327-AT1 bearing rats. Nine rats inhaled 100% O2 during irradiation (oxy), while the others were allowed to breathe air. Second, a supervised learning of the weight and biases of two feedforward neural networks was performed to predict the radio-sensitivity (target) from the initial volume and oxygenation-related information (inputs) for each rat group (air and oxygen breathing). To this purpose, four MRI-based indices related to blood and tissue oxygenation were computed, namely, the variation of signal intensity (ΔSI) in interleaved blood oxygen level dependent and tissue oxygen level dependent (IBT) sequences as well as changes in longitudinal (ΔR1) and transverse (ΔR2) relaxation rates. Results: An inverse correlation of the radio-sensitivity parameter, assessed by the model, was found with respect the ΔR2 (-0.65) for the oxy group. A further subdivision according to positive and negative values of ΔR2 showed a larger average radio-sensitivity for the oxy rats with ΔR2 <0 and a significant difference in the two distributions (p <0.05). Finally, a leave-one-out procedure yielded a radio-sensitivity error lower than 20% in both neural networks. Conclusions: While preliminary, these specific results suggest that subjects affected by the same pathology can benefit differently from the same irradiation modalities and support the usefulness of IBT in discriminating between different responses.

Original languageEnglish (US)
Pages (from-to)1275-1284
Number of pages10
JournalMedical Physics
Volume43
Issue number3
DOIs
StatePublished - Mar 1 2016

Fingerprint

Radio
Prostate
Magnetic Resonance Spectroscopy
Radiotherapy
Oxygen
Neoplasms
Air
Dose Fractionation
Tumor Burden
Prostatic Neoplasms
Appointments and Schedules
Respiration
Theoretical Models
Learning
Pathology
Neoplasm Metastasis
Weights and Measures
Pain
Therapeutics

Keywords

  • BOLD
  • LQ model
  • mathematical model
  • neural network
  • prostate cancer
  • radio-sensitivity
  • TOLD

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Tumor radio-sensitivity assessment by means of volume data and magnetic resonance indices measured on prostate tumor bearing rats. / Belfatto, Antonella; White, Derek A.; Mason, Ralph P.; Zhang, Zhang; Stojadinovic, Strahinja; Baroni, Guido; Cerveri, Pietro.

In: Medical Physics, Vol. 43, No. 3, 01.03.2016, p. 1275-1284.

Research output: Contribution to journalArticle

Belfatto, Antonella ; White, Derek A. ; Mason, Ralph P. ; Zhang, Zhang ; Stojadinovic, Strahinja ; Baroni, Guido ; Cerveri, Pietro. / Tumor radio-sensitivity assessment by means of volume data and magnetic resonance indices measured on prostate tumor bearing rats. In: Medical Physics. 2016 ; Vol. 43, No. 3. pp. 1275-1284.
@article{9da55674c4a94088befb19834809aa2a,
title = "Tumor radio-sensitivity assessment by means of volume data and magnetic resonance indices measured on prostate tumor bearing rats",
abstract = "Purpose: Radiation therapy is one of the most common treatments in the fight against prostate cancer, since it is used to control the tumor (early stages), to slow its progression, and even to control pain (metastasis). Although many factors (e.g., tumor oxygenation) are known to influence treatment efficacy, radiotherapy doses and fractionation schedules are often prescribed according to the principle {"}one-fits-all,{"} with little personalization. Therefore, the authors aim at predicting the outcome of radiation therapy a priori starting from morphologic and functional information to move a step forward in the treatment customization. Methods: The authors propose a two-step protocol to predict the effects of radiation therapy on individual basis. First, one macroscopic mathematical model of tumor evolution was trained on tumor volume progression, measured by caliper, of eighteen Dunning R3327-AT1 bearing rats. Nine rats inhaled 100{\%} O2 during irradiation (oxy), while the others were allowed to breathe air. Second, a supervised learning of the weight and biases of two feedforward neural networks was performed to predict the radio-sensitivity (target) from the initial volume and oxygenation-related information (inputs) for each rat group (air and oxygen breathing). To this purpose, four MRI-based indices related to blood and tissue oxygenation were computed, namely, the variation of signal intensity (ΔSI) in interleaved blood oxygen level dependent and tissue oxygen level dependent (IBT) sequences as well as changes in longitudinal (ΔR1) and transverse (ΔR2∗) relaxation rates. Results: An inverse correlation of the radio-sensitivity parameter, assessed by the model, was found with respect the ΔR2∗ (-0.65) for the oxy group. A further subdivision according to positive and negative values of ΔR2∗ showed a larger average radio-sensitivity for the oxy rats with ΔR2∗ <0 and a significant difference in the two distributions (p <0.05). Finally, a leave-one-out procedure yielded a radio-sensitivity error lower than 20{\%} in both neural networks. Conclusions: While preliminary, these specific results suggest that subjects affected by the same pathology can benefit differently from the same irradiation modalities and support the usefulness of IBT in discriminating between different responses.",
keywords = "BOLD, LQ model, mathematical model, neural network, prostate cancer, radio-sensitivity, TOLD",
author = "Antonella Belfatto and White, {Derek A.} and Mason, {Ralph P.} and Zhang Zhang and Strahinja Stojadinovic and Guido Baroni and Pietro Cerveri",
year = "2016",
month = "3",
day = "1",
doi = "10.1118/1.4941746",
language = "English (US)",
volume = "43",
pages = "1275--1284",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "3",

}

TY - JOUR

T1 - Tumor radio-sensitivity assessment by means of volume data and magnetic resonance indices measured on prostate tumor bearing rats

AU - Belfatto, Antonella

AU - White, Derek A.

AU - Mason, Ralph P.

AU - Zhang, Zhang

AU - Stojadinovic, Strahinja

AU - Baroni, Guido

AU - Cerveri, Pietro

PY - 2016/3/1

Y1 - 2016/3/1

N2 - Purpose: Radiation therapy is one of the most common treatments in the fight against prostate cancer, since it is used to control the tumor (early stages), to slow its progression, and even to control pain (metastasis). Although many factors (e.g., tumor oxygenation) are known to influence treatment efficacy, radiotherapy doses and fractionation schedules are often prescribed according to the principle "one-fits-all," with little personalization. Therefore, the authors aim at predicting the outcome of radiation therapy a priori starting from morphologic and functional information to move a step forward in the treatment customization. Methods: The authors propose a two-step protocol to predict the effects of radiation therapy on individual basis. First, one macroscopic mathematical model of tumor evolution was trained on tumor volume progression, measured by caliper, of eighteen Dunning R3327-AT1 bearing rats. Nine rats inhaled 100% O2 during irradiation (oxy), while the others were allowed to breathe air. Second, a supervised learning of the weight and biases of two feedforward neural networks was performed to predict the radio-sensitivity (target) from the initial volume and oxygenation-related information (inputs) for each rat group (air and oxygen breathing). To this purpose, four MRI-based indices related to blood and tissue oxygenation were computed, namely, the variation of signal intensity (ΔSI) in interleaved blood oxygen level dependent and tissue oxygen level dependent (IBT) sequences as well as changes in longitudinal (ΔR1) and transverse (ΔR2∗) relaxation rates. Results: An inverse correlation of the radio-sensitivity parameter, assessed by the model, was found with respect the ΔR2∗ (-0.65) for the oxy group. A further subdivision according to positive and negative values of ΔR2∗ showed a larger average radio-sensitivity for the oxy rats with ΔR2∗ <0 and a significant difference in the two distributions (p <0.05). Finally, a leave-one-out procedure yielded a radio-sensitivity error lower than 20% in both neural networks. Conclusions: While preliminary, these specific results suggest that subjects affected by the same pathology can benefit differently from the same irradiation modalities and support the usefulness of IBT in discriminating between different responses.

AB - Purpose: Radiation therapy is one of the most common treatments in the fight against prostate cancer, since it is used to control the tumor (early stages), to slow its progression, and even to control pain (metastasis). Although many factors (e.g., tumor oxygenation) are known to influence treatment efficacy, radiotherapy doses and fractionation schedules are often prescribed according to the principle "one-fits-all," with little personalization. Therefore, the authors aim at predicting the outcome of radiation therapy a priori starting from morphologic and functional information to move a step forward in the treatment customization. Methods: The authors propose a two-step protocol to predict the effects of radiation therapy on individual basis. First, one macroscopic mathematical model of tumor evolution was trained on tumor volume progression, measured by caliper, of eighteen Dunning R3327-AT1 bearing rats. Nine rats inhaled 100% O2 during irradiation (oxy), while the others were allowed to breathe air. Second, a supervised learning of the weight and biases of two feedforward neural networks was performed to predict the radio-sensitivity (target) from the initial volume and oxygenation-related information (inputs) for each rat group (air and oxygen breathing). To this purpose, four MRI-based indices related to blood and tissue oxygenation were computed, namely, the variation of signal intensity (ΔSI) in interleaved blood oxygen level dependent and tissue oxygen level dependent (IBT) sequences as well as changes in longitudinal (ΔR1) and transverse (ΔR2∗) relaxation rates. Results: An inverse correlation of the radio-sensitivity parameter, assessed by the model, was found with respect the ΔR2∗ (-0.65) for the oxy group. A further subdivision according to positive and negative values of ΔR2∗ showed a larger average radio-sensitivity for the oxy rats with ΔR2∗ <0 and a significant difference in the two distributions (p <0.05). Finally, a leave-one-out procedure yielded a radio-sensitivity error lower than 20% in both neural networks. Conclusions: While preliminary, these specific results suggest that subjects affected by the same pathology can benefit differently from the same irradiation modalities and support the usefulness of IBT in discriminating between different responses.

KW - BOLD

KW - LQ model

KW - mathematical model

KW - neural network

KW - prostate cancer

KW - radio-sensitivity

KW - TOLD

UR - http://www.scopus.com/inward/record.url?scp=84958267608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958267608&partnerID=8YFLogxK

U2 - 10.1118/1.4941746

DO - 10.1118/1.4941746

M3 - Article

C2 - 26936712

AN - SCOPUS:84958267608

VL - 43

SP - 1275

EP - 1284

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 3

ER -