Radiomics based targeted radiotherapy planning (Rad-TRaP): A computational framework for prostate cancer treatment planning with MRI

Rakesh Shiradkar, Tarun K. Podder, Ahmad Algohary, Satish Viswanath, Rodney J. Ellis, Anant Madabhushi

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Background: Radiomics or computer - extracted texture features have been shown to achieve superior performance than multiparametric MRI (mpMRI) signal intensities alone in targeting prostate cancer (PCa) lesions. Radiomics along with deformable co-registration tools can be used to develop a framework to generate targeted focal radiotherapy treatment plans. Methods: The Rad-TRaP framework comprises three distinct modules. Firstly, a module for radiomics based detection of PCa lesions on mpMRI via a feature enabled machine learning classifier. The second module comprises a multi-modal deformable co-registration scheme to map tissue, organ, and delineated target volumes from MRI onto CT. Finally, the third module involves generation of a radiomics based dose plan on MRI for brachytherapy and on CT for EBRT using the target delineations transferred from the MRI to the CT. Results: Rad-TRaP framework was evaluated using a retrospective cohort of 23 patient studies from two different institutions. 11 patients from the first institution were used to train a radiomics classifier, which was used to detect tumor regions in 12 patients from the second institution. The ground truth cancer delineations for training the machine learning classifier were made by an experienced radiation oncologist using mpMRI, knowledge of biopsy location and radiology reports. The detected tumor regions were used to generate treatment plans for brachytherapy using mpMRI, and tumor regions mapped from MRI to CT to generate corresponding treatment plans for EBRT. For each of EBRT and brachytherapy, 3 dose plans were generated - whole gland homogeneous (ℙWH) which is the current clinical standard, radiomics based focal (ℙRF), and whole gland with a radiomics based focal boost (ℙWH). Comparison of ℙRF against conventional ℙWH revealed that targeted focal brachytherapy would result in a marked reduction in dosage to the OARs while ensuring that the prescribed dose is delivered to the lesions. ℙWH resulted in only a marginal increase in dosage to the OARs compared to ℙWH. A similar trend was observed in case of EBRT with ℙWH and ℙWH compared to ℙWH. Conclusions: A radiotherapy planning framework to generate targeted focal treatment plans has been presented. The focal treatment plans generated using the framework showed reduction in dosage to the organs at risk and a boosted dose delivered to the cancerous lesions.

Original languageEnglish (US)
Article number148
JournalRadiation Oncology
Volume11
Issue number1
DOIs
StatePublished - Nov 10 2016

Fingerprint

Brachytherapy
Prostatic Neoplasms
Radiotherapy
Neoplasms
Organs at Risk
Therapeutics
Radiology
Biopsy
Machine Learning

All Science Journal Classification (ASJC) codes

  • Oncology
  • Radiology Nuclear Medicine and imaging

Cite this

Shiradkar, Rakesh ; Podder, Tarun K. ; Algohary, Ahmad ; Viswanath, Satish ; Ellis, Rodney J. ; Madabhushi, Anant. / Radiomics based targeted radiotherapy planning (Rad-TRaP) : A computational framework for prostate cancer treatment planning with MRI. In: Radiation Oncology. 2016 ; Vol. 11, No. 1.
@article{435274fed1ee4c599161649bf29cf5f8,
title = "Radiomics based targeted radiotherapy planning (Rad-TRaP): A computational framework for prostate cancer treatment planning with MRI",
abstract = "Background: Radiomics or computer - extracted texture features have been shown to achieve superior performance than multiparametric MRI (mpMRI) signal intensities alone in targeting prostate cancer (PCa) lesions. Radiomics along with deformable co-registration tools can be used to develop a framework to generate targeted focal radiotherapy treatment plans. Methods: The Rad-TRaP framework comprises three distinct modules. Firstly, a module for radiomics based detection of PCa lesions on mpMRI via a feature enabled machine learning classifier. The second module comprises a multi-modal deformable co-registration scheme to map tissue, organ, and delineated target volumes from MRI onto CT. Finally, the third module involves generation of a radiomics based dose plan on MRI for brachytherapy and on CT for EBRT using the target delineations transferred from the MRI to the CT. Results: Rad-TRaP framework was evaluated using a retrospective cohort of 23 patient studies from two different institutions. 11 patients from the first institution were used to train a radiomics classifier, which was used to detect tumor regions in 12 patients from the second institution. The ground truth cancer delineations for training the machine learning classifier were made by an experienced radiation oncologist using mpMRI, knowledge of biopsy location and radiology reports. The detected tumor regions were used to generate treatment plans for brachytherapy using mpMRI, and tumor regions mapped from MRI to CT to generate corresponding treatment plans for EBRT. For each of EBRT and brachytherapy, 3 dose plans were generated - whole gland homogeneous (ℙWH) which is the current clinical standard, radiomics based focal (ℙRF), and whole gland with a radiomics based focal boost (ℙWH). Comparison of ℙRF against conventional ℙWH revealed that targeted focal brachytherapy would result in a marked reduction in dosage to the OARs while ensuring that the prescribed dose is delivered to the lesions. ℙWH resulted in only a marginal increase in dosage to the OARs compared to ℙWH. A similar trend was observed in case of EBRT with ℙWH and ℙWH compared to ℙWH. Conclusions: A radiotherapy planning framework to generate targeted focal treatment plans has been presented. The focal treatment plans generated using the framework showed reduction in dosage to the organs at risk and a boosted dose delivered to the cancerous lesions.",
author = "Rakesh Shiradkar and Podder, {Tarun K.} and Ahmad Algohary and Satish Viswanath and Ellis, {Rodney J.} and Anant Madabhushi",
year = "2016",
month = "11",
day = "10",
doi = "10.1186/s13014-016-0718-3",
language = "English (US)",
volume = "11",
journal = "Radiation Oncology",
issn = "1748-717X",
publisher = "BioMed Central",
number = "1",

}

Radiomics based targeted radiotherapy planning (Rad-TRaP) : A computational framework for prostate cancer treatment planning with MRI. / Shiradkar, Rakesh; Podder, Tarun K.; Algohary, Ahmad; Viswanath, Satish; Ellis, Rodney J.; Madabhushi, Anant.

In: Radiation Oncology, Vol. 11, No. 1, 148, 10.11.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Radiomics based targeted radiotherapy planning (Rad-TRaP)

T2 - A computational framework for prostate cancer treatment planning with MRI

AU - Shiradkar, Rakesh

AU - Podder, Tarun K.

AU - Algohary, Ahmad

AU - Viswanath, Satish

AU - Ellis, Rodney J.

AU - Madabhushi, Anant

PY - 2016/11/10

Y1 - 2016/11/10

N2 - Background: Radiomics or computer - extracted texture features have been shown to achieve superior performance than multiparametric MRI (mpMRI) signal intensities alone in targeting prostate cancer (PCa) lesions. Radiomics along with deformable co-registration tools can be used to develop a framework to generate targeted focal radiotherapy treatment plans. Methods: The Rad-TRaP framework comprises three distinct modules. Firstly, a module for radiomics based detection of PCa lesions on mpMRI via a feature enabled machine learning classifier. The second module comprises a multi-modal deformable co-registration scheme to map tissue, organ, and delineated target volumes from MRI onto CT. Finally, the third module involves generation of a radiomics based dose plan on MRI for brachytherapy and on CT for EBRT using the target delineations transferred from the MRI to the CT. Results: Rad-TRaP framework was evaluated using a retrospective cohort of 23 patient studies from two different institutions. 11 patients from the first institution were used to train a radiomics classifier, which was used to detect tumor regions in 12 patients from the second institution. The ground truth cancer delineations for training the machine learning classifier were made by an experienced radiation oncologist using mpMRI, knowledge of biopsy location and radiology reports. The detected tumor regions were used to generate treatment plans for brachytherapy using mpMRI, and tumor regions mapped from MRI to CT to generate corresponding treatment plans for EBRT. For each of EBRT and brachytherapy, 3 dose plans were generated - whole gland homogeneous (ℙWH) which is the current clinical standard, radiomics based focal (ℙRF), and whole gland with a radiomics based focal boost (ℙWH). Comparison of ℙRF against conventional ℙWH revealed that targeted focal brachytherapy would result in a marked reduction in dosage to the OARs while ensuring that the prescribed dose is delivered to the lesions. ℙWH resulted in only a marginal increase in dosage to the OARs compared to ℙWH. A similar trend was observed in case of EBRT with ℙWH and ℙWH compared to ℙWH. Conclusions: A radiotherapy planning framework to generate targeted focal treatment plans has been presented. The focal treatment plans generated using the framework showed reduction in dosage to the organs at risk and a boosted dose delivered to the cancerous lesions.

AB - Background: Radiomics or computer - extracted texture features have been shown to achieve superior performance than multiparametric MRI (mpMRI) signal intensities alone in targeting prostate cancer (PCa) lesions. Radiomics along with deformable co-registration tools can be used to develop a framework to generate targeted focal radiotherapy treatment plans. Methods: The Rad-TRaP framework comprises three distinct modules. Firstly, a module for radiomics based detection of PCa lesions on mpMRI via a feature enabled machine learning classifier. The second module comprises a multi-modal deformable co-registration scheme to map tissue, organ, and delineated target volumes from MRI onto CT. Finally, the third module involves generation of a radiomics based dose plan on MRI for brachytherapy and on CT for EBRT using the target delineations transferred from the MRI to the CT. Results: Rad-TRaP framework was evaluated using a retrospective cohort of 23 patient studies from two different institutions. 11 patients from the first institution were used to train a radiomics classifier, which was used to detect tumor regions in 12 patients from the second institution. The ground truth cancer delineations for training the machine learning classifier were made by an experienced radiation oncologist using mpMRI, knowledge of biopsy location and radiology reports. The detected tumor regions were used to generate treatment plans for brachytherapy using mpMRI, and tumor regions mapped from MRI to CT to generate corresponding treatment plans for EBRT. For each of EBRT and brachytherapy, 3 dose plans were generated - whole gland homogeneous (ℙWH) which is the current clinical standard, radiomics based focal (ℙRF), and whole gland with a radiomics based focal boost (ℙWH). Comparison of ℙRF against conventional ℙWH revealed that targeted focal brachytherapy would result in a marked reduction in dosage to the OARs while ensuring that the prescribed dose is delivered to the lesions. ℙWH resulted in only a marginal increase in dosage to the OARs compared to ℙWH. A similar trend was observed in case of EBRT with ℙWH and ℙWH compared to ℙWH. Conclusions: A radiotherapy planning framework to generate targeted focal treatment plans has been presented. The focal treatment plans generated using the framework showed reduction in dosage to the organs at risk and a boosted dose delivered to the cancerous lesions.

UR - http://www.scopus.com/inward/record.url?scp=84998812079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84998812079&partnerID=8YFLogxK

U2 - 10.1186/s13014-016-0718-3

DO - 10.1186/s13014-016-0718-3

M3 - Article

C2 - 27829431

AN - SCOPUS:84998812079

VL - 11

JO - Radiation Oncology

JF - Radiation Oncology

SN - 1748-717X

IS - 1

M1 - 148

ER -