Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation

Gloria P. Mazzara, Robert P. Velthuizen, James L. Pearlman, Harvey M. Greenberg, Henry Wagner Jr.

Research output: Contribution to journalArticle

107 Citations (Scopus)

Abstract

Purpose To assess the effectiveness of two automated magnetic resonance imaging (MRI) segmentation methods in determining the gross tumor volume (GTV) of brain tumors for use in radiation therapy treatment planning. Methods and materials Two automated MRI tumor segmentation methods (supervised k-nearest neighbors [kNN] and automatic knowledge-guided [KG]) were evaluated for their potential as "cyber colleagues." This required an initial determination of the accuracy and variability of radiation oncologists engaged in the manual definition of the GTV in MRI registered with computed tomography images for 11 glioma patients. Three sets of contours were defined for each of these patients by three radiation oncologists. These outlines were compared directly to establish inter- and intraoperator variability among the radiation oncologists. A novel, probabilistic measurement of accuracy was introduced to compare the level of agreement among the automated MRI segmentations. The accuracy was determined by comparing the volumes obtained by the automated segmentation methods with the weighted average volumes prepared by the radiation oncologists. Results Intra- and inter-operator variability in outlining was found to be an average of 20% ± 15% and 28% ± 12%, respectively. Lowest intraoperator variability was found for the physician who spent the most time producing the contours. The average accuracy of the kNN segmentation method was 56% ± 6% for all 11 cases, whereas that of the KG method was 52% ± 7% for 7 of the 11 cases when compared with the physician contours. For the areas of the contours where the oncologists were in substantial agreement (i.e., the center of the tumor volume), the accuracy of kNN and KG was 75% and 72%, respectively. The automated segmentation methods were found to be least accurate in outlining at the edges of the tumor volume. Conclusions The kNN method was able to segment all cases, whereas the KG method was limited to enhancing tumors and gliomas with clear enhancing edges and no cystic formation. Both methods undersegment the tumor volume when compared with the radiation oncologists and performed within the variability of the contouring performed by experienced radiation oncologists based on the same data.

Original languageEnglish (US)
Pages (from-to)300-312
Number of pages13
JournalInternational Journal of Radiation Oncology Biology Physics
Volume59
Issue number1
DOIs
StatePublished - May 1 2004

Fingerprint

Tumor Burden
Brain Neoplasms
brain
magnetic resonance
planning
tumors
Magnetic Resonance Imaging
Radiation
radiation
physicians
Therapeutics
Glioma
operators
Physicians
radiation therapy
tomography
Radiation Oncologists
Neoplasms
Radiotherapy
Tomography

All Science Journal Classification (ASJC) codes

  • Radiation
  • Oncology
  • Radiology Nuclear Medicine and imaging
  • Cancer Research

Cite this

Mazzara, Gloria P. ; Velthuizen, Robert P. ; Pearlman, James L. ; Greenberg, Harvey M. ; Wagner Jr., Henry. / Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation. In: International Journal of Radiation Oncology Biology Physics. 2004 ; Vol. 59, No. 1. pp. 300-312.
@article{a0fa0f7c368749abb6492d8ae625cd62,
title = "Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation",
abstract = "Purpose To assess the effectiveness of two automated magnetic resonance imaging (MRI) segmentation methods in determining the gross tumor volume (GTV) of brain tumors for use in radiation therapy treatment planning. Methods and materials Two automated MRI tumor segmentation methods (supervised k-nearest neighbors [kNN] and automatic knowledge-guided [KG]) were evaluated for their potential as {"}cyber colleagues.{"} This required an initial determination of the accuracy and variability of radiation oncologists engaged in the manual definition of the GTV in MRI registered with computed tomography images for 11 glioma patients. Three sets of contours were defined for each of these patients by three radiation oncologists. These outlines were compared directly to establish inter- and intraoperator variability among the radiation oncologists. A novel, probabilistic measurement of accuracy was introduced to compare the level of agreement among the automated MRI segmentations. The accuracy was determined by comparing the volumes obtained by the automated segmentation methods with the weighted average volumes prepared by the radiation oncologists. Results Intra- and inter-operator variability in outlining was found to be an average of 20{\%} ± 15{\%} and 28{\%} ± 12{\%}, respectively. Lowest intraoperator variability was found for the physician who spent the most time producing the contours. The average accuracy of the kNN segmentation method was 56{\%} ± 6{\%} for all 11 cases, whereas that of the KG method was 52{\%} ± 7{\%} for 7 of the 11 cases when compared with the physician contours. For the areas of the contours where the oncologists were in substantial agreement (i.e., the center of the tumor volume), the accuracy of kNN and KG was 75{\%} and 72{\%}, respectively. The automated segmentation methods were found to be least accurate in outlining at the edges of the tumor volume. Conclusions The kNN method was able to segment all cases, whereas the KG method was limited to enhancing tumors and gliomas with clear enhancing edges and no cystic formation. Both methods undersegment the tumor volume when compared with the radiation oncologists and performed within the variability of the contouring performed by experienced radiation oncologists based on the same data.",
author = "Mazzara, {Gloria P.} and Velthuizen, {Robert P.} and Pearlman, {James L.} and Greenberg, {Harvey M.} and {Wagner Jr.}, Henry",
year = "2004",
month = "5",
day = "1",
doi = "10.1016/j.ijrobp.2004.01.026",
language = "English (US)",
volume = "59",
pages = "300--312",
journal = "International Journal of Radiation Oncology Biology Physics",
issn = "0360-3016",
publisher = "Elsevier Inc.",
number = "1",

}

Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation. / Mazzara, Gloria P.; Velthuizen, Robert P.; Pearlman, James L.; Greenberg, Harvey M.; Wagner Jr., Henry.

In: International Journal of Radiation Oncology Biology Physics, Vol. 59, No. 1, 01.05.2004, p. 300-312.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation

AU - Mazzara, Gloria P.

AU - Velthuizen, Robert P.

AU - Pearlman, James L.

AU - Greenberg, Harvey M.

AU - Wagner Jr., Henry

PY - 2004/5/1

Y1 - 2004/5/1

N2 - Purpose To assess the effectiveness of two automated magnetic resonance imaging (MRI) segmentation methods in determining the gross tumor volume (GTV) of brain tumors for use in radiation therapy treatment planning. Methods and materials Two automated MRI tumor segmentation methods (supervised k-nearest neighbors [kNN] and automatic knowledge-guided [KG]) were evaluated for their potential as "cyber colleagues." This required an initial determination of the accuracy and variability of radiation oncologists engaged in the manual definition of the GTV in MRI registered with computed tomography images for 11 glioma patients. Three sets of contours were defined for each of these patients by three radiation oncologists. These outlines were compared directly to establish inter- and intraoperator variability among the radiation oncologists. A novel, probabilistic measurement of accuracy was introduced to compare the level of agreement among the automated MRI segmentations. The accuracy was determined by comparing the volumes obtained by the automated segmentation methods with the weighted average volumes prepared by the radiation oncologists. Results Intra- and inter-operator variability in outlining was found to be an average of 20% ± 15% and 28% ± 12%, respectively. Lowest intraoperator variability was found for the physician who spent the most time producing the contours. The average accuracy of the kNN segmentation method was 56% ± 6% for all 11 cases, whereas that of the KG method was 52% ± 7% for 7 of the 11 cases when compared with the physician contours. For the areas of the contours where the oncologists were in substantial agreement (i.e., the center of the tumor volume), the accuracy of kNN and KG was 75% and 72%, respectively. The automated segmentation methods were found to be least accurate in outlining at the edges of the tumor volume. Conclusions The kNN method was able to segment all cases, whereas the KG method was limited to enhancing tumors and gliomas with clear enhancing edges and no cystic formation. Both methods undersegment the tumor volume when compared with the radiation oncologists and performed within the variability of the contouring performed by experienced radiation oncologists based on the same data.

AB - Purpose To assess the effectiveness of two automated magnetic resonance imaging (MRI) segmentation methods in determining the gross tumor volume (GTV) of brain tumors for use in radiation therapy treatment planning. Methods and materials Two automated MRI tumor segmentation methods (supervised k-nearest neighbors [kNN] and automatic knowledge-guided [KG]) were evaluated for their potential as "cyber colleagues." This required an initial determination of the accuracy and variability of radiation oncologists engaged in the manual definition of the GTV in MRI registered with computed tomography images for 11 glioma patients. Three sets of contours were defined for each of these patients by three radiation oncologists. These outlines were compared directly to establish inter- and intraoperator variability among the radiation oncologists. A novel, probabilistic measurement of accuracy was introduced to compare the level of agreement among the automated MRI segmentations. The accuracy was determined by comparing the volumes obtained by the automated segmentation methods with the weighted average volumes prepared by the radiation oncologists. Results Intra- and inter-operator variability in outlining was found to be an average of 20% ± 15% and 28% ± 12%, respectively. Lowest intraoperator variability was found for the physician who spent the most time producing the contours. The average accuracy of the kNN segmentation method was 56% ± 6% for all 11 cases, whereas that of the KG method was 52% ± 7% for 7 of the 11 cases when compared with the physician contours. For the areas of the contours where the oncologists were in substantial agreement (i.e., the center of the tumor volume), the accuracy of kNN and KG was 75% and 72%, respectively. The automated segmentation methods were found to be least accurate in outlining at the edges of the tumor volume. Conclusions The kNN method was able to segment all cases, whereas the KG method was limited to enhancing tumors and gliomas with clear enhancing edges and no cystic formation. Both methods undersegment the tumor volume when compared with the radiation oncologists and performed within the variability of the contouring performed by experienced radiation oncologists based on the same data.

UR - http://www.scopus.com/inward/record.url?scp=16544366594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=16544366594&partnerID=8YFLogxK

U2 - 10.1016/j.ijrobp.2004.01.026

DO - 10.1016/j.ijrobp.2004.01.026

M3 - Article

C2 - 15093927

AN - SCOPUS:16544366594

VL - 59

SP - 300

EP - 312

JO - International Journal of Radiation Oncology Biology Physics

JF - International Journal of Radiation Oncology Biology Physics

SN - 0360-3016

IS - 1

ER -