Monitoring brain tumor response to therapy using MRI segmentation

M. Vaidyanathan, Laurence P. Clarke, L. O. Hall, C. Heidtman, R. Velthuizen, K. Gosche, S. Phuphanich, H. Wagner, H. Greenberg, M. L. Silbiger

Research output: Contribution to journalArticle

48 Citations (Scopus)

Abstract

The performance evaluation of a semi-supervised fuzzy c-means (SFCM) clustering method for monitoring brain tumor volume changes during the course of routine clinical radiation-therapeutic and chemo-therapeutic regimens is presented. The tumor volume determined using the SFCM method was compared with the volume estimates obtained using three other methods: (a) a k nearest neighbor (kNN) classifier, b) a grey level thresholding and seed growing (ISG-SG) method and c) a manual pixel labeling (GT) method for ground truth estimation. The SFCM and kNN methods are applied to the multispectral, contrast enhanced T1, proton density, and T2 weighted, magnetic resonance images (MRI) whereas the ISG-SG and GT methods are applied only to the contrast enhanced T1 weighted image. Estimations of tumor volume were made on eight patient cases with follow-up MRI scans performed over a 32 week interval during treatment. The tumor cases studied include one meningioma, two brain metastases and five gliomas. Comparisons with manually labeled ground truth estimations showed that there is a limited agreement between the segmentation methods for absolute tumor volume measurements when using images of patients after treatment. The average intraobserver reproducibility for the SFCM, kNN and ISG-SG methods was found to be 5.8%, 6.6% and 8.9%, respectively. The average of the interobserver reproducibility of these methods was found to be 5.5%, 6.5% and 11.4%, respectively. For the measurement of relative change of tumor volume as required for the response assessment, the multi-spectral methods kNN and SFCM are therefore preferred over the seedgrowing method.

Original languageEnglish (US)
Pages (from-to)323-334
Number of pages12
JournalMagnetic Resonance Imaging
Volume15
Issue number3
DOIs
StatePublished - Jul 11 1997

Fingerprint

Magnetic resonance
Image segmentation
Brain Neoplasms
Tumors
Brain
Magnetic Resonance Spectroscopy
Monitoring
Tumor Burden
Therapeutics
Volume measurement
Labeling
Seed
Protons
Classifiers
Pixels
Radiation
Meningioma
Glioma
Cluster Analysis
Seeds

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Vaidyanathan, M., Clarke, L. P., Hall, L. O., Heidtman, C., Velthuizen, R., Gosche, K., ... Silbiger, M. L. (1997). Monitoring brain tumor response to therapy using MRI segmentation. Magnetic Resonance Imaging, 15(3), 323-334. https://doi.org/10.1016/S0730-725X(96)00386-4
Vaidyanathan, M. ; Clarke, Laurence P. ; Hall, L. O. ; Heidtman, C. ; Velthuizen, R. ; Gosche, K. ; Phuphanich, S. ; Wagner, H. ; Greenberg, H. ; Silbiger, M. L. / Monitoring brain tumor response to therapy using MRI segmentation. In: Magnetic Resonance Imaging. 1997 ; Vol. 15, No. 3. pp. 323-334.
@article{14db56bb211d4dfa8b6c9bcf599465c2,
title = "Monitoring brain tumor response to therapy using MRI segmentation",
abstract = "The performance evaluation of a semi-supervised fuzzy c-means (SFCM) clustering method for monitoring brain tumor volume changes during the course of routine clinical radiation-therapeutic and chemo-therapeutic regimens is presented. The tumor volume determined using the SFCM method was compared with the volume estimates obtained using three other methods: (a) a k nearest neighbor (kNN) classifier, b) a grey level thresholding and seed growing (ISG-SG) method and c) a manual pixel labeling (GT) method for ground truth estimation. The SFCM and kNN methods are applied to the multispectral, contrast enhanced T1, proton density, and T2 weighted, magnetic resonance images (MRI) whereas the ISG-SG and GT methods are applied only to the contrast enhanced T1 weighted image. Estimations of tumor volume were made on eight patient cases with follow-up MRI scans performed over a 32 week interval during treatment. The tumor cases studied include one meningioma, two brain metastases and five gliomas. Comparisons with manually labeled ground truth estimations showed that there is a limited agreement between the segmentation methods for absolute tumor volume measurements when using images of patients after treatment. The average intraobserver reproducibility for the SFCM, kNN and ISG-SG methods was found to be 5.8{\%}, 6.6{\%} and 8.9{\%}, respectively. The average of the interobserver reproducibility of these methods was found to be 5.5{\%}, 6.5{\%} and 11.4{\%}, respectively. For the measurement of relative change of tumor volume as required for the response assessment, the multi-spectral methods kNN and SFCM are therefore preferred over the seedgrowing method.",
author = "M. Vaidyanathan and Clarke, {Laurence P.} and Hall, {L. O.} and C. Heidtman and R. Velthuizen and K. Gosche and S. Phuphanich and H. Wagner and H. Greenberg and Silbiger, {M. L.}",
year = "1997",
month = "7",
day = "11",
doi = "10.1016/S0730-725X(96)00386-4",
language = "English (US)",
volume = "15",
pages = "323--334",
journal = "Magnetic Resonance Imaging",
issn = "0730-725X",
publisher = "Elsevier Inc.",
number = "3",

}

Vaidyanathan, M, Clarke, LP, Hall, LO, Heidtman, C, Velthuizen, R, Gosche, K, Phuphanich, S, Wagner, H, Greenberg, H & Silbiger, ML 1997, 'Monitoring brain tumor response to therapy using MRI segmentation', Magnetic Resonance Imaging, vol. 15, no. 3, pp. 323-334. https://doi.org/10.1016/S0730-725X(96)00386-4

Monitoring brain tumor response to therapy using MRI segmentation. / Vaidyanathan, M.; Clarke, Laurence P.; Hall, L. O.; Heidtman, C.; Velthuizen, R.; Gosche, K.; Phuphanich, S.; Wagner, H.; Greenberg, H.; Silbiger, M. L.

In: Magnetic Resonance Imaging, Vol. 15, No. 3, 11.07.1997, p. 323-334.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Monitoring brain tumor response to therapy using MRI segmentation

AU - Vaidyanathan, M.

AU - Clarke, Laurence P.

AU - Hall, L. O.

AU - Heidtman, C.

AU - Velthuizen, R.

AU - Gosche, K.

AU - Phuphanich, S.

AU - Wagner, H.

AU - Greenberg, H.

AU - Silbiger, M. L.

PY - 1997/7/11

Y1 - 1997/7/11

N2 - The performance evaluation of a semi-supervised fuzzy c-means (SFCM) clustering method for monitoring brain tumor volume changes during the course of routine clinical radiation-therapeutic and chemo-therapeutic regimens is presented. The tumor volume determined using the SFCM method was compared with the volume estimates obtained using three other methods: (a) a k nearest neighbor (kNN) classifier, b) a grey level thresholding and seed growing (ISG-SG) method and c) a manual pixel labeling (GT) method for ground truth estimation. The SFCM and kNN methods are applied to the multispectral, contrast enhanced T1, proton density, and T2 weighted, magnetic resonance images (MRI) whereas the ISG-SG and GT methods are applied only to the contrast enhanced T1 weighted image. Estimations of tumor volume were made on eight patient cases with follow-up MRI scans performed over a 32 week interval during treatment. The tumor cases studied include one meningioma, two brain metastases and five gliomas. Comparisons with manually labeled ground truth estimations showed that there is a limited agreement between the segmentation methods for absolute tumor volume measurements when using images of patients after treatment. The average intraobserver reproducibility for the SFCM, kNN and ISG-SG methods was found to be 5.8%, 6.6% and 8.9%, respectively. The average of the interobserver reproducibility of these methods was found to be 5.5%, 6.5% and 11.4%, respectively. For the measurement of relative change of tumor volume as required for the response assessment, the multi-spectral methods kNN and SFCM are therefore preferred over the seedgrowing method.

AB - The performance evaluation of a semi-supervised fuzzy c-means (SFCM) clustering method for monitoring brain tumor volume changes during the course of routine clinical radiation-therapeutic and chemo-therapeutic regimens is presented. The tumor volume determined using the SFCM method was compared with the volume estimates obtained using three other methods: (a) a k nearest neighbor (kNN) classifier, b) a grey level thresholding and seed growing (ISG-SG) method and c) a manual pixel labeling (GT) method for ground truth estimation. The SFCM and kNN methods are applied to the multispectral, contrast enhanced T1, proton density, and T2 weighted, magnetic resonance images (MRI) whereas the ISG-SG and GT methods are applied only to the contrast enhanced T1 weighted image. Estimations of tumor volume were made on eight patient cases with follow-up MRI scans performed over a 32 week interval during treatment. The tumor cases studied include one meningioma, two brain metastases and five gliomas. Comparisons with manually labeled ground truth estimations showed that there is a limited agreement between the segmentation methods for absolute tumor volume measurements when using images of patients after treatment. The average intraobserver reproducibility for the SFCM, kNN and ISG-SG methods was found to be 5.8%, 6.6% and 8.9%, respectively. The average of the interobserver reproducibility of these methods was found to be 5.5%, 6.5% and 11.4%, respectively. For the measurement of relative change of tumor volume as required for the response assessment, the multi-spectral methods kNN and SFCM are therefore preferred over the seedgrowing method.

UR - http://www.scopus.com/inward/record.url?scp=0030969131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030969131&partnerID=8YFLogxK

U2 - 10.1016/S0730-725X(96)00386-4

DO - 10.1016/S0730-725X(96)00386-4

M3 - Article

C2 - 9201680

AN - SCOPUS:0030969131

VL - 15

SP - 323

EP - 334

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

SN - 0730-725X

IS - 3

ER -

Vaidyanathan M, Clarke LP, Hall LO, Heidtman C, Velthuizen R, Gosche K et al. Monitoring brain tumor response to therapy using MRI segmentation. Magnetic Resonance Imaging. 1997 Jul 11;15(3):323-334. https://doi.org/10.1016/S0730-725X(96)00386-4