A semiautomatic method for multiple sclerosis lesion segmentation on Dual-Echo MR imaging: Application in a multicenter context

L. Storelli, E. Pagani, M. A. Rocca, M. A. Horsfield, A. Gallo, A. Bisecco, M. Battaglini, N. De Stefano, H. Vrenken, D. L. Thomas, L. Mancini, S. Ropele, C. Enzinger, P. Preziosa, M. Filippi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

BACKGROUND AND PURPOSE: The automatic segmentation of MS lesions could reduce time required for image processing together with inter-And intraoperator variability for research and clinical trials. A multicenter validation of a proposed semiautomatic method for hyperintense MS lesion segmentation on dual-echo MR imaging is presented. MATERIALS AND METHODS: The classification technique used is based on a region-growing approach starting from manual lesion identification by an expert observer with a final segmentation-refinement step. The method was validated in a cohort of 52 patients with relapsing-remitting MS, with dual-echo images acquired in 6 different European centers. RESULTS: We found a mathematic expression that made the optimization of the method independent of the need for a training dataset. The automatic segmentation was in good agreement with the manual segmentation (dice similarity coefficient = 0.62 and root mean square error = 2 mL). Assessment of the segmentation errors showed no significant differences in algorithm performance between the different MR scanner manufacturers (P ≥ .05). CONCLUSIONS: The method proved to be robust, and no center-specific training of the algorithm was required, offering the possibility for application in a clinical setting. Adoption of the method should lead to improved reliability and less operator time required for image analysis in research and clinical trials in MS.

Original languageEnglish
Pages (from-to)2043-2049
Number of pages7
JournalAmerican Journal of Neuroradiology
Volume37
Issue number11
DOIs
Publication statusPublished - Nov 1 2016

Fingerprint

Multiple Sclerosis
Clinical Trials
Mathematics
Research

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Clinical Neurology

Cite this

A semiautomatic method for multiple sclerosis lesion segmentation on Dual-Echo MR imaging : Application in a multicenter context. / Storelli, L.; Pagani, E.; Rocca, M. A.; Horsfield, M. A.; Gallo, A.; Bisecco, A.; Battaglini, M.; De Stefano, N.; Vrenken, H.; Thomas, D. L.; Mancini, L.; Ropele, S.; Enzinger, C.; Preziosa, P.; Filippi, M.

In: American Journal of Neuroradiology, Vol. 37, No. 11, 01.11.2016, p. 2043-2049.

Research output: Contribution to journalArticle

Storelli, L, Pagani, E, Rocca, MA, Horsfield, MA, Gallo, A, Bisecco, A, Battaglini, M, De Stefano, N, Vrenken, H, Thomas, DL, Mancini, L, Ropele, S, Enzinger, C, Preziosa, P & Filippi, M 2016, 'A semiautomatic method for multiple sclerosis lesion segmentation on Dual-Echo MR imaging: Application in a multicenter context', American Journal of Neuroradiology, vol. 37, no. 11, pp. 2043-2049. https://doi.org/10.3174/ajnr.A4874
Storelli, L. ; Pagani, E. ; Rocca, M. A. ; Horsfield, M. A. ; Gallo, A. ; Bisecco, A. ; Battaglini, M. ; De Stefano, N. ; Vrenken, H. ; Thomas, D. L. ; Mancini, L. ; Ropele, S. ; Enzinger, C. ; Preziosa, P. ; Filippi, M. / A semiautomatic method for multiple sclerosis lesion segmentation on Dual-Echo MR imaging : Application in a multicenter context. In: American Journal of Neuroradiology. 2016 ; Vol. 37, No. 11. pp. 2043-2049.
@article{a35c59be15684e37bd7cfd2ef5e88f61,
title = "A semiautomatic method for multiple sclerosis lesion segmentation on Dual-Echo MR imaging: Application in a multicenter context",
abstract = "BACKGROUND AND PURPOSE: The automatic segmentation of MS lesions could reduce time required for image processing together with inter-And intraoperator variability for research and clinical trials. A multicenter validation of a proposed semiautomatic method for hyperintense MS lesion segmentation on dual-echo MR imaging is presented. MATERIALS AND METHODS: The classification technique used is based on a region-growing approach starting from manual lesion identification by an expert observer with a final segmentation-refinement step. The method was validated in a cohort of 52 patients with relapsing-remitting MS, with dual-echo images acquired in 6 different European centers. RESULTS: We found a mathematic expression that made the optimization of the method independent of the need for a training dataset. The automatic segmentation was in good agreement with the manual segmentation (dice similarity coefficient = 0.62 and root mean square error = 2 mL). Assessment of the segmentation errors showed no significant differences in algorithm performance between the different MR scanner manufacturers (P ≥ .05). CONCLUSIONS: The method proved to be robust, and no center-specific training of the algorithm was required, offering the possibility for application in a clinical setting. Adoption of the method should lead to improved reliability and less operator time required for image analysis in research and clinical trials in MS.",
author = "L. Storelli and E. Pagani and Rocca, {M. A.} and Horsfield, {M. A.} and A. Gallo and A. Bisecco and M. Battaglini and {De Stefano}, N. and H. Vrenken and Thomas, {D. L.} and L. Mancini and S. Ropele and C. Enzinger and P. Preziosa and M. Filippi",
year = "2016",
month = "11",
day = "1",
doi = "10.3174/ajnr.A4874",
language = "English",
volume = "37",
pages = "2043--2049",
journal = "American Journal of Neuroradiology",
issn = "0195-6108",
publisher = "American Society of Neuroradiology",
number = "11",

}

TY - JOUR

T1 - A semiautomatic method for multiple sclerosis lesion segmentation on Dual-Echo MR imaging

T2 - Application in a multicenter context

AU - Storelli, L.

AU - Pagani, E.

AU - Rocca, M. A.

AU - Horsfield, M. A.

AU - Gallo, A.

AU - Bisecco, A.

AU - Battaglini, M.

AU - De Stefano, N.

AU - Vrenken, H.

AU - Thomas, D. L.

AU - Mancini, L.

AU - Ropele, S.

AU - Enzinger, C.

AU - Preziosa, P.

AU - Filippi, M.

PY - 2016/11/1

Y1 - 2016/11/1

N2 - BACKGROUND AND PURPOSE: The automatic segmentation of MS lesions could reduce time required for image processing together with inter-And intraoperator variability for research and clinical trials. A multicenter validation of a proposed semiautomatic method for hyperintense MS lesion segmentation on dual-echo MR imaging is presented. MATERIALS AND METHODS: The classification technique used is based on a region-growing approach starting from manual lesion identification by an expert observer with a final segmentation-refinement step. The method was validated in a cohort of 52 patients with relapsing-remitting MS, with dual-echo images acquired in 6 different European centers. RESULTS: We found a mathematic expression that made the optimization of the method independent of the need for a training dataset. The automatic segmentation was in good agreement with the manual segmentation (dice similarity coefficient = 0.62 and root mean square error = 2 mL). Assessment of the segmentation errors showed no significant differences in algorithm performance between the different MR scanner manufacturers (P ≥ .05). CONCLUSIONS: The method proved to be robust, and no center-specific training of the algorithm was required, offering the possibility for application in a clinical setting. Adoption of the method should lead to improved reliability and less operator time required for image analysis in research and clinical trials in MS.

AB - BACKGROUND AND PURPOSE: The automatic segmentation of MS lesions could reduce time required for image processing together with inter-And intraoperator variability for research and clinical trials. A multicenter validation of a proposed semiautomatic method for hyperintense MS lesion segmentation on dual-echo MR imaging is presented. MATERIALS AND METHODS: The classification technique used is based on a region-growing approach starting from manual lesion identification by an expert observer with a final segmentation-refinement step. The method was validated in a cohort of 52 patients with relapsing-remitting MS, with dual-echo images acquired in 6 different European centers. RESULTS: We found a mathematic expression that made the optimization of the method independent of the need for a training dataset. The automatic segmentation was in good agreement with the manual segmentation (dice similarity coefficient = 0.62 and root mean square error = 2 mL). Assessment of the segmentation errors showed no significant differences in algorithm performance between the different MR scanner manufacturers (P ≥ .05). CONCLUSIONS: The method proved to be robust, and no center-specific training of the algorithm was required, offering the possibility for application in a clinical setting. Adoption of the method should lead to improved reliability and less operator time required for image analysis in research and clinical trials in MS.

UR - http://www.scopus.com/inward/record.url?scp=84995640083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995640083&partnerID=8YFLogxK

U2 - 10.3174/ajnr.A4874

DO - 10.3174/ajnr.A4874

M3 - Article

AN - SCOPUS:84995640083

VL - 37

SP - 2043

EP - 2049

JO - American Journal of Neuroradiology

JF - American Journal of Neuroradiology

SN - 0195-6108

IS - 11

ER -