Multiple sclerosis: Identification of temporal changes in brain lesions with computer-assisted detection software

M. Bilello, Michal Arkuszewski, P. Nucifora, I. Nasrallah, E. R. Melhem, L. Cirillo, J. Krejza

Research output: Contribution to journalArticle

Abstract

Multiple sclerosis (MS) is a chronic disease with a progressing and evolving course. Serial imaging with MRI is the mainstay in monitoring and managing MS patients. In this work we demonstrate the performance of a locally developed computer-assisted detection (CAD) software used to track temporal changes in brain MS lesions. CAD tracks changes in T2-bright MS lesions between two time points on a 3D high-resolution isotropic FLAIR MR sequence of the brain acquired at 3 Tesla. The program consists of an image-processing pipeline, and displays scrollable difference maps used as an aid to the neuroradiologist for assessing lesional change. To assess the value of the software we have compared diagnostic accuracy and duration of interpretation of the CAD-assisted and routine clinical interpretations in 98 randomly chosen, paired MR examinations from 88 patients (68 women, 20 men, mean age 43.5, age range 21-75) with a diagnosis of definite MS. The ground truth was determined by a three-expert panel. In case-wise analysis, CAD interpretation showed higher sensitivity than a clinical report (87% vs 77%, respectively). Lesion-wise analysis demonstrated improved sensitivity of CAD over a routine clinical interpretation of 40%-48%. Mean software-assisted interpretation time was 2.7 min. Our study demonstrates the potential of including CAD software in the workflow of neuroradiology practice for the detection of MS lesional change. Automated quantification of temporal change in MS lesion load may also be used in clinical research, e.g., in drug trials.

Original languageEnglish
Pages (from-to)143-150
Number of pages8
JournalNeuroradiology Journal
Volume26
Issue number2
Publication statusPublished - Apr 2013

Fingerprint

Multiple Sclerosis
Software
Brain
Workflow
Chronic Disease
Research
Pharmaceutical Preparations

Keywords

  • Brain lesions
  • Computer assessment
  • Imaging
  • Magnetic resonance
  • Multiple sclerosis

ASJC Scopus subject areas

  • Clinical Neurology
  • Radiology Nuclear Medicine and imaging

Cite this

Bilello, M., Arkuszewski, M., Nucifora, P., Nasrallah, I., Melhem, E. R., Cirillo, L., & Krejza, J. (2013). Multiple sclerosis: Identification of temporal changes in brain lesions with computer-assisted detection software. Neuroradiology Journal, 26(2), 143-150.

Multiple sclerosis : Identification of temporal changes in brain lesions with computer-assisted detection software. / Bilello, M.; Arkuszewski, Michal; Nucifora, P.; Nasrallah, I.; Melhem, E. R.; Cirillo, L.; Krejza, J.

In: Neuroradiology Journal, Vol. 26, No. 2, 04.2013, p. 143-150.

Research output: Contribution to journalArticle

Bilello, M, Arkuszewski, M, Nucifora, P, Nasrallah, I, Melhem, ER, Cirillo, L & Krejza, J 2013, 'Multiple sclerosis: Identification of temporal changes in brain lesions with computer-assisted detection software', Neuroradiology Journal, vol. 26, no. 2, pp. 143-150.
Bilello, M. ; Arkuszewski, Michal ; Nucifora, P. ; Nasrallah, I. ; Melhem, E. R. ; Cirillo, L. ; Krejza, J. / Multiple sclerosis : Identification of temporal changes in brain lesions with computer-assisted detection software. In: Neuroradiology Journal. 2013 ; Vol. 26, No. 2. pp. 143-150.
@article{7cda694a82d6431492954ffcf60bd1e9,
title = "Multiple sclerosis: Identification of temporal changes in brain lesions with computer-assisted detection software",
abstract = "Multiple sclerosis (MS) is a chronic disease with a progressing and evolving course. Serial imaging with MRI is the mainstay in monitoring and managing MS patients. In this work we demonstrate the performance of a locally developed computer-assisted detection (CAD) software used to track temporal changes in brain MS lesions. CAD tracks changes in T2-bright MS lesions between two time points on a 3D high-resolution isotropic FLAIR MR sequence of the brain acquired at 3 Tesla. The program consists of an image-processing pipeline, and displays scrollable difference maps used as an aid to the neuroradiologist for assessing lesional change. To assess the value of the software we have compared diagnostic accuracy and duration of interpretation of the CAD-assisted and routine clinical interpretations in 98 randomly chosen, paired MR examinations from 88 patients (68 women, 20 men, mean age 43.5, age range 21-75) with a diagnosis of definite MS. The ground truth was determined by a three-expert panel. In case-wise analysis, CAD interpretation showed higher sensitivity than a clinical report (87{\%} vs 77{\%}, respectively). Lesion-wise analysis demonstrated improved sensitivity of CAD over a routine clinical interpretation of 40{\%}-48{\%}. Mean software-assisted interpretation time was 2.7 min. Our study demonstrates the potential of including CAD software in the workflow of neuroradiology practice for the detection of MS lesional change. Automated quantification of temporal change in MS lesion load may also be used in clinical research, e.g., in drug trials.",
keywords = "Brain lesions, Computer assessment, Imaging, Magnetic resonance, Multiple sclerosis",
author = "M. Bilello and Michal Arkuszewski and P. Nucifora and I. Nasrallah and Melhem, {E. R.} and L. Cirillo and J. Krejza",
year = "2013",
month = "4",
language = "English",
volume = "26",
pages = "143--150",
journal = "Neuroradiology Journal",
issn = "1971-4009",
publisher = "Centauro srl",
number = "2",

}

TY - JOUR

T1 - Multiple sclerosis

T2 - Identification of temporal changes in brain lesions with computer-assisted detection software

AU - Bilello, M.

AU - Arkuszewski, Michal

AU - Nucifora, P.

AU - Nasrallah, I.

AU - Melhem, E. R.

AU - Cirillo, L.

AU - Krejza, J.

PY - 2013/4

Y1 - 2013/4

N2 - Multiple sclerosis (MS) is a chronic disease with a progressing and evolving course. Serial imaging with MRI is the mainstay in monitoring and managing MS patients. In this work we demonstrate the performance of a locally developed computer-assisted detection (CAD) software used to track temporal changes in brain MS lesions. CAD tracks changes in T2-bright MS lesions between two time points on a 3D high-resolution isotropic FLAIR MR sequence of the brain acquired at 3 Tesla. The program consists of an image-processing pipeline, and displays scrollable difference maps used as an aid to the neuroradiologist for assessing lesional change. To assess the value of the software we have compared diagnostic accuracy and duration of interpretation of the CAD-assisted and routine clinical interpretations in 98 randomly chosen, paired MR examinations from 88 patients (68 women, 20 men, mean age 43.5, age range 21-75) with a diagnosis of definite MS. The ground truth was determined by a three-expert panel. In case-wise analysis, CAD interpretation showed higher sensitivity than a clinical report (87% vs 77%, respectively). Lesion-wise analysis demonstrated improved sensitivity of CAD over a routine clinical interpretation of 40%-48%. Mean software-assisted interpretation time was 2.7 min. Our study demonstrates the potential of including CAD software in the workflow of neuroradiology practice for the detection of MS lesional change. Automated quantification of temporal change in MS lesion load may also be used in clinical research, e.g., in drug trials.

AB - Multiple sclerosis (MS) is a chronic disease with a progressing and evolving course. Serial imaging with MRI is the mainstay in monitoring and managing MS patients. In this work we demonstrate the performance of a locally developed computer-assisted detection (CAD) software used to track temporal changes in brain MS lesions. CAD tracks changes in T2-bright MS lesions between two time points on a 3D high-resolution isotropic FLAIR MR sequence of the brain acquired at 3 Tesla. The program consists of an image-processing pipeline, and displays scrollable difference maps used as an aid to the neuroradiologist for assessing lesional change. To assess the value of the software we have compared diagnostic accuracy and duration of interpretation of the CAD-assisted and routine clinical interpretations in 98 randomly chosen, paired MR examinations from 88 patients (68 women, 20 men, mean age 43.5, age range 21-75) with a diagnosis of definite MS. The ground truth was determined by a three-expert panel. In case-wise analysis, CAD interpretation showed higher sensitivity than a clinical report (87% vs 77%, respectively). Lesion-wise analysis demonstrated improved sensitivity of CAD over a routine clinical interpretation of 40%-48%. Mean software-assisted interpretation time was 2.7 min. Our study demonstrates the potential of including CAD software in the workflow of neuroradiology practice for the detection of MS lesional change. Automated quantification of temporal change in MS lesion load may also be used in clinical research, e.g., in drug trials.

KW - Brain lesions

KW - Computer assessment

KW - Imaging

KW - Magnetic resonance

KW - Multiple sclerosis

UR - http://www.scopus.com/inward/record.url?scp=84879024549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879024549&partnerID=8YFLogxK

M3 - Article

C2 - 23859235

AN - SCOPUS:84879024549

VL - 26

SP - 143

EP - 150

JO - Neuroradiology Journal

JF - Neuroradiology Journal

SN - 1971-4009

IS - 2

ER -