Association between MRI structural features and cognitive measures in pediatric multiple sclerosis

N. Amoroso, R. Bellotti, A. Fanizzi, A. Lombardi, A. Monaco, M. Liguori, L. Margari, M. Simone, R. G. Viterbo, S. Tangaro

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Multiple sclerosis (MS) is an inflammatory and demyelinating disease associated with neurodegenerative processes that lead to brain structural changes. The disease affects mostly young adults, but 3-5% of cases has a pediatric onset (POMS). Magnetic Resonance Imaging (MRI) is generally used for diagnosis and follow-up in MS patients, however the most common MRI measures (e.g. new or enlarging T2-weighted lesions, T1-weighted gadolinium- enhancing lesions) have often failed as surrogate markers of MS disability and progression. MS is clinically heterogenous with symptoms that can include both physical changes (such as visual loss or walking difficulties) and cognitive impairment. 30-50% of POMS experience prominent cognitive dysfunction. In order to investigate the association between cognitive measures and brain morphometry, in this work we present a fully automated pipeline for processing and analyzing MRI brain scans. Relevant anatomical structures are segmented with FreeSurfer; besides, statistical features are computed. Thus, we describe the data referred to 12 patients with early POMS (mean age at MRI: 15.5 ± 2.7 years) with a set of 181 structural features. The major cognitive abilities measured are verbal and visuo-spatial learning, expressive language and complex attention. Data was collected at the Department of Basic Sciences, Neurosciences and Sense Organs, University of Bari, and exploring different abilities like the verbal and visuo-spatial learning, expressive language and complex attention. Different regression models and parameter configurations are explored to assess the robustness of the results, in particular Generalized Linear Models, Bayes Regression, Random Forests, Support Vector Regression and Artificial Neural Networks are discussed.

Original languageEnglish
Title of host publicationApplications of Digital Image Processing XL
PublisherSPIE
Volume10396
ISBN (Electronic)9781510612495
DOIs
Publication statusPublished - Jan 1 2017
EventApplications of Digital Image Processing XL 2017 - San Diego, United States
Duration: Aug 7 2017Aug 10 2017

Conference

ConferenceApplications of Digital Image Processing XL 2017
CountryUnited States
CitySan Diego
Period8/7/178/10/17

Fingerprint

Multiple Sclerosis
Pediatrics
Magnetic Resonance Imaging
magnetic resonance
brain
regression analysis
Brain
organs
lesions
learning
sense organs
Surrogate Markers
Morphometry
neurology
disabilities
walking
Neuroscience
Support Vector Regression
Random Forest
Gadolinium

Keywords

  • FreeSurfer
  • Machine learning
  • Multiple Sclerosis
  • structural MRI

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Amoroso, N., Bellotti, R., Fanizzi, A., Lombardi, A., Monaco, A., Liguori, M., ... Tangaro, S. (2017). Association between MRI structural features and cognitive measures in pediatric multiple sclerosis. In Applications of Digital Image Processing XL (Vol. 10396). [103961A] SPIE. https://doi.org/10.1117/12.2273834

Association between MRI structural features and cognitive measures in pediatric multiple sclerosis. / Amoroso, N.; Bellotti, R.; Fanizzi, A.; Lombardi, A.; Monaco, A.; Liguori, M.; Margari, L.; Simone, M.; Viterbo, R. G.; Tangaro, S.

Applications of Digital Image Processing XL. Vol. 10396 SPIE, 2017. 103961A.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Amoroso, N, Bellotti, R, Fanizzi, A, Lombardi, A, Monaco, A, Liguori, M, Margari, L, Simone, M, Viterbo, RG & Tangaro, S 2017, Association between MRI structural features and cognitive measures in pediatric multiple sclerosis. in Applications of Digital Image Processing XL. vol. 10396, 103961A, SPIE, Applications of Digital Image Processing XL 2017, San Diego, United States, 8/7/17. https://doi.org/10.1117/12.2273834
Amoroso N, Bellotti R, Fanizzi A, Lombardi A, Monaco A, Liguori M et al. Association between MRI structural features and cognitive measures in pediatric multiple sclerosis. In Applications of Digital Image Processing XL. Vol. 10396. SPIE. 2017. 103961A https://doi.org/10.1117/12.2273834
Amoroso, N. ; Bellotti, R. ; Fanizzi, A. ; Lombardi, A. ; Monaco, A. ; Liguori, M. ; Margari, L. ; Simone, M. ; Viterbo, R. G. ; Tangaro, S. / Association between MRI structural features and cognitive measures in pediatric multiple sclerosis. Applications of Digital Image Processing XL. Vol. 10396 SPIE, 2017.
@inproceedings{f72c5a77bca04d889680c2147b608fa0,
title = "Association between MRI structural features and cognitive measures in pediatric multiple sclerosis",
abstract = "Multiple sclerosis (MS) is an inflammatory and demyelinating disease associated with neurodegenerative processes that lead to brain structural changes. The disease affects mostly young adults, but 3-5{\%} of cases has a pediatric onset (POMS). Magnetic Resonance Imaging (MRI) is generally used for diagnosis and follow-up in MS patients, however the most common MRI measures (e.g. new or enlarging T2-weighted lesions, T1-weighted gadolinium- enhancing lesions) have often failed as surrogate markers of MS disability and progression. MS is clinically heterogenous with symptoms that can include both physical changes (such as visual loss or walking difficulties) and cognitive impairment. 30-50{\%} of POMS experience prominent cognitive dysfunction. In order to investigate the association between cognitive measures and brain morphometry, in this work we present a fully automated pipeline for processing and analyzing MRI brain scans. Relevant anatomical structures are segmented with FreeSurfer; besides, statistical features are computed. Thus, we describe the data referred to 12 patients with early POMS (mean age at MRI: 15.5 ± 2.7 years) with a set of 181 structural features. The major cognitive abilities measured are verbal and visuo-spatial learning, expressive language and complex attention. Data was collected at the Department of Basic Sciences, Neurosciences and Sense Organs, University of Bari, and exploring different abilities like the verbal and visuo-spatial learning, expressive language and complex attention. Different regression models and parameter configurations are explored to assess the robustness of the results, in particular Generalized Linear Models, Bayes Regression, Random Forests, Support Vector Regression and Artificial Neural Networks are discussed.",
keywords = "FreeSurfer, Machine learning, Multiple Sclerosis, structural MRI",
author = "N. Amoroso and R. Bellotti and A. Fanizzi and A. Lombardi and A. Monaco and M. Liguori and L. Margari and M. Simone and Viterbo, {R. G.} and S. Tangaro",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2273834",
language = "English",
volume = "10396",
booktitle = "Applications of Digital Image Processing XL",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Association between MRI structural features and cognitive measures in pediatric multiple sclerosis

AU - Amoroso, N.

AU - Bellotti, R.

AU - Fanizzi, A.

AU - Lombardi, A.

AU - Monaco, A.

AU - Liguori, M.

AU - Margari, L.

AU - Simone, M.

AU - Viterbo, R. G.

AU - Tangaro, S.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Multiple sclerosis (MS) is an inflammatory and demyelinating disease associated with neurodegenerative processes that lead to brain structural changes. The disease affects mostly young adults, but 3-5% of cases has a pediatric onset (POMS). Magnetic Resonance Imaging (MRI) is generally used for diagnosis and follow-up in MS patients, however the most common MRI measures (e.g. new or enlarging T2-weighted lesions, T1-weighted gadolinium- enhancing lesions) have often failed as surrogate markers of MS disability and progression. MS is clinically heterogenous with symptoms that can include both physical changes (such as visual loss or walking difficulties) and cognitive impairment. 30-50% of POMS experience prominent cognitive dysfunction. In order to investigate the association between cognitive measures and brain morphometry, in this work we present a fully automated pipeline for processing and analyzing MRI brain scans. Relevant anatomical structures are segmented with FreeSurfer; besides, statistical features are computed. Thus, we describe the data referred to 12 patients with early POMS (mean age at MRI: 15.5 ± 2.7 years) with a set of 181 structural features. The major cognitive abilities measured are verbal and visuo-spatial learning, expressive language and complex attention. Data was collected at the Department of Basic Sciences, Neurosciences and Sense Organs, University of Bari, and exploring different abilities like the verbal and visuo-spatial learning, expressive language and complex attention. Different regression models and parameter configurations are explored to assess the robustness of the results, in particular Generalized Linear Models, Bayes Regression, Random Forests, Support Vector Regression and Artificial Neural Networks are discussed.

AB - Multiple sclerosis (MS) is an inflammatory and demyelinating disease associated with neurodegenerative processes that lead to brain structural changes. The disease affects mostly young adults, but 3-5% of cases has a pediatric onset (POMS). Magnetic Resonance Imaging (MRI) is generally used for diagnosis and follow-up in MS patients, however the most common MRI measures (e.g. new or enlarging T2-weighted lesions, T1-weighted gadolinium- enhancing lesions) have often failed as surrogate markers of MS disability and progression. MS is clinically heterogenous with symptoms that can include both physical changes (such as visual loss or walking difficulties) and cognitive impairment. 30-50% of POMS experience prominent cognitive dysfunction. In order to investigate the association between cognitive measures and brain morphometry, in this work we present a fully automated pipeline for processing and analyzing MRI brain scans. Relevant anatomical structures are segmented with FreeSurfer; besides, statistical features are computed. Thus, we describe the data referred to 12 patients with early POMS (mean age at MRI: 15.5 ± 2.7 years) with a set of 181 structural features. The major cognitive abilities measured are verbal and visuo-spatial learning, expressive language and complex attention. Data was collected at the Department of Basic Sciences, Neurosciences and Sense Organs, University of Bari, and exploring different abilities like the verbal and visuo-spatial learning, expressive language and complex attention. Different regression models and parameter configurations are explored to assess the robustness of the results, in particular Generalized Linear Models, Bayes Regression, Random Forests, Support Vector Regression and Artificial Neural Networks are discussed.

KW - FreeSurfer

KW - Machine learning

KW - Multiple Sclerosis

KW - structural MRI

UR - http://www.scopus.com/inward/record.url?scp=85034758388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034758388&partnerID=8YFLogxK

U2 - 10.1117/12.2273834

DO - 10.1117/12.2273834

M3 - Conference contribution

AN - SCOPUS:85034758388

VL - 10396

BT - Applications of Digital Image Processing XL

PB - SPIE

ER -