Assessing the role of volumetric brain information in multiple sclerosis progression

Multiple sclerosis is a chronic autoimmune disease that affects the central nervous system. Understanding multiple sclerosis progression and identifying the implicated brain structures is crucial for personalized treatment decisions. Deformation-based morphometry utilizes anatomical magnetic resonan...

Full description

Saved in:
Bibliographic Details
Main Authors: Andy A. Shen, Aidan McLoughlin, Zoe Vernon, Jonathan Lin, Richard A.D. Carano, Peter J. Bickel, Zhuang Song, Haiyan Huang
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Computational and Structural Biotechnology Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2001037025001667
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151632358080512
author Andy A. Shen
Aidan McLoughlin
Zoe Vernon
Jonathan Lin
Richard A.D. Carano
Peter J. Bickel
Zhuang Song
Haiyan Huang
author_facet Andy A. Shen
Aidan McLoughlin
Zoe Vernon
Jonathan Lin
Richard A.D. Carano
Peter J. Bickel
Zhuang Song
Haiyan Huang
author_sort Andy A. Shen
collection DOAJ
description Multiple sclerosis is a chronic autoimmune disease that affects the central nervous system. Understanding multiple sclerosis progression and identifying the implicated brain structures is crucial for personalized treatment decisions. Deformation-based morphometry utilizes anatomical magnetic resonance imaging to quantitatively assess volumetric brain changes at the voxel level, providing insight into how each brain region contributes to clinical progression with regards to neurodegeneration. Utilizing such voxel-level data from a relapsing multiple sclerosis clinical trial, we extend a model-agnostic feature importance metric to identify a robust and predictive feature set that corresponds to clinical progression. These features correspond to brain regions that are clinically meaningful in MS disease research, demonstrating their scientific relevance. When used to predict progression using classical survival models and 3D convolutional neural networks, the identified regions led to the best-performing models, demonstrating their prognostic strength. We also find that these features generalize well to other definitions of clinical progression and can compensate for the omission of highly prognostic clinical features, underscoring the predictive power and clinical relevance of deformation-based morphometry as a regional identification tool.
format Article
id doaj-art-4f3b0f1e5b10463eaea7ecf594149b2a
institution OA Journals
issn 2001-0370
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Computational and Structural Biotechnology Journal
spelling doaj-art-4f3b0f1e5b10463eaea7ecf594149b2a2025-08-20T02:26:10ZengElsevierComputational and Structural Biotechnology Journal2001-03702025-01-01272014203310.1016/j.csbj.2025.05.003Assessing the role of volumetric brain information in multiple sclerosis progressionAndy A. Shen0Aidan McLoughlin1Zoe Vernon2Jonathan Lin3Richard A.D. Carano4Peter J. Bickel5Zhuang Song6Haiyan Huang7Department of Statistics, UC Berkeley, Berkeley, CA, USADivision of Biostatistics, UC Berkeley, Berkeley, CA, USADepartment of Statistics, UC Berkeley, Berkeley, CA, USADepartment of Statistical Science, Duke University, Durham, NC, USAAnalytics and Medical Imaging, Product Development, Genentech Inc., South San Francisco, CA, USADepartment of Statistics, UC Berkeley, Berkeley, CA, USA; Division of Biostatistics, UC Berkeley, Berkeley, CA, USAAnalytics and Medical Imaging, Product Development, Genentech Inc., South San Francisco, CA, USA; Z. Song and H. Huang are co-last, co-corresponding authors.Department of Statistics, UC Berkeley, Berkeley, CA, USA; Division of Biostatistics, UC Berkeley, Berkeley, CA, USA; Z. Song and H. Huang are co-last, co-corresponding authors.; Corresponding author at: 367 Evans Hall, Berkeley, CA 94720, USA.Multiple sclerosis is a chronic autoimmune disease that affects the central nervous system. Understanding multiple sclerosis progression and identifying the implicated brain structures is crucial for personalized treatment decisions. Deformation-based morphometry utilizes anatomical magnetic resonance imaging to quantitatively assess volumetric brain changes at the voxel level, providing insight into how each brain region contributes to clinical progression with regards to neurodegeneration. Utilizing such voxel-level data from a relapsing multiple sclerosis clinical trial, we extend a model-agnostic feature importance metric to identify a robust and predictive feature set that corresponds to clinical progression. These features correspond to brain regions that are clinically meaningful in MS disease research, demonstrating their scientific relevance. When used to predict progression using classical survival models and 3D convolutional neural networks, the identified regions led to the best-performing models, demonstrating their prognostic strength. We also find that these features generalize well to other definitions of clinical progression and can compensate for the omission of highly prognostic clinical features, underscoring the predictive power and clinical relevance of deformation-based morphometry as a regional identification tool.http://www.sciencedirect.com/science/article/pii/S2001037025001667Multiple sclerosisDeformation-based morphometrySurvival analysisFeature selectionRandom forestConvolutional neural network
spellingShingle Andy A. Shen
Aidan McLoughlin
Zoe Vernon
Jonathan Lin
Richard A.D. Carano
Peter J. Bickel
Zhuang Song
Haiyan Huang
Assessing the role of volumetric brain information in multiple sclerosis progression
Computational and Structural Biotechnology Journal
Multiple sclerosis
Deformation-based morphometry
Survival analysis
Feature selection
Random forest
Convolutional neural network
title Assessing the role of volumetric brain information in multiple sclerosis progression
title_full Assessing the role of volumetric brain information in multiple sclerosis progression
title_fullStr Assessing the role of volumetric brain information in multiple sclerosis progression
title_full_unstemmed Assessing the role of volumetric brain information in multiple sclerosis progression
title_short Assessing the role of volumetric brain information in multiple sclerosis progression
title_sort assessing the role of volumetric brain information in multiple sclerosis progression
topic Multiple sclerosis
Deformation-based morphometry
Survival analysis
Feature selection
Random forest
Convolutional neural network
url http://www.sciencedirect.com/science/article/pii/S2001037025001667
work_keys_str_mv AT andyashen assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT aidanmcloughlin assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT zoevernon assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT jonathanlin assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT richardadcarano assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT peterjbickel assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT zhuangsong assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression
AT haiyanhuang assessingtheroleofvolumetricbraininformationinmultiplesclerosisprogression