Article (Scientific journals)
Exploratory radiomic analysis of conventional versus quantitative brain MRI: Towards automatic diagnosis of early multiple sclerosis
Lavrova, Elizaveta; LOMMERS, Emilie; WOODRUFF, Henry et al.
2021In Frontiers in Neuroscience
Peer Reviewed verified by ORBi
 

Files


Full Text
679941_Manuscript.PDF
Author preprint (2.05 MB)
Download
Annexes
MRI Radiomics in Multiple Sclerosis_Supplementary.docx
(2.51 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
multiple sclerosis; brain MRI; radiomic feature; quantitative MRI; histological MRI
Abstract :
[en] Conventional magnetic resonance imaging (cMRI) is poorly sensitive to pathological changes related to multiple sclerosis (MS) in normal-appearing white matter (NAWM) and grey matter (GM), with the added difficulty of not being very reproducible. Quantitative MRI (qMRI) on the other hand attempts to represent physical properties of tissues, making it an ideal candidate for quantitative medical image analysis, or radiomics. We therefore hypothesized that qMRI-based radiomic features have added diagnostic value in MS compared to cMRI. This study investigated the ability of cMRI (T1w) and qMRI features extracted from WM, NAWM, and GM to distinguish between MS patients (MSP) and healthy control subjects (HCS). We developed exploratory radiomic classification models on a dataset comprising 36 MSP and 36 HCS recruited in CHU Liege, Belgium, acquired with cMRI and qMRI. For each image type and region of interest, qMRI radiomic models for MS diagnosis were developed on a training subset and validated on a testing subset. Radiomic models based on cMRI were developed on the entire training dataset and externally validated on open-source datasets with 167 HCS and 10 MSP. Ranked by region of interest, the best diagnostic performance was achieved in the whole WM. Here the model based on magnetization transfer imaging (a type of qMRI) features yielded a median area under the receiver operating characteristic curve (AUC) of 1.00 in the testing sub-cohort. Ranked by image type, the best performance was achieved by the magnetization transfer models, with median AUCs of 0.79 (0.69-0.90 90% CI) in NAWM and 0.81 (0.71-0.90) in GM. External validation of the T1w models yielded an AUC of 0.78 (0.47-1.00) in whole WM, demonstrating a large 95% CI and low sensitivity of 0.30 (0.10-0.70). This exploratory study indicates that qMRI Radiomics could provide efficient diagnostic information using NAWM and GM analysis in MSP. T1w radiomics could be useful for a fast and automated check of conventional MRI for WM abnormalities once acquisition and reconstruction heterogeneities have been overcome. Further prospective validation is needed involving more data for better interpretation and generalization of the results.
Research center :
GIGA CRC (Cyclotron Research Center) In vivo Imaging-Aging & Memory - ULiège
Maastricht University, Precision Medicine department
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Lavrova, Elizaveta   ;  Université de Liège - ULiège > GIGA CRC In vivo Imaging - Aging & Memory
LOMMERS, Emilie   ;  Centre Hospitalier Universitaire de Liège - CHU > Département de médecine interne > Service de neurologie
WOODRUFF, Henry ;  Universiteit Maastricht > Precision Medicine
MAQUET, Pierre  ;  Centre Hospitalier Universitaire de Liège - CHU > Département de médecine interne > Service de neurologie
Salmon, Eric   ;  Université de Liège - ULiège > Département des sciences cliniques > Neuroimagerie des troubles de la mémoire et revalid. cogn.
LAMBIN, Philippe 
Phillips, Christophe   ;  Université de Liège - ULiège > GIGA CRC In vivo Im. - Neuroimaging, data acquisi. & proces.
 These authors have contributed equally to this work.
Language :
English
Title :
Exploratory radiomic analysis of conventional versus quantitative brain MRI: Towards automatic diagnosis of early multiple sclerosis
Publication date :
14 June 2021
Journal title :
Frontiers in Neuroscience
ISSN :
1662-4548
eISSN :
1662-453X
Publisher :
Frontiers Media S.A., Switzerland
Peer reviewed :
Peer Reviewed verified by ORBi
European Projects :
H2020 - 766276 - PREDICT - A new era in personalised medicine: Radiomics as decision support tool for diagnostics and theragnostics in oncology
Name of the research project :
Quantitative Neuro-Imaging with Radiomics and Deep Learning in two main neurological diseases: Multiple Sclerosis and Stroke
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Maastricht Imaging Valley [NL]
CE - Commission Européenne [BE]
Available on ORBi :
since 18 July 2021

Statistics


Number of views
185 (17 by ULiège)
Number of downloads
149 (7 by ULiège)

Scopus citations®
 
7
Scopus citations®
without self-citations
6
OpenCitations
 
1

Bibliography


Similar publications



Contact ORBi