1
|
Kelly E, Varosanec M, Kosa P, Prchkovska V, Moreno-Dominguez D, Bielekova B. Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients. FRONTIERS IN RADIOLOGY 2022; 2:1026442. [PMID: 37492667 PMCID: PMC10365117 DOI: 10.3389/fradi.2022.1026442] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 10/24/2022] [Indexed: 07/27/2023]
Abstract
Composite MRI scales of central nervous system tissue destruction correlate stronger with clinical outcomes than their individual components in multiple sclerosis (MS) patients. Using machine learning (ML), we previously developed Combinatorial MRI scale (COMRISv1) solely from semi-quantitative (semi-qMRI) biomarkers. Here, we asked how much better COMRISv2 might become with the inclusion of quantitative (qMRI) volumetric features and employment of more powerful ML algorithm. The prospectively acquired MS patients, divided into training (n = 172) and validation (n = 83) cohorts underwent brain MRI imaging and clinical evaluation. Neurological examination was transcribed to NeurEx™ App that automatically computes disability scales. qMRI features were computed by lesion-TOADS algorithm. Modified random forest pipeline selected biomarkers for optimal model(s) in the training cohort. COMRISv2 models validated moderate correlation with cognitive disability [Spearman Rho = 0.674; Lin's concordance coefficient (CCC) = 0.458; p < 0.001] and strong correlations with physical disability (Spearman Rho = 0.830-0.852; CCC = 0.789-0.823; p < 0.001). The NeurEx led to the strongest COMRISv2 model. Addition of qMRI features enhanced performance only of cognitive disability model, likely because semi-qMRI biomarkers measure infratentorial injury with greater accuracy. COMRISv2 models predict most granular clinical scales in MS with remarkable criterion validity, expanding scientific utilization of cohorts with missing clinical data.
Collapse
Affiliation(s)
- Erin Kelly
- Neuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United States
| | - Mihael Varosanec
- Neuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United States
| | - Peter Kosa
- Neuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United States
| | | | | | - Bibiana Bielekova
- Neuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United States
| |
Collapse
|
2
|
Hannoun S, Kocevar G, Codjia P, Barile B, Cotton F, Durand-Dubief F, Sappey-Marinier D. T1/T2 ratio: A quantitative sensitive marker of brain tissue integrity in multiple sclerosis. J Neuroimaging 2021; 32:328-336. [PMID: 34752685 DOI: 10.1111/jon.12943] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2021] [Revised: 09/30/2021] [Accepted: 10/14/2021] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND AND PURPOSE The aim of this study is to determine whether cerebral white matter (WM) microstructural damage, defined by decreased fractional anisotropy (FA) and increased axial (AD) and radial (RD) diffusivities, could be detected as accurately by measuring the T1/T2 ratio, in relapsing-remitting multiple sclerosis (RRMS) patients compared to healthy control (HC) subjects. METHODS Twenty-eight RRMS patients and 24 HC subjects were included in this study. Region-based analysis based on the ICBM-81 diffusion tensor imaging (DTI) atlas WM labels was performed to compare T1/T2 ratio to DTI values in normal-appearing WM (NAWM) regions of interest. Lesions segmentation was also performed and compared to the HC global WM. RESULTS A significant 19.65% decrease of T1/T2 ratio values was observed in NAWM regions of RRMS patients compared to HC. A significant 6.30% decrease of FA, as well as significant 4.76% and 10.27% increases of AD and RD, respectively, were observed in RRMS compared to the HC group in various NAWM regions. Compared to the global WM HC mask, lesions have significantly decreased T1/T2 ratio and FA and increased AD and RD (p < . 001). CONCLUSIONS Results showed significant differences between RRMS and HC in both DTI and T1/T2 ratio measurements. T1/T2 ratio even demonstrated extensive WM abnormalities when compared to DTI, thereby highlighting the ratio's sensitivity to subtle differences in cerebral WM structural integrity using only conventional MRI sequences.
Collapse
Affiliation(s)
- Salem Hannoun
- Medical Imaging Sciences Program, Division of Health Professions, Faculty of Health Sciences, American University of Beirut, Beirut, Lebanon
| | - Gabriel Kocevar
- CREATIS, UMR 5220 CNRS & U1294 INSERM, Université Claude Bernard - Lyon1, Université de Lyon, Villeurbanne, France.,Seenovate, Datascience pole, Lyon, France
| | - Pekes Codjia
- CREATIS, UMR 5220 CNRS & U1294 INSERM, Université Claude Bernard - Lyon1, Université de Lyon, Villeurbanne, France.,Service de Radiologie, Centre Hospitalier Lyon-Sud, Hospices Civils de Lyon, Pierre Bénite, France
| | - Berardino Barile
- CREATIS, UMR 5220 CNRS & U1294 INSERM, Université Claude Bernard - Lyon1, Université de Lyon, Villeurbanne, France
| | - Francois Cotton
- CREATIS, UMR 5220 CNRS & U1294 INSERM, Université Claude Bernard - Lyon1, Université de Lyon, Villeurbanne, France.,Service de Radiologie, Centre Hospitalier Lyon-Sud, Hospices Civils de Lyon, Pierre Bénite, France
| | - Francoise Durand-Dubief
- CREATIS, UMR 5220 CNRS & U1294 INSERM, Université Claude Bernard - Lyon1, Université de Lyon, Villeurbanne, France.,Service de Neurologie A, Hôpital Neurologique Pierre Wertheimer, Groupement Hospitalier Est, Hospices Civils de Lyon, Bron, France
| | - Dominique Sappey-Marinier
- CREATIS, UMR 5220 CNRS & U1294 INSERM, Université Claude Bernard - Lyon1, Université de Lyon, Villeurbanne, France.,Département IRM, CERMEP-Imagerie du Vivant, Université de Lyon, Bron, France
| |
Collapse
|
3
|
Madsen MAJ, Wiggermann V, Bramow S, Christensen JR, Sellebjerg F, Siebner HR. Imaging cortical multiple sclerosis lesions with ultra-high field MRI. NEUROIMAGE-CLINICAL 2021; 32:102847. [PMID: 34653837 PMCID: PMC8517925 DOI: 10.1016/j.nicl.2021.102847] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/25/2021] [Revised: 08/19/2021] [Accepted: 08/25/2021] [Indexed: 11/29/2022]
Abstract
BACKGROUND Cortical lesions are abundant in multiple sclerosis (MS), yet difficult to visualize in vivo. Ultra-high field (UHF) MRI at 7 T and above provides technological advances suited to optimize the detection of cortical lesions in MS. PURPOSE To provide a narrative and quantitative systematic review of the literature on UHF MRI of cortical lesions in MS. METHODS A systematic search of all literature on UHF MRI of cortical lesions in MS published before September 2020. Quantitative outcome measures included cortical lesion numbers reported using 3 T and 7 T MRI and between 7 T MRI sequences, along with sensitivity of UHF MRI towards cortical lesions verified by histopathology. RESULTS 7 T MRI detected on average 52 ± 26% (mean ± 95% confidence interval) more cortical lesions than the best performing image contrast at 3 T, with the largest increase in type II-IV intracortical lesion detection. Across all studies, the mean cortical lesion number was 17 ± 6 per patient. In progressive MS cohorts, approximately four times more cortical lesions were reported than in CIS/early RRMS, and RRMS. Yet, there was no difference in lesion type ratio between these MS subtypes. Furthermore, superiority of one MRI sequence over another could not be established from available data. Post-mortem lesion detection with UHF MRI agreed only modestly with pathological examinations. Mean pro- and retrospective sensitivity was 33 ± 6% and 71 ± 10%, respectively, with the highest sensitivity towards type I and type IV lesions. CONCLUSION UHF MRI improves cortical lesion detection in MS considerably compared to 3 T MRI, particularly for type II-IV lesions. Despite modest sensitivity, 7 T MRI is still capable of visualizing all aspects of cortical lesion pathology and could potentially aid clinicians in diagnosing and monitoring MS, and progressive MS in particular. However, standardization of acquisition and segmentation protocols is needed.
Collapse
Affiliation(s)
- Mads A J Madsen
- Danish Research Centre for Magnetic Resonance, Copenhagen University Hospital - Amager & Hvidovre, Kettegard Allé 30, 2650 Hvidovre, Denmark.
| | - Vanessa Wiggermann
- Danish Research Centre for Magnetic Resonance, Copenhagen University Hospital - Amager & Hvidovre, Kettegard Allé 30, 2650 Hvidovre, Denmark
| | - Stephan Bramow
- Danish Multiple Sclerosis Center, Department of Neurology, Copenhagen University Hospital - Rigshospitalet, Valdemar Hansens Vej 1-23, 2600 Glostrup, Denmark
| | - Jeppe Romme Christensen
- Danish Multiple Sclerosis Center, Department of Neurology, Copenhagen University Hospital - Rigshospitalet, Valdemar Hansens Vej 1-23, 2600 Glostrup, Denmark
| | - Finn Sellebjerg
- Danish Multiple Sclerosis Center, Department of Neurology, Copenhagen University Hospital - Rigshospitalet, Valdemar Hansens Vej 1-23, 2600 Glostrup, Denmark; Department of Clinical Medicine, University of Copenhagen, Blegdamsvej 3b, 2200 Copenhagen, Denmark
| | - Hartwig R Siebner
- Danish Research Centre for Magnetic Resonance, Copenhagen University Hospital - Amager & Hvidovre, Kettegard Allé 30, 2650 Hvidovre, Denmark; Department of Neurology, Copenhagen University Hospital - Bispebjerg, Bispebjerg Bakke 23, 2400 Copenhagen, Denmark; Department of Clinical Medicine, University of Copenhagen, Blegdamsvej 3b, 2200 Copenhagen, Denmark
| |
Collapse
|
4
|
Song X, Li D, Qiu Z, Su S, Wu Y, Wang J, Liu Z, Dong H. Correlation between EDSS scores and cervical spinal cord atrophy at 3T MRI in multiple sclerosis: A systematic review and meta-analysis. Mult Scler Relat Disord 2019; 37:101426. [PMID: 32172997 DOI: 10.1016/j.msard.2019.101426] [Citation(s) in RCA: 22] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2019] [Revised: 08/28/2019] [Accepted: 09/30/2019] [Indexed: 12/14/2022]
Abstract
BACKGROUND Cervical spinal cord atrophy (CSCA), which partly reflects the axonal loss in the spinal cord, is increasingly recognized as a valuable predictor of disease outcome. However, inconsistent results have been reported regarding the correlation of CSCA and clinical disability in multiple sclerosis (MS). The aim of this meta-analysis was to synthesize the available data obtained from 3.0-Tesla (3T) MRI scanners and to explore the relationship between CSCA and scores on the Expanded Disability Status Scale (EDSS). METHODS We searched PubMed, Embase, and Web of Science for articles published from the database inception to February 1, 2019. The quality of the articles was assessed according to a quality evaluation checklist which was created based on the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) guidelines. We conducted a meta-analysis of the correlation between EDSS scores and CSCA at 3T MRI in MS. RESULTS Twenty-two eligible studies involving 1933 participants were incorporated into our meta-analysis. Our results demonstrated that CSCA was negatively and moderately correlated with EDSS scores (rs = -0.42, 95% CI: -0.51 to -0.32; p < 0.0001). Subgroup analyses revealed a weaker correlation in the group of relapsing-remitting multiple sclerosis (RRMS) and clinically isolated syndrome (CIS) (rs = -0.19, 95% CI: -0.31 to -0.07; p = 0.0029). CONCLUSIONS The correlation between CSCA and EDSS scores was significant but moderate. We encourage more studies using reliable and consistent methods to explore whether CSCA is suitable as a predictor for MS progression.
Collapse
Affiliation(s)
- Xiaodong Song
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China
| | - Dawei Li
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China
| | - Zhandong Qiu
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China
| | - Shengyao Su
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China
| | - Yan Wu
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China
| | - Jingsi Wang
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China
| | - Zheng Liu
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China.
| | - Huiqing Dong
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing 100053, PR China.
| |
Collapse
|
5
|
Casserly C, Seyman EE, Alcaide-Leon P, Guenette M, Lyons C, Sankar S, Svendrovski A, Baral S, Oh J. Spinal Cord Atrophy in Multiple Sclerosis: A Systematic Review and Meta-Analysis. J Neuroimaging 2018; 28:556-586. [PMID: 30102003 DOI: 10.1111/jon.12553] [Citation(s) in RCA: 65] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2018] [Revised: 07/12/2018] [Accepted: 07/16/2018] [Indexed: 01/18/2023] Open
Abstract
BACKGROUND AND PURPOSE Spinal cord atrophy (SCA) is an important emerging outcome measure in multiple sclerosis (MS); however, there is limited consensus on the magnitude and rate of atrophy. The objective of this study was to synthesize the available data on measures of SCA in MS. METHODS Using published guidelines, relevant literature databases were searched between 1977 and 2017 for case-control or cohort studies reporting a quantitative measure of SCA in MS patients. Random-effects models pooled cross-sectional measures and longitudinal rates of SCA in MS and healthy controls (HCs). Student's t-test assessed differences between pooled measures in patient subgroups. Heterogeneity was assessed using DerSimonian and Laird's Q-test and the I 2 -index. RESULTS A total of 1,465 studies were retrieved including 94 that met inclusion and exclusion criteria. Pooled estimates of mean cervical spinal cord (SC) cross-sectional area (CSA) in all MS patients, relapsing-remitting MS (RRMS), all progressive MS, secondary progressive MS (SPMS), primary-progressive MS (PPMS), and HC were: 73.07 mm2 (95% CI [71.52-74.62]), 78.88 mm2 (95% CI [76.92-80.85]), 69.72 mm2 (95% CI [67.96-71.48]), 68.55 mm2 (95% CI [65.43-71.66]), 70.98 mm2 (95% CI [68.78-73.19]), and 80.87 mm2 (95% C I [78.70-83.04]), respectively. Pooled SC-CSA was greater in HC versus MS (P < .001) and RRMS versus progressive MS (P < .001). SCA showed moderate correlations with global disability in cross-sectional studies (r-value with disability score range [-.75 to -.22]). In longitudinal studies, the pooled annual rate of SCA was 1.78%/year (95%CI [1.28-2.27]). CONCLUSIONS The SC is atrophied in MS. The magnitude of SCA is greater in progressive versus relapsing forms and correlates with clinical disability. The pooled estimate of annual rate of SCA is greater than reported rates of brain atrophy in MS. These results demonstrate that SCA is highly relevant as an imaging outcome in MS clinical trials.
Collapse
Affiliation(s)
- Courtney Casserly
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada.,Department of Neurology, London Health Sciences Centre, Western University, London, Ontario, Canada
| | - Estelle E Seyman
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Paula Alcaide-Leon
- Division of Neuroradiology, Department of Medical Imaging, St. Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Melanie Guenette
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Carrie Lyons
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Stephanie Sankar
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Anton Svendrovski
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada
| | - Stefan Baral
- Department of Epidemiology, Johns Hopkins School of Public Health, Baltimore, MD
| | - Jiwon Oh
- Division of Neurology, Department of Medicine, St Michael's Hospital, University of Toronto, Toronto, Ontario, Canada.,Department of Neurology, Johns Hopkins University, Baltimore, MD
| |
Collapse
|
6
|
Abstract
Since its technical development in the early 1980s, magnetic resonance imaging (MRI) has quickly been adopted as an essential tool in supporting the diagnosis, longitudinal monitoring, evaluation of therapeutic response, and scientific investigations in multiple sclerosis (MS). The clinical usage of MRI has increased in parallel with technical innovations in the technique itself; the widespread adoption of clinically routine MRI at 1.5T has allowed sensitive qualitative and quantitative assessments of macroscopic central nervous system (CNS) inflammatory demyelinating lesions and tissue atrophy. However, conventional MRI lesion measures lack specificity for the underlying MS pathology and only weakly correlate with clinical status. Higher field strength units and newer, advanced MRI techniques offer increased sensitivity and specificity in the detection of disease activity and disease severity. This review summarizes the current status and future prospects regarding the role of MRI in the characterization of MS-related brain and spinal cord involvement.
Collapse
Affiliation(s)
- Christopher C Hemond
- Laboratory for Neuroimaging Research, Partners Multiple Sclerosis Center, Ann Romney Center for Neurologic Diseases, Departments of Neurology and Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts 02115
| | - Rohit Bakshi
- Laboratory for Neuroimaging Research, Partners Multiple Sclerosis Center, Ann Romney Center for Neurologic Diseases, Departments of Neurology and Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts 02115
| |
Collapse
|