Evaluation of the Central Vein Sign as a Diagnostic Imaging Biomarker in Multiple Sclerosis

Sinnecker, Tim; Clarke, Mitch; Meier, Dominik; Enzinger, Christian; Calabrese, Massimiliano; Stefano, Nicola De; Pitiot, Alain; Giorgio, Antonio; Schoonheim, Menno M.; Paul, Friedemann; Pawlak, Mikołaj A.; Schmidt, Reinhold; Kappos, Ludwig; Montalbán, Xavier; Rovira, Àlex; Evangelou, Nikos; Wuerfel, Jens

doi:10.1001/jamaneurol.2019.2478

Cited by 156 publications

(171 citation statements)

References 38 publications

Supporting

Mentioning

148

Contrasting

Unclassified

Order By: Relevance

“…8 A recent large, multicentre study included patients with CISs and relapsing-remitting multiple sclerosis (RRMS) from observational studies or neuroimaging research databases. 4 This study confirmed the three-lesion rule as showing the most balanced diagnostic properties (61.9% sensitivity and 89.0% specificity) when assessing different absolute lesion number thresholds to differentiate MS from non-MS. However, despite including patients with CIS and early RRMS, the mean disease duration was 7 years, it was a cross-sectional study, and not all data originated from observational cohorts.…”

supporting

confidence: 73%

“…The central vein sign (CVS) has been proposed as a specific biomarker for multiple sclerosis (MS). 1 Although best visualized at ultra-high field magnetic resonance imaging (MRI), recent evidence demonstrates that the CVS can be detected with MRI at 3.0 and 1.5 T, [2][3][4] making it potentially useful in the clinical practice. The high specificity of the CVS in MS derives from comparisons with other neurological diseases with focal white matter hyperintensities.…”

mentioning

confidence: 99%

“…Susceptibility-weighted images (SWIs) have short acquisition times and are readily available, but they appear to be less sensitive than other imaging sequences in detecting the CVS. 2,4,5 Proper comparisons among sequences and general protocols used in MS are thus necessary. If such technical issues are not solved, the translation of the CVS to the clinical practice may prove limited.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Detection of central vein should be part of MS diagnostic criteria – No

Arrambide

2020

Mult Scler

View full text Add to dashboard Cite

The central vein sign (CVS) has been proposed as a specific biomarker for multiple sclerosis (MS). 1 Although best visualized at ultra-high field magnetic resonance imaging (MRI), recent evidence demonstrates that the CVS can be detected with MRI at 3.0 and 1.5 T, 2-4 making it potentially useful in the clinical practice. The high specificity of the CVS in MS derives from comparisons with other neurological diseases with focal white matter hyperintensities. 5 This is precisely one of the reasons the CVS cannot, at this point, be part of the MS diagnostic criteria. The McDonald criteria were not developed to differentiate MS from other diseases, but to confirm the diagnosis of MS in patients with typical symptoms once other diagnoses have been reasonably ruled out. 6 Nevertheless, incorporating more disease-specific biomarkers in the diagnostic criteria would of course be desirable. In this sense, we could then consider the results of previous studies as proof-of-concept of the high specificity of the CVS in MS lesions, which reflects the perivenous inflammatory demyelination occurring in this disease. To do so, the CVS should be assessed in the context of the 2017 McDonald criteria to determine whether its inclusion does increase the diagnostic specificity while maintaining a high sensitivity.There are, however, several issues to consider first. One is that the CVS can also be seen in diseases other than MS, 5 thus requiring the use of a proportion threshold of lesions with CVS which is usually but not always ⩾40%. 3,4 Using a proportion-based approach is not practical in the daily clinical practice, particularly in patients with a high lesion load. Furthermore, the proportion threshold appears to depend on the type of non-MS diseases the comparison is made against. 3,4,7 Instead, identifying a minimum number of lesions with CVS could simplify its use. However, past efforts in small, retrospective studies have suggested differing cut-offs. Whereas in one of these studies MS was diagnosed if at least 6 out of 10 randomly assessed lesions were perivenular, 8 in the other MS was diagnosed when 3 out of 3 randomly assessed lesions were perivenular. 9 Moreover, a third, small, retrospective study showed that the proportion-based approach, using a 50% and a 40% rule, yielded a higher diagnostic accuracy compared to the six-and three-lesion rule. 3 Another point to consider in these studies is that the mean/median disease duration in patients with MS was 7.7-10.0 years, besides one of the studies including both relapsing and progressive forms of the disease. 3,8,9 With such disease duration, the lesion load would be expected to be high and, at that point in the evolution of the disease, few reasonable doubts about the diagnosis would exist. Diagnosing MS in earlier stages in which the lesion count is usually lower is certainly more challenging. Efforts should thus be directed toward the assessment of the CVS in this setting, especially when considering that the CVS is more difficult to visualize in infratentorial and sp...

show abstract

supporting

confidence: 73%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Detection of central vein should be part of MS diagnostic criteria – No

Arrambide

2020

Mult Scler

View full text Add to dashboard Cite

show abstract

“…Our findings are particularly relevant considering that recent studies using manual CVS classification at clinical field strengths have shown potential for application of the CVS imaging biomarker in clinical practice . Importantly, the most recent international panel for MS diagnosis called for further research on this topic before considering inclusion of the CVS in future MS diagnostic criteria .…”

Section: Discussionmentioning

confidence: 81%

“…Today, the vein at the center of WM lesions can be imaged in vivo using optimized susceptibility‐based MRI sequences, and several studies have shown that the CVS can accurately distinguish MS from other disorders showing similar T2 hyperintensities on MRI . Results from a recent multicenter study suggest that the diagnostic performance of this CVS biomarker at clinical field strengths is highly dependent on the type of susceptibility‐based MRI sequence used . In this context, recent data from our group using an optimized three‐dimensional (3D) T2*‐weighted segmented echo‐planar imaging (T2*‐EPI) sequence at clinical field strengths have shown that the CVS can efficiently discriminate between MS and inflammatory vasculopathies of the CNS and that this imaging biomarker can accurately predict an MS diagnosis in patients harboring atypical features for the disease …”

Section: Introductionmentioning

confidence: 99%

CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis

et al. 2020

View full text Add to dashboard Cite

The central vein sign (CVS) is an efficient imaging biomarker for multiple sclerosis (MS) diagnosis, but its application in clinical routine is limited by inter-rater variability and the expenditure of time associated with manual assessment. We describe a deep learning-based prototype for automated assessment of the CVS in white matter MS lesions using data from three different imaging centers. We retrospectively analyzed data from 3 T magnetic resonance images acquired on four scanners from two different vendors, including adults with MS (n = 42), MS mimics (n = 33, encompassing 12 distinct neurological diseases mimicking MS) and uncertain diagnosis (n = 5). Brain white matter lesions were manually segmented on FLAIR* images. Perivenular assessment was performed according to consensus guidelines and used as ground truth, yielding 539 CVS-positive (CVS + ) and 448 CVS-negative (CVS − ) lesions. A 3D convolutional neural network ("CVSnet") was designed and trained on 47 datasets, keeping 33 for testing. FLAIR* lesion patches of CVS + /CVS − lesions were used for training and validation (n = 375/298) and for testing (n = 164/150). Performance was evaluated lesion-wise and subject-wise and compared with a state-of-the-art vesselness filtering approach through McNemar's test. The proposed CVSnet approached human performance, with lesion-wise median balanced accuracy of 81%, and subject-wise balanced accuracy of 89% on the validation set, and 91% on the test set. The process of CVS assessment, in previously manually segmented lesions, was~600-fold faster using the proposed CVSnet compared with human visual assessment (test set: 4 seconds vs. 40 minutes). On the validation and test sets, the lesion-wise performance outperformed the vesselness filter method (P < 0.001). The proposed deep learning prototype shows promising performance in differentiating MS from its mimics. Our approach was evaluated using data from different hospitals, enabling larger multicenter trials to evaluate the benefit of introducing the CVS marker into MS diagnostic criteria.Abbreviations used: AUC, area under the curve; CVS, central vein sign; FLAIR, 3D T2-weighted fluid-attenuated inversion recovery; GPU, graphics processing unit; MRI, magnetic resonance imaging; MS, multiple sclerosis; NIR, no information rate; ReLU, rectified linear unit; ROC, receiver operating characteristic; T2*-EPI, T2*-weighted segmented echo-planar imaging; 3D, threedimensional; WM, white matter.Pietro Maggi and Mário João Fartaria contributed equally to this work.

show abstract

Correction to Author’s Academic Degrees

2020

JAMA Neurol

View full text Add to dashboard Cite

In addition, he had a patent to a tyrosine kinase inhibitor (TKI) in neurodegeneration pending and issued and is an inventor on several US and international Georgetown University patents to use nilotinib and other TKIs as a treatment for neurodegenerative diseases. Dr Moussa, his laboratory, and Georgetown University previously received some income from the licensing of the technology to Axovant Science, which was spun out to a start-up company (KiefeRX LLC) from which Dr Moussa receives consulting fees.

show abstract

Evaluation of the Central Vein Sign as a Diagnostic Imaging Biomarker in Multiple Sclerosis

Cited by 156 publications

References 38 publications

Detection of central vein should be part of MS diagnostic criteria – No

Detection of central vein should be part of MS diagnostic criteria – No

CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis

Correction to Author’s Academic Degrees

Contact Info

Product

Resources

About