scholarly journals Accuracy of magnetic resonance imaging for the diagnosis of multiple sclerosis: systematic review

2006 ◽  
Vol 31 (4) ◽  
pp. 319-319
Author(s):  
Penny Whiting ◽  
Roger Harbord ◽  
Caroline Main ◽  
Jonathan J Deeks ◽  
Graziella Filippini ◽  
...  
2020 ◽  
Vol 28 ◽  
pp. 102371
Author(s):  
Benjamin V. Ineichen ◽  
Pascal Sati ◽  
Tobias Granberg ◽  
Martina Absinta ◽  
Nathanael J. Lee ◽  
...  

2021 ◽  
Vol 15 (4) ◽  
pp. 54-65
Author(s):  
Galina N. Chernyaeva ◽  
Sergey P. Morozov ◽  
Anton V. Vladzimirskyy

A systematic review was undertaken to summarize the data regarding accuracy and effectiveness of artificial intelligence algorithms for identifying MRI manifestations of multiple sclerosis. The review included 39 papers, whose authors put forth a multitude of corresponding algorithms and mathematical models. However, quality assessment of these developments was limited by retrospective testing on repeat data sets. Clinical test results were almost entirely absent, and there were no prospective independent studies of accuracy and applicability. The relatively high values obtained for the main measures (similarity, sensitivity and specificity coefficients, which were 7585%) were offset by the methodological errors when creating the baseline data sets, and lack of validation using independent data. Due to small sample sizes and methodological errors when measuring the result accuracy, most of the studies did not meet the criteria for evidence-based research. Studies with the highest methodological quality had algorithms that achieved a sensitivity of 51.677.0%, with a SrensenDice coefficient of 53.556.0%. These numbers are not high, but they indicate that automatic identification of multiple sclerosis manifestations on magnetic resonance imaging may be achievable. Further development of computer-aided analysis requires the creation of clinical use scenarios and testing methodology, and prospective clinical testing.


BMJ ◽  
2006 ◽  
Vol 332 (7546) ◽  
pp. 875-884 ◽  
Author(s):  
Penny Whiting ◽  
Roger Harbord ◽  
Caroline Main ◽  
Jonathan J Deeks ◽  
Graziella Filippini ◽  
...  

2020 ◽  
Vol 267 (11) ◽  
pp. 3199-3212 ◽  
Author(s):  
Tobias Granberg ◽  
Thomas Moridi ◽  
Judith S. Brand ◽  
Susanne Neumann ◽  
Martin Hlavica ◽  
...  

Abstract Background Perivascular spaces can become detectable on magnetic resonance imaging (MRI) upon enlargement, referred to as enlarged perivascular spaces (EPVS) or Virchow-Robin spaces. EPVS have been linked to small vessel disease. Some studies have also indicated an association of EPVS to neuroinflammation and/or neurodegeneration. However, there is conflicting evidence with regards to their potential as a clinically relevant imaging biomarker in multiple sclerosis (MS). Methods To perform a systematic review and meta-analysis of EPVS as visualized by MRI in MS. Nine out of 299 original studies addressing EPVS in humans using MRI were eligible for the systematic review and meta-analysis including a total of 457 MS patients and 352 control subjects. Results In MS, EPVS have been associated with cognitive decline, contrast-enhancing MRI lesions, and brain atrophy. Yet, these associations were not consistent between studies. The meta-analysis revealed that MS patients have greater EPVS prevalence (odds ratio = 4.61, 95% CI = [1.84; 11.60], p = 0.001) as well as higher EPVS counts (standardized mean difference [SMD] = 0.46, 95% CI = [0.26; 0.67], p < 0.001) and larger volumes (SMD = 0.88, 95% CI = [0.19; 1.56], p = 0.01) compared to controls. Conclusions Available literature suggests a higher EPVS burden in MS patients compared to controls. The association of EPVS to neuroinflammatory or -degenerative pathology in MS remains inconsistent. Thus, there is currently insufficient evidence supporting EPVS as diagnostic and/or prognostic marker in MS. In order to benefit future comparisons of studies, we propose recommendations on EPVS assessment standardization in MS. PROSPERO No: CRD42019133946.


Sign in / Sign up

Export Citation Format

Share Document