Deep Learning on Conventional Magnetic Resonance Imaging Improves the Diagnosis of Multiple Sclerosis Mimics

2020 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Maria A. Rocca ◽  
Nicoletta Anzalone ◽  
Loredana Storelli ◽  
Anna Del Poggio ◽  
Laura Cacciaguerra ◽  
...  
2012 ◽  
Vol 18 (11) ◽  
pp. 1585-1591 ◽  
Author(s):  
Delphine Wybrecht ◽  
Françoise Reuter ◽  
Wafaa Zaaraoui ◽  
Anthony Faivre ◽  
Lydie Crespy ◽  
...  

Background: The ability of conventional magnetic resonance imaging (MRI) to predict subsequent physical disability and cognitive deterioration after a clinically isolated syndrome (CIS) is weak. Objectives: We aimed to investigate whether conventional MRI changes over 1 year could predict cognitive and physical disability 5 years later in CIS. We performed analyses using a global approach (T2 lesion load, number of T2 lesions), but also a topographic approach. Methods: This study included 38 patients with a CIS. At inclusion, 10 out of 38 patients fulfilled the 2010 revised McDonald’s criteria for the diagnosis of multiple sclerosis. Expanded Disability Status Scale (EDSS) evaluation was performed at baseline, year 1 and year 5, and cognitive evaluation at baseline and year 5. T2-weighted MRI was performed at baseline and year 1. We used voxelwise analysis to analyse the predictive value of lesions location for subsequent disability. Results: Using the global approach, no correlation was found between MRI and clinical data. The occurrence or growth of new lesions in the brainstem was correlated with EDSS changes over the 5 years of follow-up. The occurrence or growth of new lesions in cerebellum, thalami, corpus callosum and frontal lobes over 1 year was correlated with cognitive impairment at 5 years. Conclusion: The assessment of lesion location at the first stage of multiple sclerosis may be of value to predict future clinical disability.


2016 ◽  
Vol 29 (11) ◽  
pp. 742 ◽  
Author(s):  
Sara Peixoto ◽  
Pedro Abreu

Introduction: Clinically isolated syndrome may be the first manifestation of multiple sclerosis, a chronic demyelinating disease of the central nervous system, and it is defined by a single clinical episode suggestive of demyelination. However, patients with this syndrome, even with long term follow up, may not develop new symptoms or demyelinating lesions that fulfils multiple sclerosis diagnostic criteria. We reviewed, in clinically isolated syndrome, what are the best magnetic resonance imaging findings that may predict its conversion to multiple sclerosis.Material and Methods: A search was made in the PubMed database for papers published between January 2010 and June 2015 using the following terms: ‘clinically isolated syndrome’, ‘cis’, ‘multiple sclerosis’, ‘magnetic resonance imaging’, ‘magnetic resonance’ and ‘mri’.Results: In this review, the following conventional magnetic resonance imaging abnormalities found in literature were included: lesion load, lesion location, Barkhof’s criteria and brain atrophy related features. The non conventional magnetic resonance imaging techniques studied were double inversion recovery, magnetization transfer imaging, spectroscopy and diffusion tensor imaging.Discussion: The number and location of demyelinating lesions have a clear role in predicting clinically isolated syndrome conversion to multiple sclerosis. On the other hand, more data are needed to confirm the ability to predict this disease development of non conventional techniques and remaining neuroimaging abnormalities.Conclusion: In forthcoming years, in addition to the established predictive value of the above mentioned neuroimaging abnormalities,different clinically isolated syndrome neuroradiological findings may be considered in multiple sclerosis diagnostic criteria and/or change its treatment recommendations.


2013 ◽  
Vol 339 ◽  
pp. 361-365 ◽  
Author(s):  
Yan Xiang ◽  
Jian Feng He ◽  
Lei Ma ◽  
San Li Yi ◽  
Jia Ping Xu

Multiple sclerosis (MS) is a chronic disease that affects the central nervous system and impacts substantially on patients. MS lesions are visible in conventional magnetic resonance imaging (cMRI) and the automatic segmentation of MS lesions enables the efficient processing of images for research studies and in clinical trials. A new method for the segmentation of MS white matter lesions (WML) on cMRI is presented in this paper. Firstly the Kernel Fuzzy C-Means Clustering (KFCM) is applied to the preprocessed T1-weight (T1-w) image for extracting the white matter (WM) region. Then region growing algorithm is applied to the WM region image to make a binary mask which is then superimposed on the corresponding T2-weight (T2-w) image to yield a masked image only containing WM structures and lesions. The KFCM is then reapplied to the masked image to obtain MS lesions. The testing results show that the proposed method is able to segment WML on cMRI automatically and effectively.


Sign in / Sign up

Export Citation Format

Share Document