Objective
The main objective was to compare clinical features, disease course, and myelin oligodendrocyte glycoprotein (MOG) antibody (Ab) dynamics between children and adults with MOG‐Ab–associated ...disease (MOGAD).
Methods
This retrospective multicentric, national study included 98 children and 268 adults with MOGAD between January 2014 and September 2019. Cox regression model for recurrent time‐to‐event data and Kaplan–Meier curves for time to antibody negativity were performed for the objectives.
Results
Isolated optic neuritis was the most frequent clinical presentation in both children (40.8%) and adults (55.9%, p = 0.013), and acute disseminated encephalomyelitis syndrome was more frequent in children (36.7% vs 5.6%, p < 0.001). Compared to adults, children displayed better recovery (Expanded Disability Status Scale ≥ 3.0 at last follow‐up reached only by 10 of 97 10.3% vs 66/247 26.7%, p < 0.001). In the multivariate analysis, adults were at higher risk of relapse than children (hazard ratio = 1.41, 95% confidence interval CI = 1.12–1.78, p = 0.003). At 2 years, 64.2% (95% CI = 40.9–86.5) of nonrelapsing children became MOG‐Ab negative compared to 14.1% (95% CI = 4.7–38.3) of relapsing children (log‐rank p < 0.001), with no differences observed in adults (log‐rank p = 0.280).
Interpretation
MOGAD patients differ in the clinical presentation at onset, showing an age‐related shift in the clinical features across age groups. Compared to children, adults have a higher risk of relapse and worse functional recovery. Finally, children with monophasic disease become MOG‐Ab negative earlier than relapsing children, but this is not true in adults. Considering these differences, management and treatment guidelines should be considered independently in children and adults. ANN NEUROL 2021;89:30–41
Background and objective
The prognosis in myelin oligodendrocyte glycoprotein (MOG) antibody‐associated disease (MOGAD) is a matter of debate. Our aim was to assess the long‐term outcomes of patients ...with MOGAD.
Methods
We retrospectively analysed the clinical and paraclinical data of patients from the French nationwide observatory study NOMADMUS who tested positive for MOG antibodies (MOG‐IgG) and who had clinical follow‐up of at least 8 years from their first episode.
Results
Sixty‐one patients (median range age at onset 27 3–69 years), with a median (mean; range) follow‐up of 177 (212.8; 98–657) months, were included. Among 58 patients with a relapsing course, 26.3% relapsed in the first year after onset. Of the 61 patients, 90.2% experienced at least one episode of optic neuritis. At last visit, the median (mean; range) Expanded Disability Status Scale (EDSS) score was 1 (2.12; 0–7.5), 12.5% had an EDSS score ≥6 and 37.5% had an EDSS score ≥3. Of 51 patients with final visual acuity (VA) data available, 15.7% had VA ≤0.1 in at least one eye and 25.5% had VA ≤0.5 in at least one eye. Bilateral blindness (VA ≤0.1) was present in 5.9% of patients. Finally, 12.5% of patients presented bladder dysfunction requiring long‐term urinary catheterization. No factor associated significantly with a final EDSS score ≥3 or with final VA ≤0.1 was found.
Conclusion
Overall long‐term favourable outcomes were achieved in a majority of our patients, but severe impairment, in particular visual damage, was not uncommon.
Sixty one patients with myelin oligodendrocyte glycoprotein antibody‐associated disease were included, of whom 90.2% experienced at least one episode of optic neuritis. At last visit (median range follow‐up of 177 98–657 months), the median (mean; range) Expanded Disability Status Scale (EDSS) score was 1 (2.12; 0–7.5), 12.5% had an EDSS score ≥6 and 15.7% had visual acuity (VA) ≤0.1. Bilateral blindness (VA ≤0.1) was present in 5.9% of patients. No factor was associated significantly with a final EDSS ≥3 or with final VA ≤0.1. Overall long‐term favourable outcomes were achieved in a majority of patients, but severe impairment, in particular visual damage, was not uncommon.
•Generating synthetic brain networks is not trivial due to multiple interconnections between different nodes.•Generative Adversarial Autoencoder neural network is employed for the generation of ...synthetic structural brain network with Multiple Sclerosis.•Structural comparison between real and synthetic brain network is performed for assessing the quality of generated samples.•Classification performance comparison shows significant improvement over traditional upsampling methods.
Background and objective:Machine learning frameworks have demonstrated their potentials in dealing with complex data structures, achieving remarkable results in many areas, including brain imaging. However, a large collection of data is needed to train these models. This is particularly challenging in the biomedical domain since, due to acquisition accessibility, costs and pathology related variability, available datasets are limited and usually imbalanced. To overcome this challenge, generative models can be used to generate new data.
Methods: In this study, a framework based on generative adversarial network is proposed to create synthetic structural brain networks in Multiple Sclerosis (MS). The dataset consists of 29 relapsing-remitting and 19 secondary-progressive MS patients. T1 and diffusion tensor imaging (DTI) acquisitions were used to obtain the structural brain network for each subject. Evaluation of the quality of newly generated brain networks is performed by (i) analysing their structural properties and (ii) studying their impact on classification performance.
Results: We demonstrate that advanced generative models could be directly applied to the structural brain networks. We quantitatively and qualitatively show that newly generated data do not present significant differences compared to the real ones. In addition, augmenting the existing dataset with generated samples leads to an improvement of the classification performance (F1score 81%) with respect to the baseline approach (F1score 66%).
Conclusions: Our approach defines a new tool for biomedical application when connectome-based data augmentation is needed, providing a valid alternative to usual image-based data augmentation techniques.
The lack of interpretability of deep learning reduces understanding of what happens when a network does not work as expected and hinders its use in critical fields like medicine, which require ...transparency of decisions. For example, a healthy vs pathological classification model should rely on radiological signs and not on some training dataset biases. Several post-hoc models have been proposed to explain the decision of a trained network. However, they are very seldom used to enforce interpretability during training and none in accordance with the classification. In this paper, we propose a new weakly supervised method for both interpretable healthy vs pathological classification and anomaly detection. A new loss function is added to a standard classification model to constrain each voxel of healthy images to drive the network decision towards the healthy class according to gradient-based attributions. This constraint reveals pathological structures for patient images, allowing their unsupervised segmentation. Moreover, we advocate both theoretically and experimentally, that constrained training with the simple Gradient attribution is similar to constraints with the heavier Expected Gradient, consequently reducing the computational cost. We also propose a combination of attributions during the constrained training making the model robust to the attribution choice at inference. Our proposition was evaluated on two brain pathologies: tumors and multiple sclerosis. This new constraint provides a more relevant classification, with a more pathology-driven decision. For anomaly detection, the proposed method outperforms state-of-the-art especially on difficult multiple sclerosis lesions segmentation task with a 15 points Dice improvement.
We report a case of multiple cervical artery dissections that occurred 4 days after a first course of alemtuzumab in a woman with relapsing–remitting multiple sclerosis and discuss its potential ...relationship and mechanisms of action. In particular, an arterial inflammatory process, secondary to cytokine release, could potentially lead to intimal thickening, luminal irregularities, stenosis, and ultimately occlusion. Occurrence of an unexpected serious adverse event, in our case, multiple cervical artery dissections, especially in a close time window after drug administration, questions a potential causal relationship with the drug or a simple coincidence.
Background:
Leptomeningeal enhancement (LME) is a key feature of Susac syndrome (SuS) but is only occasionally depicted on post-contrast T1-weighted images (T1-WI).
Objective:
As post-contrast ...fluid-attenuated inversion recovery (FLAIR) may be more sensitive, our aim was to assess LME in SuS on this sequence.
Methods:
From 2010 to 2020, 20 patients with definite SuS diagnosis were retrospectively enrolled in this multicentre study. Two radiologists independently assessed the number of LME on post-contrast FLAIR and T1-WI acquisitions performed before any treatment. A chi-square test was used to compare both sequences and the interrater agreement was calculated.
Results:
Thirty-five magnetic resonance imagings (MRIs) were performed before treatment, including 19 post-contrast FLAIR images in 17 patients and 25 post-contrast T1-WI in 19 patients. In terms of patients, LME was observed on all post-contrast FLAIR, contrary to post-contrast T1-WI (17/17 (100%) vs. 15/19 (79%), p < 0.05). In terms of sequences, LME was observed on all post-contrast FLAIR, contrary to post-contrast T1-WI (19/19 (100%) vs. 16/25 (64%), p < 0.005). LME was disseminated at both supratentorial (19/19) and infratentorial (18/19) levels on post-contrast FLAIR, contrary to post-contrast T1-WI (3/25 and 9/25, respectively). Interrater agreement was excellent for post-contrast FLAIR (κ = 0.95) but only moderate for post-contrast T1-WI (κ = 0.61).
Conclusion:
LME was always observed and easily visible on post-contrast FLAIR images prior to SuS treatment. In association with other MRI features, it is highly indicative of SuS.
Multiple Sclerosis (MS) is an autoimmune disease that combines chronic inflammatory and neurodegenerative processes underlying different clinical forms of evolution, such as relapsing-remitting, ...secondary progressive, or primary progressive MS. This identification is usually performed by clinical evaluation at the diagnosis or during the course of the disease for the secondary progressive phase. In parallel, magnetic resonance imaging (MRI) analysis is a mandatory diagnostic complement. Identifying the clinical form from MR images is therefore a helpful and challenging task. Here, we propose a new approach for the automatic classification of MS forms based on conventional MRI (i.e., T1-weighted images) that are commonly used in clinical context. For this purpose, we investigated the morphological connectome features using graph based convolutional neural network. Our results obtained from the longitudinal study of 91 MS patients highlight the performance (F1-score) of this approach that is better than state-of-the-art as 3D convolutional neural networks. These results open the way for clinical applications such as disability correlation only using T1-weighted images.
We report 5 cases of acute heart failure (AHF) related to multiple sclerosis (MS) relapses. AHF was inaugural in 3 patients, always preceded or accompanied by signs of brainstem dysfunction; it was ...severe, requiring intensive care management. Echocardiography showed left ventricular hypokinesis. No other cause of AHF has been found. All patients showed a new medullary lesion on brain magnetic resonance imaging. All had rapid and complete recovery of ventricular function after intravenous corticosteroids. We concluded that the cases represent a takotsubo phenomenon. Physicians should be aware of rare cases of takotsubo cardiomyopathy in MS relapses. Ann Neurol 2017;81:754–758
Recent advances in image acquisition and processing techniques, along with the success of novel deep learning architectures, have given the opportunity to develop innovative algorithms capable to ...provide a better characterization of neurological related diseases. In this work, we introduce a neural network based approach to classify Multiple Sclerosis (MS) patients into four clinical profiles. Starting from their structural connectivity information, obtained by diffusion tensor imaging and represented as a graph, we evaluate the classification performances using unweighted and weighted connectivity matrices. Furthermore, we investigate the role of graph-based features for a better characterization and classification of the pathology. Ninety MS patients (12 clinically isolated syndrome, 30 relapsing-remitting, 28 secondary-progressive, and 20 primary-progressive) along with 24 healthy controls, were considered in this study. This work shows the great performances achieved by neural networks methods in the classification of the clinical profiles. Furthermore, it shows local graph metrics do not improve the classification results suggesting that the latent features created by the neural network in its layers have a much important informative content. Finally, we observe that graph weights representation of brain connections preserve important information to discriminate between clinical forms.