Susanna Asseyer

Susanna Asseyer

Auto-generated profile, based on publicly available information

Susanna Asseyer

Experimental and Clinical Research Center a Cooperation between Max Delbrück Center for Molecular Medicine in the Helmholtz Association and Charité‐Universitätsmedizin Berlin Berlin Germany

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019 in NeuroImage: Clinical
Verified
Journal Article
Open access
FEFabian Eitel
Fabian Eitel
ESEmily Soehler
Emily Soehler
JBJudith Bellmann-Strobl
Judith Bellmann-Strobl
ABAlexander Ulrich Brandt
Alexander Ulrich Brandt
KRKlemens Ruprecht
Klemens Ruprecht
KRKerstin Ritter
Kerstin Ritter
Machine learning-based imaging diagnostics has recently reached or even surpassed the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on 3D convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS), the most widespread autoimmune neuroinflammatory disease. MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer's Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients (n = 76) and healthy controls (n = 71). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of CNN models transparent, which could serve to justify classification decisions for clinical review, verify diagnosis-relevant features and potentially gather new disease knowledge.

25 February 2022 in Neurology Neuroimmunology & Neuroinflammation
Verified
Journal Article
Open access
PDF file
JMJannis Müller
Jannis Müller
TSTim Sinnecker
Tim Sinnecker
MWMaria Janina Wendebourg
Maria Janina Wendebourg
RSRegina Schläger
Regina Schläger
JKJens Kuhle
Jens Kuhle
ÖYÖzgür Yaldizli
Özgür Yaldizli
Background and Objectives The choroid plexus has been shown to play a crucial role in CNS inflammation. Previous studies found larger choroid plexus in multiple sclerosis (MS) compared with healthy controls. However, it is not clear whether the choroid plexus is similarly involved in MS and in neuromyelitis optica spectrum disorder (NMOSD). Thus, the aim of this study was to compare the choroid plexus volume in MS and NMOSD. Methods In this retrospective, cross-sectional study, patients were included by convenience sampling from 4 international MS centers. The choroid plexus of the lateral ventricles was segmented fully automatically on T1-weighted MRI sequences using a deep learning algorithm (Multi-Dimensional Gated Recurrent Units). Uni- and multivariable linear models were applied to investigate associations between the choroid plexus volume, clinically meaningful disease characteristics, and MRI parameters. Results We studied 180 patients with MS and 98 patients with NMOSD. In total, 94 healthy individuals and 47 patients with migraine served as controls. The choroid plexus volume was larger in MS (median 1,690 µL, interquartile range [IQR] 648 µL) than in NMOSD (median 1,403 µL, IQR 510 µL), healthy individuals (median 1,533 µL, IQR 570 µL), and patients with migraine (median 1,404 µL, IQR 524 µL; all p < 0.001), whereas there was no difference between NMOSD, migraine, and healthy controls. This was also true when adjusted for age, sex, and the intracranial volume. In contrast to NMOSD, the choroid plexus volume in MS was associated with the number of T2-weighted lesions in a linear model adjusted for age, sex, total intracranial volume, disease duration, relapses in the year before MRI, disease course, Expanded Disability Status Scale score, disease-modifying treatment, and treatment duration (beta 4.4; 95% CI 0.78–8.1; p = 0.018). Discussion This study supports an involvement of the choroid plexus in MS in contrast to NMOSD and provides clues to better understand the respective pathogenesis.

21 August 2020 in Frontiers in Neurology
Verified
Journal Article
Open access
PDF file
SASusanna Asseyer
Susanna Asseyer
GCGraham Cooper
Graham Cooper
Friedemann PaulFriedemann Paul
Friedemann Paul
Neuromyelitis optica spectrum disorders (NMOSDs) and myelin oligodendrocyte glycoprotein-antibody-associated disease (MOGAD) are autoimmune inflammatory disorders of the central nervous system (CNS). Pain is highly prevalent and debilitating in NMOSD and MOGAD with a severe impact on quality of life, and there is a critical need for further studies to successfully treat and manage pain in these rare disorders. In NMOSD, pain has a prevalence of over 80%, and pain syndromes include neuropathic, nociceptive, and mixed pain, which can emerge in acute relapse or become chronic during the disease course. The impact of pain in MOGAD has only recently received increased attention, with an estimated prevalence of over 70%. These patients typically experience not only severe headache, retrobulbar pain, and/or pain on eye movement in optic neuritis but also neuropathic and nociceptive pain. Given the high relevance of pain in MOGAD and NMOSD, this article provides a systematic review of the current literature pertaining to pain in both disorders, focusing on the etiology of their respective pain syndromes and their pathophysiological background. Acknowledging the challenge and complexity of diagnosing pain, we also provide a mechanism-based classification of NMOSD- and MOGAD-related pain syndromes and summarize current treatment strategies.

1 May 2021 in Neurology Neuroimmunology & Neuroinflammation
Verified
Journal Article
Open access
PDF file
IAIlya Ayzenberg
Ilya Ayzenberg
DRDaniel Richter
Daniel Richter
EHEugenia Henke
Eugenia Henke
SASusanna Asseyer
Susanna Asseyer
Friedemann PaulFriedemann Paul
Friedemann Paul
OGon behalf of the NEMOS (Neuromyelitis Optica Study Group)
on behalf of the NEMOS (Neuromyelitis Optica Study Group)
Objectives To evaluate prevalence, clinical characteristics, and predictors of pain, depression, and their impact on the quality of life (QoL) in a large neuromyelitis optica spectrum disorder (NMOSD) cohort. Methods We included 166 patients with aquaporin-4–seropositive NMOSD from 13 tertiary referral centers. Patients received questionnaires on demographic and clinical characteristics, PainDetect, short form of Brief Pain Inventory, Beck Depression Inventory–II, and Short Form 36 Health Survey. Results One hundred twenty-five (75.3%) patients suffered from chronic NMOSD-associated pain. Of these, 65.9% had neuropathic pain, 68.8% reported spasticity-associated pain and 26.4% painful tonic spasms. Number of previous myelitis attacks (OR = 1.27, p = 0.018) and involved upper thoracic segments (OR = 1.31, p = 0.018) were the only predictive factors for chronic pain. The latter was specifically associated with spasticity-associated pain (OR = 1.36, p = 0.002). More than a third (39.8%) suffered from depression, which was moderate to severe in 51.5%. Pain severity (OR = 1.81, p < 0.001) and especially neuropathic character (OR = 3.44, p < 0.001) were associated with depression. Pain severity and walking impairment explained 53.9% of the physical QoL variability, while depression and walking impairment 39.7% of the mental QoL variability. No specific medication was given to 70.6% of patients with moderate or severe depression and 42.5% of those with neuropathic pain. Two-thirds (64.2%) of patients with symptomatic treatment still reported moderate to severe pain. Conclusions Myelitis episodes involving upper thoracic segments are main drivers of pain in NMOSD. Although pain intensity was lower than in previous studies, pain and depression remain undertreated and strongly affect QoL. Interventional studies on targeted treatment strategies for pain are urgently needed in NMOSD.

1 May 2020 in Multiple Sclerosis and Related Disorders
Verified
Journal Article
Closed access
SASusanna Asseyer
Susanna Asseyer
JHJosh Hamblin
Josh Hamblin
SMSilvia Messina
Silvia Messina
RMRomina Mariano
Romina Mariano
NSNadja Siebert
Nadja Siebert
JPJacqueline Palace
Jacqueline Palace

1 September 2021 in Neurology Neuroimmunology & Neuroinflammation
Verified
Journal Article
Open access
PDF file
TLTing-Yi Lin
Ting-Yi Lin
VVViktoriya Vitkova
Viktoriya Vitkova
SASusanna Asseyer
Susanna Asseyer
ISIvette Martorell Serra
Ivette Martorell Serra
SMSeyedamirhosein Motamedi
Seyedamirhosein Motamedi
HZHanna G. Zimmermann
Hanna G. Zimmermann
Objective To investigate the association of combined serum neurofilament light chain (sNfL) and retinal optical coherence tomography (OCT) measurements with future disease activity in patients with early multiple sclerosis (MS). Methods We analyzed sNfL by single molecule array technology and performed OCT measurements in a prospective cohort of 78 patients with clinically isolated syndrome and early relapsing-remitting MS with a median (interquartile range) follow-up of 23.9 (23.3–24.7) months. Patients were grouped into those with abnormal or normal sNfL levels, defined as sNfL ≥/<80th percentile of age-corrected reference values. Likewise, patients were grouped by a median split into those with thin or thick ganglion cell and inner plexiform layer (GCIP), peripapillary retinal nerve fiber layer, and inner nuclear layer in nonoptic neuritis eyes. Outcome parameters were violation of no evidence of disease activity (NEDA-3) criteria or its components. Results Patients with abnormal baseline sNfL had a higher risk of violating NEDA-3 (hazard ratio [HR] 2.28, 95% CI 1.27–4.09, p = 0.006) and developing a new brain lesion (HR 2.47, 95% CI 1.30–4.69, p = 0.006), but not for a new relapse (HR 2.21, 95% CI 0.97–5.03, p = 0.058). Patients with both abnormal sNfL and thin GCIP had an even higher risk for NEDA-3 violation (HR 3.61, 95% CI 1.77–7.36, p = 4.2e−4), new brain lesion (HR 3.19, 95% CI 1.51–6.76, p = 0.002), and new relapse (HR 5.38, 95% CI 1.61–17.98, p = 0.006) than patients with abnormal sNfL alone. Conclusions In patients with early MS, the presence of both abnormal sNfL and thin GCIP is a stronger risk factor for future disease activity than the presence of each parameter alone.