Susanne Merz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Susanne Merz has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Samuel Kaski
Department of Computer Science, Aalto University, Espoo, Finland
2 shared publications Alexandra Markl
Institute of Medical Psychology and Behavioral Neurobiology, University of Tübingen, Tübingen, Germany
1 shared publicationAnna Fournier
1 shared publication- Anttoni Ojanperä
Department of Computer Science Aalto University Espoo Finland
1 shared publication Arnaud Muller
Genomics Research Unit, Oncology Department, LIH, Luxembourg, L-1526, Luxembourg
1 shared publicationBoris Kotchoubey
Institute of Medical Psychology and Behavioral Neurobiology, University of Tübingen, Tübingen, Germany
1 shared publication
Latest Publications
- Open Access
Machine learning on magnetoencephalography data yields generalizable low-dimensional neural fingerprints that distinguish individuals across task conditions
Individual brains are unique in structure and function. Functional differences are captured by neural fingerprints, which reflect individual differences in behavior and cognition as well as group-level changes related to neurodegenerative diseases. Most research efforts so far have focused on fingerprints com-prising full functional connectomes. However, the high dimensionality of the connectomes can increase computational load and impede performance of machine learning methods in potential applications. A low-dimensional alternative that retains individual features of the full connectomes would thus be beneficial. The present study employed latent-noise Bayesian Reduced Rank Regression (lnBRRR) to learn low-dimensional latent spaces that capture individual features in functional connectivity and power spectral density data derived from MEG recordings. LnBRRR performance was assessed with low training set sizes (N=20-44), and against principal component analysis and linear discriminant analysis. Model performance was also assessed with task data, and the solutions were compared across task conditions with cosine similarity to establish whether individual features are altered by different cognitive processes. LnBRRR captured generalizable individual patterns already at N=20 but N=30-35 was needed to reach optimal test accuracies and to prevent potential overfitting. The model also achieved comparable performance to the alternative models. Latent fingerprints derived from task data attained comparable performance to resting-state latent fingerprints, and lnBRRR solutions were shown to generalize across conditions. Additionally, the model solutions for power spectral density data were discovered to be notably similar, yet differently rotated, over task conditions, suggesting that similar patterns of individual features were captured by the model regardless of the task condition. Altogether, the present results highlight lnBRRR as a potential tool for neuroimaging data analysis and demonstrate that individual differences in power spectral density are largely intrinsic and unaffected by varying cognitive processes.
Open AccessMachine learning on magnetoencephalography data yields generalizable low-dimensional neural fingerprints that distinguish individuals across task conditions
Individual brains are unique in structure and function. Functional differences are captured by neural fingerprints, which reflect individual differences in behavior and cognition as well as group-level changes related to neurodegenerative diseases. Most research efforts so far have focused on fingerprints com-prising full functional connectomes. However, the high dimensionality of the connectomes can increase computational load and impede performance of machine learning methods in potential applications. A low-dimensional alternative that retains individual features of the full connectomes would thus be beneficial. The present study employed latent-noise Bayesian Reduced Rank Regression (lnBRRR) to learn low-dimensional latent spaces that capture individual features in functional connectivity and power spectral density data derived from MEG recordings. LnBRRR performance was assessed with low training set sizes (N=20-44), and against principal component analysis and linear discriminant analysis. Model performance was also assessed with task data, and the solutions were compared across task conditions with cosine similarity to establish whether individual features are altered by different cognitive processes. LnBRRR captured generalizable individual patterns already at N=20 but N=30-35 was needed to reach optimal test accuracies and to prevent potential overfitting. The model also achieved comparable performance to the alternative models. Latent fingerprints derived from task data attained comparable performance to resting-state latent fingerprints, and lnBRRR solutions were shown to generalize across conditions. Additionally, the model solutions for power spectral density data were discovered to be notably similar, yet differently rotated, over task conditions, suggesting that similar patterns of individual features were captured by the model regardless of the task condition. Altogether, the present results highlight lnBRRR as a potential tool for neuroimaging data analysis and demonstrate that individual differences in power spectral density are largely intrinsic and unaffected by varying cognitive processes.
- Open Access
- 12 September 2023
- Published by Wiley
Bayesian reduced rank regression reveals generalisable neural fingerprints that differentiate between individuals in magnetoencephalography data
Recent magnetoencephalography (MEG) studies have reported that functional connectivity (FC) and power spectra can be used as neural fingerprints in differentiating individuals. Such studies have mainly used correlations between measurement sessions to distinguish individuals from each other. However, it has remained unclear whether such correlations might reflect a more generalisable principle of individually distinctive brain patterns. Here, we evaluated a machine-learning based approach, termed latent-noise Bayesian reduced rank regression (BRRR) as a means of modelling individual differences in the resting-state MEG data of the Human Connectome Project (HCP), using FC and power spectra as neural features. First, we verified that BRRR could model and reproduce the differences between metrics that correlation-based fingerprinting yields. We trained BRRR models to distinguish individuals based on data from one measurements and used the models to identify subsequent measurement sessions of those same individuals. The best performing BRRR models, using only 20 spatiospectral components, were able to identify subjects across measurement sessions with over 90% accuracy, approaching the highest correlation-based accuracies. Using cross-validation, we then determined whether that BRRR could generalize to unseen subjects, successfully classifying the measurement sessions of novel individuals with over 80% accuracy. The results demonstrate that individual neurofunctional differences can be reliably extracted from MEG data with a low-dimensional predictive model.
- 12 September 2023
- Published by Wiley
Open AccessBayesian reduced rank regression reveals generalisable neural fingerprints that differentiate between individuals in magnetoencephalography data
Recent magnetoencephalography (MEG) studies have reported that functional connectivity (FC) and power spectra can be used as neural fingerprints in differentiating individuals. Such studies have mainly used correlations between measurement sessions to distinguish individuals from each other. However, it has remained unclear whether such correlations might reflect a more generalisable principle of individually distinctive brain patterns. Here, we evaluated a machine-learning based approach, termed latent-noise Bayesian reduced rank regression (BRRR) as a means of modelling individual differences in the resting-state MEG data of the Human Connectome Project (HCP), using FC and power spectra as neural features. First, we verified that BRRR could model and reproduce the differences between metrics that correlation-based fingerprinting yields. We trained BRRR models to distinguish individuals based on data from one measurements and used the models to identify subsequent measurement sessions of those same individuals. The best performing BRRR models, using only 20 spatiospectral components, were able to identify subjects across measurement sessions with over 90% accuracy, approaching the highest correlation-based accuracies. Using cross-validation, we then determined whether that BRRR could generalize to unseen subjects, successfully classifying the measurement sessions of novel individuals with over 80% accuracy. The results demonstrate that individual neurofunctional differences can be reliably extracted from MEG data with a low-dimensional predictive model.
- Open Access
- 31 May 2016
- Published by Springer Nature in Scientific Reports
- Vol. 6 (1) , 26822
Analysis of the dynamic co-expression network of heart regeneration in the zebrafish
The zebrafish has the capacity to regenerate its heart after severe injury. While the function of a few genes during this process has been studied, we are far from fully understanding how genes interact to coordinate heart regeneration. To enable systematic insights into this phenomenon, we generated and integrated a dynamic co-expression network of heart regeneration in the zebrafish and linked systems-level properties to the underlying molecular events. Across multiple post-injury time points, the network displays topological attributes of biological relevance. We show that regeneration steps are mediated by modules of transcriptionally coordinated genes, and by genes acting as network hubs. We also established direct associations between hubs and validated drivers of heart regeneration with murine and human orthologs. The resulting models and interactive analysis tools are available at http://infused.vital-it.ch. Using a worked example, we demonstrate the usefulness of this unique open resource for hypothesis generation and in silico screening for genes involved in heart regeneration.
- 31 May 2016
- Published by Springer Nature in Scientific Reports
- Vol. 6 (1) , 26822
Open AccessAnalysis of the dynamic co-expression network of heart regeneration in the zebrafish
The zebrafish has the capacity to regenerate its heart after severe injury. While the function of a few genes during this process has been studied, we are far from fully understanding how genes interact to coordinate heart regeneration. To enable systematic insights into this phenomenon, we generated and integrated a dynamic co-expression network of heart regeneration in the zebrafish and linked systems-level properties to the underlying molecular events. Across multiple post-injury time points, the network displays topological attributes of biological relevance. We show that regeneration steps are mediated by modules of transcriptionally coordinated genes, and by genes acting as network hubs. We also established direct associations between hubs and validated drivers of heart regeneration with murine and human orthologs. The resulting models and interactive analysis tools are available at http://infused.vital-it.ch. Using a worked example, we demonstrate the usefulness of this unique open resource for hypothesis generation and in silico screening for genes involved in heart regeneration.
- 6 November 2012
- Published by Springer Nature in Journal of Neurology
- Vol. 260 (4) , 975-983
Global functional connectivity reveals highly significant differences between the vegetative and the minimally conscious state
A major challenge in the diagnosis of disorders of consciousness is the differential diagnosis between the vegetative state (VS) and the minimally conscious state (MCS). Clinically, VS is defined by complete unawareness, whereas MCS is defined by the presence of inconsistent but clearly discernible behavioural signs of consciousness. In healthy individuals, pain cries have been reported to elicit functional activation within the pain matrix of the brain, which may be interpreted as empathic reaction. In this study, pain cries were presented to six VS patients, six MCS patients, and 17 age-matched healthy controls. Conventional task-related functional magnetic resonance imaging (fMRI) showed no significant differences in functional activation between the VS and MCS groups. In contrast to this negative finding, the application of a novel data-driven technique for the analysis of the brain’s global functional connectivity yielded a positive result. The weighted global connectivity (WGC) was significantly greater in the MCS group compared to the VS group (p < 0.05, family-wise error corrected). Using areas of significant WGC differences as ‘seed regions’ in a secondary connectivity analysis revealed extended functional networks in both MCS and healthy groups, whereas no such long-range functional connections were observed in the VS group. These results demonstrate the potential of functional connectivity MRI (fcMRI) as a clinical tool for differential diagnosis in disorders of consciousness.
- 6 November 2012
- Published by Springer Nature in Journal of Neurology
- Vol. 260 (4) , 975-983
Global functional connectivity reveals highly significant differences between the vegetative and the minimally conscious state
A major challenge in the diagnosis of disorders of consciousness is the differential diagnosis between the vegetative state (VS) and the minimally conscious state (MCS). Clinically, VS is defined by complete unawareness, whereas MCS is defined by the presence of inconsistent but clearly discernible behavioural signs of consciousness. In healthy individuals, pain cries have been reported to elicit functional activation within the pain matrix of the brain, which may be interpreted as empathic reaction. In this study, pain cries were presented to six VS patients, six MCS patients, and 17 age-matched healthy controls. Conventional task-related functional magnetic resonance imaging (fMRI) showed no significant differences in functional activation between the VS and MCS groups. In contrast to this negative finding, the application of a novel data-driven technique for the analysis of the brain’s global functional connectivity yielded a positive result. The weighted global connectivity (WGC) was significantly greater in the MCS group compared to the VS group (p < 0.05, family-wise error corrected). Using areas of significant WGC differences as ‘seed regions’ in a secondary connectivity analysis revealed extended functional networks in both MCS and healthy groups, whereas no such long-range functional connections were observed in the VS group. These results demonstrate the potential of functional connectivity MRI (fcMRI) as a clinical tool for differential diagnosis in disorders of consciousness.
- 19 March 2012
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 109 (14) , 5464-5468
Electroconvulsive therapy reduces frontal cortical connectivity in severe depressive disorder
To date, electroconvulsive therapy (ECT) is the most potent treatment in severe depression. Although ECT has been successfully applied in clinical practice for over 70 years, the underlying mechanisms of action remain unclear. We used functional MRI and a unique data-driven analysis approach to examine functional connectivity in the brain before and after ECT treatment. Our results show that ECT has lasting effects on the functional architecture of the brain. A comparison of pre- and posttreatment functional connectivity data in a group of nine patients revealed a significant cluster of voxels in and around the left dorsolateral prefrontal cortical region (Brodmann areas 44, 45, and 46), where the average global functional connectivity was considerably decreased after ECT treatment (P< 0.05, family-wise error-corrected). This decrease in functional connectivity was accompanied by a significant improvement (P< 0.001) in depressive symptoms; the patients’ mean scores on the Montgomery Asberg Depression Rating Scale pre- and posttreatment were 36.4 (SD = 4.9) and 10.7 (SD = 9.6), respectively. The findings reported here add weight to the emerging “hyperconnectivity hypothesis” in depression and support the proposal that increased connectivity may constitute both a biomarker for mood disorder and a potential therapeutic target.
- 19 March 2012
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 109 (14) , 5464-5468
Electroconvulsive therapy reduces frontal cortical connectivity in severe depressive disorder
To date, electroconvulsive therapy (ECT) is the most potent treatment in severe depression. Although ECT has been successfully applied in clinical practice for over 70 years, the underlying mechanisms of action remain unclear. We used functional MRI and a unique data-driven analysis approach to examine functional connectivity in the brain before and after ECT treatment. Our results show that ECT has lasting effects on the functional architecture of the brain. A comparison of pre- and posttreatment functional connectivity data in a group of nine patients revealed a significant cluster of voxels in and around the left dorsolateral prefrontal cortical region (Brodmann areas 44, 45, and 46), where the average global functional connectivity was considerably decreased after ECT treatment (P< 0.05, family-wise error-corrected). This decrease in functional connectivity was accompanied by a significant improvement (P< 0.001) in depressive symptoms; the patients’ mean scores on the Montgomery Asberg Depression Rating Scale pre- and posttreatment were 36.4 (SD = 4.9) and 10.7 (SD = 9.6), respectively. The findings reported here add weight to the emerging “hyperconnectivity hypothesis” in depression and support the proposal that increased connectivity may constitute both a biomarker for mood disorder and a potential therapeutic target.