You can also find a complete list of my publications in my Google Scholar page.
- Mehraveh Salehi, Abigail S. Greene, Amin Karbasi, Xilin Shen, Dustin Scheinost, and R. Todd Constable. "There is no single functional atlas even for a single individual: Parcellation of the human brain is state dependent." bioRxiv (2018): 431833. (In revision)
The goal of human brain mapping has long been to delineate the functional subunits in the brain and elucidate the functional role of each of these brain regions. Recent work has focused on whole-brain parcellation of functional Magnetic Resonance Imaging (fMRI) data to identify these subunits and create a functional atlas. Functional connectivity approaches to understand the brain at the network level require such an atlas to assess connections between parcels and extract network properties. While no single functional atlas has emerged as the dominant atlas to date, there remains an underlying assumption that such an atlas exists. Using fMRI data from a highly sampled subject as well as two independent replication data sets, we demonstrate that functional parcellations based on fMRI connectivity data reconfigure substantially and in a meaningful manner, according to brain state. [ Code:
- Mehraveh Salehi, Amin Karbasi, Xilin Shen, Dustin Scheinost, and R. Todd Constable. "State-specific individualized functional networks form a predictive signature of brain state." bioRxiv (2018): 372110. (In revision)
There is extensive evidence that human brain functional organization is dynamic, varying within a subject as the brain switches between tasks demands. This functional organization also varies across subjects, even when they are all engaged in similar tasks. Currently, we lack a comprehensive model that unifies the two dimensions of variation (brain state and subject). Using fMRI data obtained across multiple task-evoked and rest conditions (which we operationally define as brain states) and across multiple subjects, we develop a state- and subject-specific functional network parcellation (the assignment of nodes to networks). Our parcellation approach provides a measure of how node-to-network assignment (NNA) changes across states and across subjects. We demonstrate that the brain's functional networks are not spatially fixed, but reconfigure with brain state. This reconfiguration is robust and reliable to such an extent that it can be used to predict brain state with accuracies up to 97%. [ Code:
[ Received the Best Poster Award at Yale BioImaging Sciences Retreat ]
- Mehraveh Salehi, Amin Karbasi, Xilin Shen, Dustin Scheinost, and R. Todd Constable. "An exemplar-based approach to individualized parcellation reveals the need for sex specific functional networks." NeuroImage 170 (2018): 54-67.
Recent work with functional connectivity data has led to significant progress in understanding the functional organization of the brain. While the majority of the literature has focused on group-level parcellation approaches, there is ample evidence that the brain varies in both structure and function across individuals. In this work, we introduce a parcellation technique that incorporates delineation of functional networks both at the individual- and group-level. The proposed technique deploys the notion of "submodularity" to jointly parcellate the cerebral cortex while establishing an inclusive correspondence between the individualized functional networks. Using this parcellation technique, we successfully establish a cross-validated predictive model that predicts individuals' sex, solely based on the parcellation schemes (i.e. the node-to-network assignment vectors). The sex prediction finding illustrates that individualized parcellation of functional networks can reveal subgroups in a population and suggests that the use of a global network parcellation may overlook fundamental differences in network organization. This is a particularly important point to consider in studies comparing patients versus controls or even patient subgroups. This approach to the individualized study of functional organization in the brain has many implications for both neuroscience and clinical applications. [ Code:
- Mehraveh Salehi, Dustin Scheinost, Monica D. Rosenberg, Emily S. Finn, Marvin M. Chun, and R. Todd Constable. "Network connectivity changes between task and resting-state fMRI data reveal flexibility and generalize attention prediction." (In revision)
While it is well known that patterns of functional brain connectivity differ between task performance and rest, it is unclear how changes in network properties across mental states relate to behavior. To quantify such state differences, we define a novel higher-order measure of brain connectivity based on the correlation of network nodal measures within and between periods of task performance and rest. Using this higher-order brain measure, we found that individuals with greater variability in their nodal characteristics during rest, but higher consistency during task, exhibit better task performance, suggesting a flexible brain reconfiguration. A fully cross-validated predictive model is developed that uses higher-order brain measures as features to predict task performance across individuals in three independent data sets. The tasks include a working memory task (n-back), a continuous performance task (gradCPT), and the Attention Network Task (ANT).
- Dustin Scheinost, Stephanie Noble, Corey Horien, Abigail S. Greene, Evelyn MR Lake, Mehraveh Salehi, Siyuan Gao et al. "Ten simple rules for predictive modeling of individual differences in neuroimaging." NeuroImage (2019).
Establishing brain-behavior associations that map brain organization to phenotypic measures and generalize to novel individuals remains a challenge in neuroimaging. Predictive modeling approaches that define and validate models with independent datasets offer a solution to this problem. While these methods can detect novel and generalizable brain-behavior associations, they can be daunting, which has limited their use by the wider connectivity community. Here, we offer practical advice and examples based on functional magnetic resonance imaging (fMRI) functional connectivity data for implementing these approaches. We hope these ten rules will increase the use of predictive models with neuroimaging data.
- Daniel Barron, Mehraveh Salehi, Michael Browning, Catherine Harmer, Todd Constable, and Eugene Duff. "S142. A Predictive Approach to Identify Clinical State, Emotional Valence and Pharmacologic Effect in Human Task-Based fMRI Data." Biological Psychiatry 83, no. 9 (2018): S403.
- Daniel Barron, Mehraveh Salehi, Michael Browning, Catherine Harmer, Todd Constable, and Eugene Duff. "Exploring the prediction of emotional valence and pharmacologic effect across fMRI studies of antidepressants." NeuroImage: Clinical 20 (2018): 407-414.
Clinically approved antidepressants modulate the brain's emotional valence circuits, suggesting that the response of these circuits could serve as a biomarker for screening candidate antidepressant drugs. However, it is necessary that these modulations can be reliably detected. Here, we apply a cross-validated predictive model to classify emotional valence and pharmacologic effect across eleven task-based fMRI datasets (n = 306) exploring the effect of antidepressant administration on emotional face processing.
- Mehraveh Salehi, Eser Aygun, Shibl Murad, Doina Precup. "A top-down, bottom-up attention model for reinforcement learning." In Multidisciplinary Conference on Reinforcement Learning and Decision Making (2019).
Reinforcement Learning (RL) agents typically have to process massive amounts of sensory data in order to execute a specific task. However, a large portion of the sensory input may not be directly related to the task at hand. Here, inspired by the human brain's attention system, we develop a novel augmented attention mechanism for RL agents, which enables them to adaptively select the most relevant information from the input. In order to evaluate the proposed algorithms, we use an attention-demanding grid-world environment and compare our model's performance against two other attentive agents and one naive agent. We demonstrate that our proposed augmented attention model outperforms other agents both in terms of scalability and ability to perform transfer learning. [Received the Student Travel Fellowship]
- Mehraveh Salehi, Amin Karbasi, Dustin Scheinost, and R. Todd Constable. "A submodular approach to create individualized parcellations of the human brain." In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 478-485. Springer, Cham, 2017.
Recent studies on functional neuroimaging (e.g. fMRI) attempt to model the brain as a network. A conventional functional connectivity approach for defining nodes in the network is grouping similar voxels together, a method known as functional parcellation. The majority of previous work on human brain parcellation employs a group-level analysis by collapsing data from the entire population. However, these methods ignore the large amount of inter-individual variability and uniqueness in connectivity. This is particularly relevant for patient studies or even developmental studies where a single functional atlas may not be appropriate for all individuals or conditions. To account for the individual differences, we developed an approach to individualized parcellation. The algorithm starts with an initial group-level parcellation and forms the individualized ones using a local exemplar-based submodular clustering method. The utility of individualized parcellations is further demonstrated through improvement in the accuracy of a predictive model that predicts IQ using functional connectome. [ Code:
] [ Received the Best Paper Award and the Travel Fellowship; Featured in Yale News ]
- Mohammad J. Salehi, Mehraveh Salehi, Hamidreza Bagheri, Babak H. Khalaj, Marcos Katz, and Pavel Loskot. "Exploiting Relative Consensus Techniques in Future Advanced Communications Networks in the Presence of Failures." In Proceedings of International Conference on Electrical Engineering and Applications, pp. 4-6. 2014.