cv

Postdoctoral Research Associate

Postdoctoral Research Associate, Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), GSU, GATech, Emory

In this role, I conduct advanced research in machine learning, focusing on the application of models to neuroimaging data. I design and evaluate machine learning experiments aimed at extracting meaningful insights from these datasets. My responsibilities include overseeing the entire data lifecycle, from collection and analysis to data management. I also collaborate closely with principal investigators to prepare, publish, and present research findings in scientific journals and at conferences. Additionally, I contribute to grant proposal development, working with both internal and external research teams to secure funding for innovative projects.

• Neuroimaging
• Machine Learning
• Deep Learning

Graduate Student Research Assistant

Graduate Student Research Assistant , Georgia Institute of Technology, Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), GSU, GATech, Emory

During my time at Georgia Tech, I conducted research at the intersection of machine learning and neuroimaging data. My work involved designing and evaluating machine learning experiments tailored to neuroimaging applications. I collaborated with principal investigators to prepare and publish scientific manuscripts, while also presenting research findings at conferences and academic venues.

• Neuroimaging
• Machine Learning
• Deep Learning

Graduate Student Research Assistant

Graduate Student Research Assistant , University of New Mexico

At UNM, I conducted research in machine learning, neuroimaging, and cybersecurity. My work involved designing and evaluating experiments to apply advanced machine learning techniques to these interdisciplinary domains, contributing to the development of innovative research methodologies.

PhD

Georgia Institute of Technology, Atlanta, GA USA

Electrical and Computer Engineering

PhD student

University of New Mexico, Albuquerque, NM USA

Computer Science

Master of Science

University of New Mexico, Albuquerque, NM USA

Computer Science

Bachelor

Islamic Azad University, Tehran, Iran

Computer Software Engineering

Paht-Based Differential Analysis in Near-Centenarians and Centenarians Brain Network, 46th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2024

IEEE

Investigating brain networks in dementia-free centenarians offers a unique opportunity to uncover distinctive characteristics contributing to the preservation of cognitive function into their eleventh decade of life. While graph theory techniques have been widely applied in aging studies, the predominant focus has been on graph metrics, with minimal attention given to the intricate information embedded in paths. A more comprehensive understanding of how these paths are disrupted could yield invaluable insights. In this study, we introduce a novel approach to estimating brain graphs for both younger and centenarian groups using a Gaussian graphical model. Employing graph theory, we pinpoint edges within the centenarian group graph that either initiate additional paths or exhibit absent paths compared to the younger group. Our results reveal two critical edges associated with disconnections within and between functional domains. Specifically, one edge pertains to the connection between the visual and cognitive control domains, while the other involves disconnection within the cognitive control domain. The identification of these edges not only advances our understanding of brain networks in centenarians but also sheds light on potential implications for cognitive function. By elucidating disruptions in specific pathways, this research contributes to a more nuanced comprehension of the neural mechanisms underlying successful cognitive aging. Such insights may pave the way for targeted interventions and therapeutic strategies to promote cognitive health in aging populations.

Label NOISE-Robust Ensemble Deep Multimodal Framework for NEUROIMAGING Data, 46th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2024

IEEE

Neuroimaging data have become widely studied in the context of identifying brain-based markers of mental illness. however, this work is hampered by the use of symptom and self-report assessments of diagnosis, as well as lack of clarity in the nosological categories. Hence, treating existing diagnostic categories as label noise problems might be beneficial. Ensemble methods and deep learning models were used in many applications and revealed remarkable findings dealing with label noise. In this study, we incorporated deep convolutional frameworks and bagging approaches for diagnostic classification, identifying potential biomarkers and mitigating the effects of label noise across mood and psychosis categories using structural and functional MRI data. We conducted repeated k-fold cross-validation techniques to train individual base models on different subsets of data and aggregate independent models for final classification. Moreover, we interpreted the results and identified class-specific relevant learned features contributing to a successful diagnosis and highlighted differences for different modalities. Overall, our proposed method shows improvement in classification performance.

Evaluation of boundaries between mood and psychosis disorder using dynamic functional network connectivity (dFNC) via deep learning classification, Human Brain Mapping, 2023

Wiley

Multimodal brain network analysis has the potential to provide insights into the mechanisms of brain disorders. Most previous studies have analyzed either unimodal brain graphs or focused on local/global graphic metrics with little consideration of details of disrupted paths in the patient group. As we show, the combination of multimodal brain graphs and disrupted path-based analysis can be highly illuminating to recognize path-based disease biomarkers. In this study, we first propose a way to estimate multimodal brain graphs using static functional network connectivity (sFNC) and gray matter features using a Gaussian graphical model of schizophrenia versus controls. Next, applying the graph theory approach we identify disconnectors or connectors in the patient group graph that create additional paths or cause absent paths compared to the control graph. Results showed several edges in the schizophrenia group graph that trigger missing or additional paths. Identified edges associated with these disrupted paths were identified both within and between dFNC and gray matter which highlights the importance of considering multimodal studies and moving beyond pairwise edges to provide a more comprehensive understanding of brain disorders.Clinical Relevance— We identified a path-based biomarker in schizophrenia, by imitating the structure of paths in a multimodal (sMIR+fMRI) brain graph of the control group. Identified cross-modal edges associated with disrupted paths were related to the middle temporal gyrus and cerebellar regions.

Network Differential in Gaussian Graphical Models from Multimodal Neuroimaging Data, 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2023

IEEE

Multimodal brain network analysis has the potential to provide insights into the mechanisms of brain disorders. Most previous studies have analyzed either unimodal brain graphs or focused on local/global graphic metrics with little consideration of details of disrupted paths in the patient group. As we show, the combination of multimodal brain graphs and disrupted path-based analysis can be highly illuminating to recognize path-based disease biomarkers. In this study, we first propose a way to estimate multimodal brain graphs using static functional network connectivity (sFNC) and gray matter features using a Gaussian graphical model of schizophrenia versus controls. Next, applying the graph theory approach we identify disconnectors or connectors in the patient group graph that create additional paths or cause absent paths compared to the control graph. Results showed several edges in the schizophrenia group graph that trigger missing or additional paths. Identified edges associated with these disrupted paths were identified both within and between dFNC and gray matter which highlights the importance of considering multimodal studies and moving beyond pairwise edges to provide a more comprehensive understanding of brain disorders.Clinical Relevance— We identified a path-based biomarker in schizophrenia, by imitating the structure of paths in a multimodal (sMIR+fMRI) brain graph of the control group. Identified cross-modal edges associated with disrupted paths were related to the middle temporal gyrus and cerebellar regions.

A Deep Learning Approach for Psychosis Spectrum Label Noise Detection from Multimodal Neuroimaging, Data 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2023

IEEE

Understanding the structural and functional mechanisms of the brain is challenging for mood and mental disorders. Many neuroimaging techniques are widely used to reveal hidden patterns from different brain imaging modalities. However, these findings are bounded by the limitation of each modality. In addition, the lack of validity of current psychosis nosology created more complications in understanding biomarkers. In this study, we introduced a deep convolutional framework to classify and identify label noises using structural and functional magnetic resonance imaging data. We applied our method to functional and structural MRI data from a schizophrenia dataset and evaluated the model’s performance in a cross-validated form. In addition, we introduced a noise criterion to distinguish a potentially noisy subject for each modality. Our results show the learned model using resting-state functional MRI data is more informative and has higher performance in comparison with structural MRI data. Lastly, based on the noise level, we investigated potential borderline subjects as possible subtypes and made a statistical analysis to distinguish differences between resting-state static functional connectivity features.Clinical Relevance— Results show schizophrenia patients are separable from the healthy control group based on their neuroimaging data and resting-state functional MRI data is more informative than structural MRI data and hence contains less label noise.