Pavel Popov
Research Subjects
Pavel Popov has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Sergey M. Plis
Department of Computer Science, Georgia State University, Atlanta, GA 30302, USA
3 shared publications - Vince D. Calhoun
Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA, USA
3 shared publications - Ansar R. Safin
National Research University "Moscow Power Engineering Institute"; Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences
2 shared publications S.A. Nikitov
Kotel’nikov Institute of Radio-Engineering and Electronics of RAS, Moscow 125009, Russia
2 shared publicationsA. Kirilyuk
Kotel’nikov Institute of Radio-Engineering and Electronics of RAS, Moscow 125009, Russia
1 shared publicationA. Slavin
Department of Physics, Oakland University, Rochester, Michigan 48309-4479, USA
1 shared publication
Latest Publications
- Open Access
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (11) , 5468-5484
Message in a Bottleneck: Interpretable Deep Learning for Dynamic Effective Brain Connectivity
Deep learning (DL) approaches find increasingly more applications in medical imaging analysis, where they excel at predictive tasks such as diagnosis classification, but often offer little insight on the underlying mechanisms governing complex systems, a key goal of scientific inquiry. One way to bridge this gap is to design DL architectures for modeling the underlying system reflected in imaging data, which can give insights into the system through the analysis of fitted models. In this spirit, we present a novel approach for deep extraction of causally informed features via restricted architecture (DECIFRA), designed for multivariate time series modeling. DECIFRA introduces an interpretable bottleneck in its computation flow, where dynamically generated transition matrices exclusively model the directed influences between channels over time. These matrices function as both the model's internal computational mechanism and its primary, interpretable output that gives insights into the cross-channel interactions. To validate our method, we apply it to the challenging task of learning dynamic brain connectivity from functional magnetic resonance imaging (fMRI) data. We demonstrate that DECIFRA learns stable, reproducible connectivity patterns that are discriminative for group-level analysis. Moreover, these learned dynamics can be fine-tuned for specific classification tasks, improving predictive performance while retaining interpretability. Our findings show that DECIFRA captures functionally grounded brain connectivity patterns, with certain dynamics associated with age or schizophrenia classification tasks and others consistently preserved across tasks.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (11) , 5468-5484
Open AccessMessage in a Bottleneck: Interpretable Deep Learning for Dynamic Effective Brain Connectivity
Deep learning (DL) approaches find increasingly more applications in medical imaging analysis, where they excel at predictive tasks such as diagnosis classification, but often offer little insight on the underlying mechanisms governing complex systems, a key goal of scientific inquiry. One way to bridge this gap is to design DL architectures for modeling the underlying system reflected in imaging data, which can give insights into the system through the analysis of fitted models. In this spirit, we present a novel approach for deep extraction of causally informed features via restricted architecture (DECIFRA), designed for multivariate time series modeling. DECIFRA introduces an interpretable bottleneck in its computation flow, where dynamically generated transition matrices exclusively model the directed influences between channels over time. These matrices function as both the model's internal computational mechanism and its primary, interpretable output that gives insights into the cross-channel interactions. To validate our method, we apply it to the challenging task of learning dynamic brain connectivity from functional magnetic resonance imaging (fMRI) data. We demonstrate that DECIFRA learns stable, reproducible connectivity patterns that are discriminative for group-level analysis. Moreover, these learned dynamics can be fine-tuned for specific classification tasks, improving predictive performance while retaining interpretability. Our findings show that DECIFRA captures functionally grounded brain connectivity patterns, with certain dynamics associated with age or schizophrenia classification tasks and others consistently preserved across tasks.
- Open Access
- 1 September 2025
- Published by MDPI AG in Brain Sciences
- Vol. 15 (9) , 954
Interpretable Disorder Signatures: Probing Neural Latent Spaces for Schizophrenia, Alzheimer’s, and Autism Stratification
Objective: This study aims to develop and validate an interpretable deep learning framework that leverages self-supervised time reversal (TR) pretraining to identify consistent, biologically plausible functional network biomarkers across multiple neurological and psychiatric disorders. Methods: We pretrained a hierarchical LSTM model using a TR pretext task on the Human Connectome Project (HCP) dataset. The pretrained weights were transferred to downstream classification tasks on five clinical datasets (FBIRN, BSNIP, ADNI, OASIS, and ABIDE) spanning schizophrenia, Alzheimer’s disease, and autism spectrum disorder. After fine-tuning, we extracted latent features and employed a logistic regression probing analysis to decode class-specific functional network contributions. Models trained from scratch without pretraining served as a baseline. Statistical tests (one-sample and two-sample t-tests) were performed on the latent features to assess their discriminative power and consistency. Results: TR pretraining consistently improved classification performance in four out of five datasets, with AUC gains of up to 5.3%, particularly in data-scarce settings. Probing analyses revealed biologically meaningful and consistent patterns: schizophrenia was associated with reduced auditory network activity, Alzheimer’s with disrupted default mode and cerebellar networks, and autism with sensorimotor anomalies. TR-pretrained models produced more statistically significant latent features and demonstrated higher consistency across datasets (e.g., Pearson correlation = 0.9003 for schizophrenia probing vs. −0.67 for non-pretrained). In contrast, non-pretrained models showed unstable performance and inconsistent feature importance. Conclusions: Time Reversal pretraining enhances both the performance and interpretability of deep learning models for fMRI classification. By enabling more stable and biologically plausible representations, TR pretraining supports clinically relevant insights into disorder-specific network disruptions. This study demonstrates the utility of interpretable self-supervised models in neuroimaging, offering a promising step toward transparent and trustworthy AI applications in psychiatry.
- 1 September 2025
- Published by MDPI AG in Brain Sciences
- Vol. 15 (9) , 954
Open AccessInterpretable Disorder Signatures: Probing Neural Latent Spaces for Schizophrenia, Alzheimer’s, and Autism Stratification
Objective: This study aims to develop and validate an interpretable deep learning framework that leverages self-supervised time reversal (TR) pretraining to identify consistent, biologically plausible functional network biomarkers across multiple neurological and psychiatric disorders. Methods: We pretrained a hierarchical LSTM model using a TR pretext task on the Human Connectome Project (HCP) dataset. The pretrained weights were transferred to downstream classification tasks on five clinical datasets (FBIRN, BSNIP, ADNI, OASIS, and ABIDE) spanning schizophrenia, Alzheimer’s disease, and autism spectrum disorder. After fine-tuning, we extracted latent features and employed a logistic regression probing analysis to decode class-specific functional network contributions. Models trained from scratch without pretraining served as a baseline. Statistical tests (one-sample and two-sample t-tests) were performed on the latent features to assess their discriminative power and consistency. Results: TR pretraining consistently improved classification performance in four out of five datasets, with AUC gains of up to 5.3%, particularly in data-scarce settings. Probing analyses revealed biologically meaningful and consistent patterns: schizophrenia was associated with reduced auditory network activity, Alzheimer’s with disrupted default mode and cerebellar networks, and autism with sensorimotor anomalies. TR-pretrained models produced more statistically significant latent features and demonstrated higher consistency across datasets (e.g., Pearson correlation = 0.9003 for schizophrenia probing vs. −0.67 for non-pretrained). In contrast, non-pretrained models showed unstable performance and inconsistent feature importance. Conclusions: Time Reversal pretraining enhances both the performance and interpretability of deep learning models for fMRI classification. By enabling more stable and biologically plausible representations, TR pretraining supports clinically relevant insights into disorder-specific network disruptions. This study demonstrates the utility of interpretable self-supervised models in neuroimaging, offering a promising step toward transparent and trustworthy AI applications in psychiatry.
- Open Access
- 6 November 2024
- Published by Elsevier in NeuroImage
- Vol. 303, 120909
A simple but tough-to-beat baseline for fMRI time-series classification
- 6 November 2024
- Published by Elsevier in NeuroImage
- Vol. 303, 120909
Open AccessA simple but tough-to-beat baseline for fMRI time-series classification
- 30 April 2020
- Published by American Physical Society (APS) in Physical Review Applied
- Vol. 13 (4) , 044080
Voltage-Controlled Anisotropy and Current-Induced Magnetization Dynamics in Antiferromagnetic-Piezoelectric Layered Heterostructures
It is shown theoretically that in a layered heterostructure comprising piezoelectric, dielectric antiferromagnetic crystal, and heavy metal (PZ/AFM/HM), it is possible to control the anisotropy of the AFM layer by applying a dc voltage across the PZ layer. In particular, we show that by varying the dc voltage across the heterostructure and/or the dc current in the HM, it is possible to vary the frequency of the antiferromagnetic resonance of the AFM in a passive (subcritical) regime and, also, to reduce the threshold of the current-induced terahertz-frequency generation. Our analysis also shows that, unfortunately, the voltage-induced reduction of the generation threshold leads to the proportional reduction of the amplitude of the terahertz-frequency signal generated in the active (supercritical) regime. The general results are illustrated by a calculation of the characteristics of experimentally realizable PZT-5H//.- 30 April 2020
- Published by American Physical Society (APS) in Physical Review Applied
- Vol. 13 (4) , 044080
Voltage-Controlled Anisotropy and Current-Induced Magnetization Dynamics in Antiferromagnetic-Piezoelectric Layered Heterostructures
It is shown theoretically that in a layered heterostructure comprising piezoelectric, dielectric antiferromagnetic crystal, and heavy metal (PZ/AFM/HM), it is possible to control the anisotropy of the AFM layer by applying a dc voltage across the PZ layer. In particular, we show that by varying the dc voltage across the heterostructure and/or the dc current in the HM, it is possible to vary the frequency of the antiferromagnetic resonance of the AFM in a passive (subcritical) regime and, also, to reduce the threshold of the current-induced terahertz-frequency generation. Our analysis also shows that, unfortunately, the voltage-induced reduction of the generation threshold leads to the proportional reduction of the amplitude of the terahertz-frequency signal generated in the active (supercritical) regime. The general results are illustrated by a calculation of the characteristics of experimentally realizable PZT-5H//.- 1 January 2020
- Published by Ioffe Institute Russian Academy of Sciences in Журнал технической физики
- Vol. 46 (20) , 23
Синтезатор дискретной сетки частот на основе антиферромагнитного спинтронного осциллятора
Dynamics of an antiferromagnetic spintronic oscillator phase-locked loop-based frequency synthesizer, which generates terahertz oscillations in a wide frequency range under the influence of direct current, was investigated. By the method of slowly varying amplitudes, a dependence of the gain on the ring of the phase locked loop on the difference in frequencies of synchronized oscillations at different division coefficients in the feedback circuit is obtained. It is shown that as the division coefficient increases, the band of synchronized oscillations decreases with unchanged parameters of the antiferromagnet-based spintronic oscillator.
- 1 January 2020
- Published by Ioffe Institute Russian Academy of Sciences in Журнал технической физики
- Vol. 46 (20) , 23
Синтезатор дискретной сетки частот на основе антиферромагнитного спинтронного осциллятора
Dynamics of an antiferromagnetic spintronic oscillator phase-locked loop-based frequency synthesizer, which generates terahertz oscillations in a wide frequency range under the influence of direct current, was investigated. By the method of slowly varying amplitudes, a dependence of the gain on the ring of the phase locked loop on the difference in frequencies of synchronized oscillations at different division coefficients in the feedback circuit is obtained. It is shown that as the division coefficient increases, the band of synchronized oscillations decreases with unchanged parameters of the antiferromagnet-based spintronic oscillator.
- 4 December 2018
- Published by Elsevier in Journal of Magnetism and Magnetic Materials
- Vol. 476, 423-427
Spin wave propagation in three-dimensional magnonic crystals and coupled structures
- 4 December 2018
- Published by Elsevier in Journal of Magnetism and Magnetic Materials
- Vol. 476, 423-427
Spin wave propagation in three-dimensional magnonic crystals and coupled structures