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//.
Current neuroimaging studies frequently use complex machine learning models to classify human fMRI data, distinguishing healthy and disordered brains, often to validate new methods or enhance prediction accuracy. Yet, where prediction accuracy is a concern, our results suggest that precision in prediction does not always require such sophistication. When a classifier as simple as logistic regression is applied to feature-engineered fMRI data, it can match or even outperform more sophisticated recent models. Classification of the raw time series fMRI data generally benefits from complex parameter-rich models. However, this complexity often pushes them into the class of black-box models. Yet, we found that a relatively simple model can consistently outperform much more complex classifiers in both accuracy and speed. This model applies the same multi-layer perceptron repeatedly across time and averages the results. Thus, the complexity and black-box nature of the parameter rich models, often perceived as a necessary trade-off for higher performance, do not invariably yield superior results on fMRI. Given the success of straightforward approaches, we challenge the merit of research that concentrates solely on complex model development driven by classification. Instead, we advocate for increased focus on designing models that prioritize the explainability of fMRI data or pursue applicable objectives beyond mere classification accuracy, unless they significantly outperform logistic regression or our proposed model. To validate our claim, we explore possible reasons for the superior performance of our straightforward model by examining the innate characteristics of fMRI time series data. Our findings suggest that the sequential information hidden in the temporal order may be far less important for the accurate fMRI classification than the stand-alone pieces of information scattered across the frames of the time series.
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 January 2026 in IEEE Transactions on Medical Imaging
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.
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.