Many efforts have been made to image the spatiotemporal electrical activity of the brain with the purpose of mapping its function and dysfunction as well as aiding the management of brain disorders. Here, we propose a non-conventional deep learning-based source imaging framework (DeepSIF) that provides robust and precise spatiotemporal estimates of underlying brain dynamics from noninvasive high-density electroencephalography (EEG) recordings. DeepSIF employs synthetic training data generated by biophysical models capable of modeling mesoscale brain dynamics. The rich characteristics of underlying brain sources are embedded in the realistic training data and implicitly learned by DeepSIF networks, avoiding complications associated with explicitly formulating and tuning priors in an optimization problem, as often is the case in conventional source imaging approaches. The performance of DeepSIF is evaluated by 1) a series of numerical experiments, 2) imaging sensory and cognitive brain responses in a total of 20 healthy subjects from three public datasets, and 3) rigorously validating DeepSIF's capability in identifying epileptogenic regions in a cohort of 20 drug-resistant epilepsy patients by comparing DeepSIF results with invasive measurements and surgical resection outcomes. DeepSIF demonstrates robust and excellent performance, producing results that are concordant with common neuroscience knowledge about sensory and cognitive information processing as well as clinical findings about the location and extent of the epileptogenic tissue and outperforming conventional source imaging methods. The DeepSIF method, as a data-driven imaging framework, enables efficient and effective high-resolution functional imaging of spatiotemporal brain dynamics, suggesting its wide applicability and value to neuroscience research and clinical applications.

High-frequency oscillations (HFOs) are a promising biomarker for localizing epileptogenic brain and guiding successful neurosurgery. However, the utility and translation of noninvasive HFOs, although highly desirable, is impeded by the difficulty in differentiating pathological HFOs from nonepileptiform high-frequency activities and localizing the epileptic tissue using noninvasive scalp recordings, which are typically contaminated with high noise levels. Here, we show that the consistent concurrence of HFOs with epileptiform spikes (pHFOs) provides a tractable means to identify pathological HFOs automatically, and this in turn demarks an epileptiform spike subgroup with higher epileptic relevance than the other spikes in a cohort of 25 temporal epilepsy patients (including a total of 2,967 interictal spikes and 1,477 HFO events). We found significant morphological distinctions of HFOs and spikes in the presence/absence of this concurrent status. We also demonstrated that the proposed pHFO source imaging enhanced localization of epileptogenic tissue by 162% (∼5.36 mm) for concordance with surgical resection and by 186% (∼12.48 mm) with seizure-onset zone determined by invasive studies, compared to conventional spike imaging, and demonstrated superior congruence with the surgical outcomes. Strikingly, the performance of spike imaging was selectively boosted by the presence of spikes with pHFOs, especially in patients with multitype spikes. Our findings suggest that concurrent HFOs and spikes reciprocally discriminate pathological activities, providing a translational tool for noninvasive presurgical diagnosis and postsurgical evaluation in vulnerable patients.

The androgen receptor (AR) is a key driver of prostate cancer (PC), even in the state of castration-resistant PC (CRPC) and frequently even after treatment with second-line hormonal therapies such as abiraterone and enzalutamide. The persistence of AR activity via both ligand-dependent and ligand-independent mechanisms (including constitutively active AR splice variants) highlights the unmet need for alternative approaches to block AR signaling in CRPC. We investigated the transcription factor GATA-binding protein 2 (GATA2) as a regulator of AR signaling and an actionable therapeutic target in PC. We demonstrate that GATA2 directly promotes expression of both full-length and splice-variant AR, resulting in a strong positive correlation between GATA2 and AR expression in both PC cell lines and patient specimens. Conversely, GATA2 expression is repressed by androgen and AR, suggesting a negative feedback regulatory loop that, upon androgen deprivation, derepresses GATA2 to contribute to AR overexpression in CRPC. Simultaneously, GATA2 is necessary for optimal transcriptional activity of both full-length and splice-variant AR. GATA2 colocalizes with AR and Forkhead box protein A1 on chromatin to enhance recruitment of steroid receptor coactivators and formation of the transcriptional holocomplex. In agreement with these important functions, high GATA2 expression and transcriptional activity predicted worse clinical outcome in PC patients. A GATA2 small molecule inhibitor suppressed the expression and transcriptional function of both full-length and splice-variant AR and exerted potent anticancer activity against PC cell lines. We propose pharmacological inhibition of GATA2 as a first-in-field approach to target AR expression and function and improve outcomes in CRPC.