An Overview of ICA/BSS-Based Application to Alzheimer's Brain Signal Processing

Neuroimaging techniques, gene therapy, and gut microbiota: frontier advances and integrated applications in Alzheimer's Disease research

Alzheimer's Disease (AD) is a neurodegenerative disorder marked by cognitive decline, for which effective treatments remain elusive due to complex pathogenesis. Recent advances in neuroimaging, gene therapy, and gut microbiota research offer new insights and potential intervention strategies. Neuroimaging enables early detection and staging of AD through visualization of biomarkers, aiding diagnosis and tracking of disease progression. Gene therapy presents a promising approach for modifying AD-related genetic expressions, targeting amyloid and tau pathology, and potentially repairing neuronal damage. Furthermore, emerging evidence suggests that the gut microbiota influences AD pathology through the gut-brain axis, impacting inflammation, immune response, and amyloid metabolism. However, each of these technologies faces significant challenges, including concerns about safety, efficacy, and ethical considerations. This article reviews the applications, advantages, and limitations of neuroimaging, gene therapy, and gut microbiota research in AD, with a particular focus on their combined potential for early diagnosis, mechanistic insights, and therapeutic interventions. We propose an integrated approach that leverages these tools to provide a multi-dimensional framework for advancing AD diagnosis, treatment, and prevention.

Exploring the frontier: Transformer-based models in EEG signal analysis for brain-computer interfaces

This review systematically explores the application of transformer-based models in EEG signal processing and brain-computer interface (BCI) development, with a distinct focus on ensuring methodological rigour and adhering to empirical validations within the existing literature. By examining various transformer architectures, such as the Temporal Spatial Transformer Network (TSTN) and EEG Conformer, this review delineates their capabilities in mitigating challenges intrinsic to EEG data, such as noise and artifacts, and their subsequent implications on decoding and classification accuracies across disparate mental tasks. The analytical scope extends to a meticulous examination of attention mechanisms within transformer models, delineating their role in illuminating critical temporal and spatial EEG features and facilitating interpretability in model decision-making processes. The discourse additionally encapsulates emerging works that substantiate the efficacy of transformer models in noise reduction of EEG signals and diversifying applications beyond the conventional motor imagery paradigm. Furthermore, this review elucidates evident gaps and propounds exploratory avenues in the applications of pre-trained transformers in EEG analysis and the potential expansion into real-time and multi-task BCI applications. Collectively, this review distils extant knowledge, navigates through the empirical findings, and puts forward a structured synthesis, thereby serving as a conduit for informed future research endeavours in transformer-enhanced, EEG-based BCI systems.

The Value of Diffuse Splenic and Hepatic 18F-FDG Uptake on PET/CT in Diagnosing Patients with Anemia

Objective

Anemia is a disease with a negative impact on the progression and prognosis of tumor diseases and usually diagnosed by blood tests. Imaging examination has been used as an alternative method to diagnose anemia in addition to blood tests for patients who cannot tolerate blood draw (such as those with severe coagulopathy). The purpose of this study was to investigate the role of diffuse splenic and hepatic ¹⁸F-FDG uptake on PET/CT in anemia, by analyzing the correlation between the hemoglobin level and diffuse splenic and hepatic as well as marrow ¹⁸F-FDG uptakes in patients who underwent PET/CT.

Materials and Methods

Forty four patients who underwent a peripheral blood examination within 2 days of a ¹⁸F-FDG-PET/CT in our hospital from March 2020 to March 2021 were included. The standardized uptake value (SUV) of the spleen, liver, and marrow were measured, including the maximum value (SUVmax) and the mean value (SUVmean), and the CT value (CTV) of the left ventricular (LV) cavity was measured, including the maximum value (CTVmax) and the mean value (CTVmean). The relation between these measurements and the blood hemoglobin level were analyzed.

Results

Our analysis revealed that the hemoglobin level was negatively correlated with the SUVmax of the spleen (P ≤ 0.01, R = −0.385), SUVmean of the spleen (P ≤ 0.01, R = −0.395), SUVmax of the liver (P ≤ 0.05, R = −0.365), and SUVmean of the liver (P ≤ 0.05, R = −0.315). The hemoglobin level was positively correlated with CTVmax of the LV cavity (P ≤ 0.05, R = 0.33) and CTVmean of the LV cavity (P ≤ 0.05, R = 0.382), while no statistically significant correlation between the hemoglobin level and the SUV of marrow was observed (P > 0.05).

Conclusion

Our study revealed a negative correlation between the hemoglobin level and spleen SUV as well as liver SUV, and a positive correlation between the hemoglobin level and CTV of the LV cavity. These findings may provide potential indictors for the imaging diagnosis of anemia, which has important clinical significance in certain clinical scenarios including the evaluation of anemia status in patients who cannot tolerate blood draws and retrospective clinical studies based on patient imaging data.