Brain Informatics最新文献

This study focuses on classifying multiple sessions of loving kindness meditation (LKM) and non-meditation electroencephalography (EEG) data. This novel study focuses on using multiple sessions of EEG data from a single individual to train a machine learning pipeline, and then using a new session data from the same individual for the classification. Here, two meditation techniques, LKM-Self and LKM-Others were compared with non-meditation EEG data for 12 participants. Among many tested, three BCI pipelines we built produced promising results, successfully detecting features in meditation/ non-meditation EEG data. While testing different feature extraction algorithms, a common neural network structure was used as the classification algorithm to compare the performance of the feature extraction algorithms. For two of those pipelines, Common Spatial Patterns (CSP) and Short Time Fourier Transform (STFT) were successfully used as feature extraction algorithms where both these algorithms are significantly new for meditation EEG. As a novel concept, the third BCI pipeline used a feature extraction algorithm that fused the features of CSP and STFT, achieving the highest classification accuracies among all tested pipelines. Analyses were conducted using EEG data of 3, 4 or 5 sessions, totaling 3960 tests on the entire dataset. At the end of the study, when considering all the tests, the overall classification accuracy using SCP alone was 67.1%, and it was 67.8% for STFT alone. The algorithm combining the features of CSP and STFT achieved an overall classification accuracy of 72.9% which is more than 5% higher than the other two pipelines. At the same time, the highest mean classification accuracy for the 12 participants was achieved using the pipeline with the combination of CSP STFT algorithm, reaching 75.5% for LKM-Self/ non-meditation for the case of 5 sessions of data. Additionally, the highest individual classification accuracy of 88.9% was obtained by the participant no. 14. Furthermore, the results showed that the classification accuracies for all three pipelines increased with the number of training sessions increased from 2 to 3 and then to 4. The study was successful in classifying a new session of EEG meditation/ non-meditation data after training machine learning algorithms using a different set of session data, and this achievement will be beneficial in the development of algorithms that support meditation.

Cognitive resilience (CR) describes the phenomenon of individuals evading cognitive decline despite prominent Alzheimer's disease neuropathology. Operationalization and measurement of this latent construct is non-trivial as it cannot be directly observed. The residual approach has been widely applied to estimate CR, where the degree of resilience is estimated through a linear model's residuals. We demonstrate that this approach makes specific, uncontrollable assumptions and likely leads to biased and erroneous resilience estimates. This is especially true when information about CR is contained in the data the linear model was fitted to, either through inclusion of CR-associated variables or due to correlation. We propose an alternative strategy which overcomes the standard approach's limitations using machine learning principles. Our proposed approach makes fewer assumptions about the data and CR and achieves better estimation accuracy on simulated ground-truth data.

Calcium plays an important role in regulating various neuronal activities in human brains. Investigating the dynamics of the calcium level in neurons is essential not just for understanding the pathophysiology of neuropsychiatric disorders but also as a quantitative gauge to evaluate the influence of drugs on neuron activities. Accessing human brain tissue to study neuron activities has historically been challenging due to ethical concerns. However, a significant breakthrough in the field has emerged with the advent of utilizing patient-derived human induced pluripotent stem cells (iPSCs) to culture neurons and develop brain organoids. This innovative approach provides a promising modeling system to overcome these critical obstacles. Many robust calcium imaging analysis tools have been developed for calcium activity analysis. However, most of the tools are designed for calcium signal detection only. There are limited choices for in-depth downstream applications, particularly in discerning differences between patient and normal calcium dynamics and their responses to drug treatment obtained from human iPSC-based models. Moreover, end-user researchers usually face a considerable challenge in mastering the entire analysis procedure and obtaining critical outputs due to the steep learning curve associated with these available tools. Therefore, we developed CalciumZero, a user-friendly toolbox to satisfy the unmet needs in calcium activity studies in human iPSC-based 3D-organoid/neurosphere models. CalciumZero includes a graphical user interface (GUI), which provides end-user iconic visualization and smooth adjustments on parameter tuning. It streamlines the entire analysis process, offering full automation with just one click after parameter optimization. In addition, it includes supplementary features to statistically evaluate the impact on disease etiology and the detection of drug candidate effects on calcium activities. These evaluations will enhance the analysis of imaging data obtained from patient iPSC-derived brain organoid/neurosphere models, providing a more comprehensive understanding of the results.

A digital twin is a virtual model of a real-world system that updates in real-time. In healthcare, digital twins are gaining popularity for monitoring activities like diet, physical activity, and sleep. However, their application in predicting serious conditions such as heart attacks, brain strokes and cancers remains under investigation, with current research showing limited accuracy in such predictions. Moreover, concerns around data security and privacy continue to challenge the widespread adoption of these models. To address these challenges, we developed a secure, machine learning powered digital twin application with three main objectives enhancing prediction accuracy, strengthening security, and ensuring scalability. The application achieved an accuracy of 98.28% for brain stroke prediction on the selected dataset. The data security was enhanced by integrating consortium blockchain technology with machine learning. The results show that the application is tamper-proof and is capable of detecting and automatically correcting backend data anomalies to maintain robust data protection. The application can be extended to monitor other pathologies such as heart attacks, cancers, osteoporosis, and epilepsy with minimal configuration changes.

Brain age, a biomarker reflecting brain health relative to chronological age, is increasingly used in neuroimaging to detect early signs of neurodegenerative diseases and support personalized treatment plans. Two primary approaches for brain age prediction have emerged: morphometric feature extraction from MRI scans and deep learning (DL) applied to raw MRI data. However, a systematic comparison of these methods regarding performance, interpretability, and clinical utility has been limited. In this study, we present a comparative evaluation of two pipelines: one using morphometric features from FreeSurfer and the other employing 3D convolutional neural networks (CNNs). Using a multisite neuroimaging dataset, we assessed both model performance and the interpretability of predictions through eXplainable Artificial Intelligence (XAI) methods, applying SHAP to the feature-based pipeline and Grad-CAM and DeepSHAP to the CNN-based pipeline. Our results show comparable performance between the two pipelines in Leave-One-Site-Out (LOSO) validation, achieving state-of-the-art performance on the independent test set ( $MAE=3.21$ with DNN and morphometric features and $MAE=3.08$ with a DenseNet-121 architecture). SHAP provided the most consistent and interpretable results, while DeepSHAP exhibited greater variability. Further work is needed to assess the clinical utility of Grad-CAM. This study addresses a critical gap by systematically comparing the interpretability of multiple XAI methods across distinct brain age prediction pipelines. Our findings underscore the importance of integrating XAI into clinical practice, offering insights into how XAI outputs vary and their potential utility for clinicians.

High-throughput mesoscopic optical imaging technology has tremendously boosted the efficiency of procuring massive mesoscopic datasets from mouse brains. Constrained by the imaging field of view, the image strips obtained by such technologies typically require further processing, such as cross-sectional stitching, artifact removal, and signal area cropping, to meet the requirements of subsequent analyse. However, obtaining a batch of raw array mouse brain data at a resolution of $0.65\times 0.65\times 3\mu {\text{m}}^3$ can reach 220TB, and the cropping of the outer contour areas in the disjointed processing still relies on manual visual observation, which consumes substantial computational resources and labor costs. In this paper, we design an efficient deep differential guided filtering module (DDGF) by fusing multi-scale iterative differential guided filtering with deep learning, which effectively refines image details while mitigating background noise. Subsequently, by amalgamating DDGF with deep learning network, we propose a lightweight deep differential guided filtering segmentation network (DDGF-SegNet), which demonstrates robust performance on our dataset, achieving Dice of 0.92, Precision of 0.98, Recall of 0.91, and Jaccard index of 0.86. Building on the segmentation, we utilize connectivity analysis for ascertaining three-dimensional spatial orientation of each brain within the array. Furthermore, we streamline the entire processing workflow by developing an automated pipeline optimized for cluster-based message passing interface(MPI) parallel computation, which reduces the processing time for a mouse brain dataset to a mere 1.1 h, enhancing manual efficiency by 25 times and overall data processing efficiency by 2.4 times, paving the way for enhancing the efficiency of big data processing and parsing for high-throughput mesoscopic optical imaging techniques.

Affective computing is a key research area in computer science, neuroscience, and psychology, aimed at enabling computers to recognize, understand, and respond to human emotional states. As the demand for affective computing technology grows, emotion recognition methods based on physiological signals have become research hotspots. Among these, electroencephalogram (EEG) signals, which reflect brain activity, are highly promising. However, due to individual physiological and anatomical differences, EEG signals introduce noise, reducing emotion recognition performance. Additionally, the synchronous collection of multimodal data in practical applications requires high equipment and environmental standards, limiting the practical use of EEG signals. To address these issues, this study proposes the Emotion Preceptor, a cross-subject emotion recognition model based on unimodal EEG signals. This model introduces a Static Spatial Adapter to integrate spatial information in EEG signals, reducing individual differences and extracting robust encoding information. The Temporal Causal Network then leverages temporal information to extract beneficial features for emotion recognition, achieving precise recognition based on unimodal EEG signals. Extensive experiments on the SEED and SEED-V datasets demonstrate the superior performance of the Emotion Preceptor and validate the effectiveness of the new data processing method that combines DE features in a temporal sequence. Additionally, we analyzed the model's data flow and encoding methods from a biological interpretability perspective and validated it with neuroscience research related to emotion generation and regulation, promoting further development in emotion recognition research based on EEG signals.

EEG-based emotion recognition uses high-level information from neural activities to predict emotional responses in subjects. However, this information is sparsely distributed in frequency, time, and spatial domains and varied across subjects. To address these challenges in emotion recognition, we propose a novel neural network model named Temporal-Spectral Graph Convolutional Network (TSGCN). To capture high-level information distributed in time, spatial, and frequency domains, TSGCN considers both neural oscillation changes in different time windows and topological structures between different brain regions. Specifically, a Minimum Category Confusion (MCC) loss is used in TSGCN to reduce the inconsistencies between subjective ratings and predefined labels. In addition, to improve the generalization of TSGCN on cross-subject variation, we propose Deep and Shallow feature Dynamic Adversarial Learning (DSDAL) to calculate the distance between the source domain and the target domain. Extensive experiments were conducted on public datasets to demonstrate that TSGCN outperforms state-of-the-art methods in EEG-based emotion recognition. Ablation studies show that the mixed neural networks and our proposed methods in TSGCN significantly contribute to its high performance and robustness. Detailed investigations further provide the effectiveness of TSGCN in addressing the challenges in emotion recognition.

The mental health of students in higher education has been a growing concern, with increasing evidence pointing to heightened risks of developing mental health condition. This research aims to explore whether day-long heart rate sequences, collected continuously through Apple Watch in an open environment without restrictions on daily routines, can effectively indicate mental states, particularly stress for university students. While heart rate (HR) is commonly used to monitor physical activity or responses to isolated stimuli in a controlled setting, such as stress-inducing tests, this study addresses the gap by analyzing heart rate fluctuations throughout a day, examining their potential to gauge overall stress levels in a more comprehensive and real-world context. The data for this research was collected at a public university in the UK. Using signal processing, both original heart rate sequences and their representations, via Fourier transformation and wavelet analysis, have been modeled using advanced machine learning algorithms. Having achieving statistically significant results over the baseline, this provides a understanding of how heart rate sequences alone may be used to characterize mental states through signal processing and machine learning, with the system poised for further testing as the ongoing data collection continues.

Accurate monitoring of the depth of anesthesia (DoA) is essential for ensuring patient safety and effective anesthesia management. Existing methods, such as the Bispectral Index (BIS), are limited in real-time accuracy and robustness. Current methods have problems in generalizability across diverse patient datasets and are sensitive to artifacts, making it difficult to provide reliable DoA assessments in real time. This study proposes a novel method for DoA monitoring using EEG signals, focusing on accuracy, robustness, and real-time application. EEG signals were pre-processed using wavelet denoising and discrete wavelet transform (DWT). Features such as Permutation Lempel-Ziv Complexity (PLZC) and Power Spectral Density (PSD) were extracted. A random forest regression model was employed to estimate anesthetic states, and an unsupervised learning method using the Hurst exponent algorithm and hierarchical clustering was introduced to detect transitions between anesthesia states. The method was tested on two independent datasets (UniSQ and VitalDB), achieving an average Pearson correlation coefficient of 0.86 and 0.82, respectively. For the combined dataset, the model demonstrated an R-squared value of 0.70, a RMSE of 6.31, a MAE of 8.38, and a Pearson correlation of 0.84, showcasing its robustness and generalizability. This approach offers a more accurate and reliable real-time DoA monitoring tool that could significantly improve patient safety and anesthesia management, especially in diverse clinical environments.