IEEE Journal of Biomedical and Health Informatics最新文献

Brain network analysis plays a crucial role in identifying distinctive patterns associated with neurological disorders. Functional magnetic resonance imaging (fMRI) enables the construction of brain networks by analyzing correlations in blood-oxygen-level-dependent (BOLD) signals across different brain regions, known as regions of interest (ROIs). These networks are typically constructed using atlases that parcellate the brain based on various hypotheses of functional and anatomical divisions. However, there is no standard atlas for brain network classification, leading to limitations in detecting abnormalities in disorders. Recent methods leveraging multiple atlases fail to ensure consistency across atlases and lack effective ROI-level information exchange, limiting their efficacy. To address these challenges, we propose the Atlas-Integrated Distillation and Fusion network (AIDFusion), a novel framework designed to enhance brain network classification using fMRI data. AIDFusion introduces a disentangle Transformer to filter out inconsistent atlas-specific information and distill meaningful cross-atlas connections. Additionally, it enforces subject- and population-level consistency constraints to improve cross-atlas coherence. To further enhance feature integration, AIDFusion incorporates an inter-atlas message-passing mechanism that facilitates the fusion of complementary information across brain regions. We evaluate AIDFusion on four resting-state fMRI datasets encompassing different neurological disorders. Experimental results demonstrate its superior classification performance and computational efficiency compared to state-of-the-art methods. Furthermore, a case study highlights AIDFusion's ability to extract interpretable patterns that align with established neuroscience findings, reinforcing its potential as a robust tool for multi-atlas brain network analysis.

Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.

Medical time series data are indispensable in healthcare, providing critical insights for disease diagnosis, treatment planning, and patient management. The exponential growth in data complexity, driven by advanced sensor technologies, has presented challenges related to data labeling. Self-supervised learning (SSL) has emerged as a transformative approach to address these challenges, eliminating the need for extensive human annotation. In this study, we introduce a novel framework for Medical Time Series Representation Learning, known as MTS-LOF. MTS-LOF leverages the strengths of Joint-Embedding SSL and Masked Autoencoder (MAE) methods, offering a unique approach to representation learning for medical time series data. By combining these techniques, MTS-LOF enhances the potential of healthcare applications by providing more sophisticated, context-rich representations. Additionally, MTS-LOF employs a multi-masking strategy to facilitate occlusion-invariant feature learning. This approach allows the model to create multiple views of the data by masking portions of it. By minimizing the discrepancy between the representations of these masked patches and the fully visible patches, MTS-LOF learns to capture rich contextual information within medical time series datasets. The results of experiments conducted on diverse medical time series datasets demonstrate the superiority of MTS-LOF over other methods. These findings hold promise for significantly enhancing healthcare applications by improving representation learning. Furthermore, our work delves into the integration of Joint-Embedding SSL and MAE techniques, shedding light on the intricate interplay between temporal and structural dependencies in healthcare data. This understanding is crucial, as it allows us to grasp the complexities of healthcare data analysis.

Deep learning associated with neurological signals is poised to drive major advancements in diverse fields such as medical diagnostics, neurorehabilitation, and brain-computer interfaces. The challenge in harnessing the full potential of these signals lies in the dependency on extensive, high-quality annotated data, which is often scarce and expensive to acquire, requiring specialized infrastructure and domain expertise. To address the appetite for data in deep learning, we present Neuro-BERT, a self-supervised pre-training framework of neurological signals based on masked autoencoding in the Fourier domain. The intuition behind our approach is simple: frequency and phase distribution of neurological signals can reveal intricate neurological activities. We propose a novel pre-training task dubbed Fourier Inversion Prediction (FIP), which randomly masks out a portion of the input signal and then predicts the missing information using the Fourier inversion theorem. Pre-trained models can be potentially used for various downstream tasks such as sleep stage classification and gesture recognition. Unlike contrastive-based methods, which strongly rely on carefully hand-crafted augmentations and siamese structure, our approach works reasonably well with a simple transformer encoder with no augmentation requirements. By evaluating our method on several benchmark datasets, we show that Neuro-BERT improves downstream neurological-related tasks by a large margin.

The rapid explosion of medical data, exarcebated by the demands of smart healthcare, poses significant challenges for authentication and integrity verification. Moreover, the surge in cybercrime targeting healthcare data jeopardizes patient privacy, compromising both trust and diagnostic reliability. To address these concerns, we propose a robust healthcare system that integrates a kidney stone segmentation framework with a watermarking protocol tailored for Internet of Medical Things (IoMT) applications. Drawing upon patient information and biometrics, chaotic keys are generated for obfuscation and randomization, along with the watermark for integrity verification and authentication. The watermark is imperceptibly embedded into the obfuscated medical image using Singular Value Decomposition (SVD) and adaptive quantization, followed by randomization. Upon reception, successful watermark extraction and verification ensure secure access to unaltered medical data, enabling precise segmentation. To facilitate this, a ResNeXt-50 inspired encoder and attention-guided decoder are introduced within the U-Net architecture to enhance comprehensive feature learning. The effectiveness and practicality of the proposed system have been evaluated through comprehensive experiments on kidney CT scans. Comparative analysis with state-of-the-art techniques highlights its superior performance.

Breakthroughs in sequencing technologies led to an exponential growth of genomic data, providing novel biological insights and therapeutic applications. However, analyzing large amounts of sensitive data raises key data privacy concerns, specifically when the information is outsourced to untrusted third-party infrastructures for data storage and processing (e.g., cloud computing). We introduce Gyosa, a secure and privacy-preserving distributed genomic analysis solution. By leveraging trusted execution environments (TEEs), Gyosa allows users to confidentially delegate their GWAS analysis to untrusted infrastructures. Gyosa implements a computation partitioning scheme that reduces the computation done inside the TEEs while safeguarding the users' genomic data privacy. By integrating this security scheme in Glow, Gyosa provides a secure and distributed environment that facilitates diverse GWAS studies. The experimental evaluation validates the applicability and scalability of Gyosa, reinforcing its ability to provide enhanced security guarantees.

The advancement of remote photoplethys-mography (rPPG) technology depends on the availability of comprehensive datasets. However, the reliance on facial features for rPPG signal acquisition poses significant privacy concerns, hindering the development of open-access datasets. This work establishes privacy protection principles for rPPG datasets and introduces the secure anonymization and encryption framework (SAEF) to address these challenges while preserving rPPG data integrity. SAEF first identifies privacy-sensitive facial regions for removal through importance and necessity analysis. The irreversible removal of these regions has an insignificant impact on signal quality, with an R-value deviation of less than 0.06 for BVP extraction and a mean absolute error (MAE) deviation of less than 0.05 for heart rate (HR) calculation. Additionally, SAEF introduces a high efficiency cascade key encryption method (CKEM), achieving encryption in 5.54 × 10^-5 seconds per frame, which is over three orders of magnitude faster than other methods, and reducing approximate point correlation (APC) values to below 0.005, approaching complete randomness. These advancements significantly improve real-time video encryption performance and security. Finally, SAEF serves as a preprocessing tool for generating volunteer-friendly, open-access rPPG datasets.

Increasing the volume of training data can enable the auxiliary diagnostic algorithms for Autism Spectrum Disorder (ASD) to learn more accurate and stable models. However, due to the significant heterogeneity and domain shift in rs-fMRI data across different sites, the accuracy of auxiliary diagnosis remains unsatisfactory. Moreover, there has been limited exploration of multi-source domain adaptation models on ASD recognition, and many existing models lack inherent interpretability, as they do not explicitly incorporate prior neurobiological knowledge such as the hierarchical structure of functional brain networks. To address these challenges, we proposed a domain-adaptive algorithm based on hyperbolic space embedding. Hyperbolic space is naturally suited for representing the topology of complex networks such as brain functional networks. Therefore, we embedded the brain functional network into hyperbolic space and constructed the corresponding hyperbolic space community network to effectively extract latent representations. To address the heterogeneity of data across different sites and the issue of domain shift, we introduce a constraint loss function, Hyperbolic Maximum Mean Discrepancy (HMMD), to align the marginal distributions in the hyperbolic space. Additionally, we employ class prototype alignment to mitigate discrepancies in conditional distributions across domains. Experimental results indicate that the proposed algorithm achieves superior classification performance for ASD compared to baseline models, with improved robustness to multi-site heterogeneity. Specifically, our method achieves an average accuracy improvement of 4.03% . Moreover, its generalization capability is further validated through experiments conducted on extra Major Depressive Disorder (MDD) datasets.

In this paper, the problem of triggering early warning for intra-operative hypotension (IOH) is addressed. Recent studies on the Hypotension Prediction Index have demonstrated a gap between the results presented during model development and clinical evaluation. Thus, there is a need for better collaboration between data scientists and clinicians who need to agree on a common basis to evaluate those models. In this paper, we propose a comprehensive framework for IOH prediction: to address several issues inherent to the commonly used fixed-time-to-onset approach in the literature, a sliding window approach is suggested. The risk prediction problem is formalized with consistent precision-recall metrics rather than the receiver-operator characteristic. For illustration, a standard machine learning method is applied using two different datasets from non-cardiac and cardiac surgery. Training is done on a part of the non-cardiac surgery dataset and tests are performed separately on the rest of the non-cardiac dataset and cardiac dataset. Compared to a realistic clinical baseline, the proposed method achieves a significant improvement on the non-cardiac surgeries (precision of 48% compared to 32% for a recall of 28% (p$< $0.001)). For cardiac surgery, this improvement is less significant but still demonstrate the generalization of the model.

Semi-supervised medical image segmentation is essential for alleviating the cost of manual annotation in clinical applications. However, existing methods often suffer from unreliable pseudo-labels and confirmation bias in consistency-based training, which can lead to unstable optimization and degraded performance. To address these issues, a novel method named dual-Student adversarial framework with discriminator and consistency-driven learning for semi-supervised medical image segmentation is proposed. Specifically, an adversarial learning-based segmentation refinement (ALSR) module is designed to encourage prediction diversity between two student networks and leverage a shared discriminator for adversarial refinement of pseudo-labels. To further stabilize the consistency process, a residual exponential moving average (R-EMA) is applied in the uncertainty estimation with inter-instance consistency measurement (UIM) module to construct a robust teacher model, while noisy voxel predictions are selectively filtered based on uncertainty estimation. In addition, a Contrastive Representation Stabilization (CRS) module is developed to enhance voxel-level semantic alignment by performing contrastive learning only on confident regions, improving feature discriminability and structural consistency. Extensive experiments on benchmark datasets demonstrate that our method consistently outperforms prior state-of-the-art approaches.