Irbm最新文献

Objective: Alzheimer's disease (AD) is an irreversible neurodegenerative disease, while mild cognitive impairment (MCI) is a clinical precursor of AD, thus differentiation of AD, MCI and normal control (NC) from noninvasive magnetic resonance imaging (MRI) has positive clinical implications. Material and method: We utilize a 3D residual network to classify AD, MCI, and NC, and add a multiscale module to the original network to enhance the feature representation capability of the network, as well as a cross-dimensional attentional mechanism to enhance the network's attention to important brain regions. We experimentally verified that the network is more inclined to overestimate the brain age of patients in AD and MCI subgroups, thus proving that there is a high correlation between the brain age prediction task and the AD classification task. Therefore, we adopted a multi-task learning approach, using brain age prediction as a supplementary task for AD classification to reduce the risk of overfitting of the network during the training process. Results: Our method achieved 96.02% accuracy, 93.40% precision, 91.48% recall, and 92.24% F1 value in AD/MCI/NC classification. Conclusions: Ablation experiments confirmed that our proposed cross-dimensional attention and multiscale modules can improve the diagnostic performance of AD and MCI, and that multi-task learning in conjunction with brain age prediction can further improve the performance.

Objective

This study addresses the challenge of user-specific bias in Brain-Computer Interfaces (BCIs) by proposing a novel methodology. The primary objective is to employ a hybrid deep learning model, combining 2D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers, to analyze EEG signals and classify imagined tasks. The overarching goal is to create a generalized model that is applicable to a broader population and mitigates user-specific biases.

Materials and Methods

EEG signals from imagined motor tasks in the public dataset Physionet form the basis of the study. This is due to the need to use other databases in addition to the BCI competition. A model of arrays emulating the electrode arrangement in the head is proposed to capture spatial information using CNN, and LSTM algorithms are used to capture temporal information, followed by signal classification.

Results

The hybrid model is implemented to achieve a high classification rate, reaching up to 90% for specific users and averaging 74.54%. Error detection thresholds are set to eliminate subjects with low task affinity, resulting in a significant improvement in classification accuracy of up to 21.34%.

Conclusion

The proposed methodology makes a significant contribution to the BCI field by providing a generalized system trained on diverse user data that effectively captures spatial and temporal EEG signal features. This study emphasizes the value of the hybrid model in advancing BCIs, highlighting its potential for improved reliability and accuracy in human-computer interaction. It also suggests the exploration of additional advanced layers, such as transformers, to further enhance the proposed methodology.

Objective

Unstable plaques can cause acute cardiovascular and cerebrovascular diseases. The stability and instability of plaque are related to the plaque echo status in ultrasound. Carotid videos provide detailed plaque information compared to static images. Ultrasound-based plaque echo classification is challenging due to noise, interference frames, small targets (plaques), and complex shape changes.

Methods

This study proposes a Multi-dimensional Aggregation Network (MA-Net) guided by key features for plaque diagnosis based on carotid ultrasound video, which uses only video-level labels. MA-Net consists of Key-Feature (KF) and Temporal-Channel-Spatial (TCS) modules. The KF module learns the contribution of each frame to the classification at the feature level, adaptively infers the importance score of each frame, thereby reducing the influence of interference frames. The TCS module includes the Temporal-Channel (TC) and Temporal-Spatial (TS) sub-modules. In addition to studying the temporal dimension, it delves into the relationship between the channel and spatial dimensions. TC analyses the temporal dependencies among the channels and filters noise. Moreover, TS extracts features more accurately through the spatio-temporal information contained in the surrounding environment of the plaque.

Results

The performance of MA-Net on the SHU-Ultrasound-Video-2020 dataset is better than that of the state-of-the-art models of video classification, showing at least a 5% increase in accuracy, with an accuracy rate of 87.36%.

Conclusion

The outstanding diagnostic capability of the proposed model will help provide a more robust and reproducible diagnostic process with a lower labour cost for clinical carotid plaque diagnosis.

Objectives

Electromyography is one of the few measurement methods that can be implanted, and it has been used in swallowing detection to measure superficial muscles, but has failed to provide satisfactory performances for a real-time detection. Yet, we seek to allow for the feasibility of an implantable active artificial larynx that would protect the airway during swallowing. Therefore, it requires a real-time detection of swallowing through measurements that must provide dedicated and early activity on swallowing, to close the airways soon as possible. In that regard, promising results were published about the stylohyoid and posterior digastric muscles, but no study provided simultaneous and independent measurements. So, this paper aims to evaluate both muscles with intra muscular EMG, in a large set of tasks, to evaluate their recruitment pattern for the feasibility of an implantable active artificial larynx.

Materials and methods

we used intramuscular EMG to measure the stylohyoid and the posterior digastric muscles independently. We also used surface electrodes to measure the submental muscles and provide a basis for comparison. Besides, the swallowing sound measurement method was used to locate the moment the bolus starts to enter the upper esophageal sphincter (UES). That moment defines a temporal limit after which the airway are in danger of aspiration and the temporal evolution of the muscles' is evaluated in comparison to that limit. The onsets and offsets of each muscles were located with a generalized likelihood ratio method, and the UES bolus passage was localized manually after the transformation of the signals with a Teager-Kaiser energy operator. 17 participants were measured, and were asked to perform 4 swallowing tasks and 13 non-swallowing tasks.

Results

we found a strong implication of the stylohyoid for swallowing and mastication. The posterior digastric showed a clear tendency towards swallow-related tasks, and especially swallowing, mastication, open mouth, jaw, and clench teeth. Both muscles provided significant activity before the temporal limit, with a characteristic pattern.

Conclusion

the stylohyoid and the posterior digastric muscles shows a net increase in potential for a detection, compared to the submental muscles, for the feasibility of an implantable active artificial larynx.

Background

Infectious diseases like COVID-19 pose major global health threats. Robust surveillance systems are needed to swiftly detect and contain outbreaks. This study investigates the integration of Blockchain technology and machine learning to establish a secure and ethically sound approach to tracking infectious diseases.

Methods

We established a Blockchain-based framework for the collection and analysis of epidemiological data while upholding privacy standards. We employed encryption and privacy-enhancing technologies to gather information on case numbers, locations, and disease progression. Artificial neural networks were employed to scrutinize the data and pinpoint transmission patterns. A prototype was specifically designed to work with COVID-19 data from specific countries.

Results

The Blockchain system enabled reliable and tamper-proof data gathering with enhanced transparency. The evaluation showed it allowed cost-effective tracking of infectious diseases while upholding confidentiality safeguards. The neural networks effectively modeled disease spread based on the Blockchain data.

Conclusions

This research demonstrates the viability of Blockchain and machine learning for infectious disease surveillance. The system strikes a balance between public health concerns and personal privacy considerations. It also addresses the challenges of misinformation and accountability gaps during disease outbreaks. Ongoing development can lay the foundation for an ethical framework for digital disease tracking, ensuring both pandemic preparedness and response capabilities are upheld.

Ultrasound is a powerful tool in ophthalmology with a wide range of physical effects that can interact with biological tissue. This ranges from low-intensity linear transducers for diagnosis to high-intensity pulsed or continuous focused ultrasound for therapy. Designing devices for ophthalmological applications requires creating fine focal spots, minimizing heating, and accounting for eye movements. Ultrasound is essential for ophthalmologists to provide accurate diagnosis and quantitative information on tissue composition and blood flow. Ultrasound has revolutionized cataract surgery, making it less invasive and in an outpatient basis, while enhancing the safety and predictability of glaucoma treatment using high-intensity focused ultrasound. The article aims to review the complex and multifaceted bioeffects of ultrasound used in ophthalmology, and its current and future applications of ultrasound in ophthalmology, notably regarding cavitation-mediated drug delivery.

Objectives

This study was performed to prove the concept that transfer learning techniques, assisted with a generative model, could be used to alleviate the ‘big data’ requirement for training high-fidelity deep learning (DL) models in prediction of stiffness tensor of trabecular bone cubes.

Material and methods

Transfer learning approaches of domain adaptation were used, in which a source domain included 1,641 digital trabecular bone cubes synthesized from a generative model, and a target domain included 868 real trabecular bone cubes from human cadaver femurs. Simulated quantitative computed tomography (QCT) images of both the synthesized and real bone cubes were used as input, whereas the stiffness tensor of these cubes determined using finite element simulations were used as output. Three transfer learning algorithms, including instance-based (TrAdaBoostR2 and WANN) and parameter-based (RNN) methods, were used. Two case studies, one with varying sizes of training dataset and the other with a gender-biased training dataset, were performed to evaluate these deep transfer learning models in comparison with a base deep learning (DL) model trained using the dataset from the target domain.

Results

The results indicated that these deep transfer learning models were robust both to sample size and to the gender-biased training dataset, whereas the base DL model was very sensitive to such changes. Among the three transfer learning algorithms, the prediction accuracy of the RNN-based deep transfer learning model was the best (0.92-0.96%) and comparable to that of the base DL model trained using the dataset from the target domain.

Conclusion

This study proved the proposed concept and confirmed that high fidelity QCT-based deep learning models could be obtained for prediction of stiffness tensor of trabecular bone cubes.

Background and objective

Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) aim to detect target frequencies corresponding to specific commands in electroencephalographic (EEG) signals by classification algorithms to achieve the desired control. However, SSVEP signals suffer from low signal-to-noise ratio and large differences in brain activity. Moreover, the existing CNN models have small receptive fields, which make it difficult to receive large range of feature information and limit the effectiveness of classification algorithms.

Methods

To this end, we proposed a high-order temporal convolutional neural network (HOT-CNN) model for enhancing the performance of SSVEP target recognition. Specifically, the SSVEP-EEG signals was divided into equal-length time segments and a time-slice attention module was designed to capture the correlation between time slices. The module improves the local characterization of signals and reduces biological noise interference by automatically assigning high weights to locally relevant temporal sampling cues and lower weights to other temporal cues. Moreover, for global features, a temporal convolutional network module was designed to increases the receptive field of the network and to extract more comprehensive time domain features by using dilated causal convolution. Finally, the fusion and analysis of local and global features are achieved by designing a feature fusion and classification module to accomplish accurate classification of SSVEP signals.

Results

Our method was evaluated on large publicly available datasets containing 35 subjects and 40 categories. Experimental results indicated that HOT-CNN achieved encouraging performance compared with other advanced methods: the highest information transfer rate of 241.01bits/min was obtained using 0.5s stimuli, and the highest average accuracy of 96.39% was obtained using 1.0s stimuli.

Conclusions

The method effectively reinforced the global and local time-domain information and improved the classification performance of SSVEP, which has wide application prospects.