Medical & Biological Engineering & Computing最新文献

The current clinical gold standard to assess the condition and detect loosening of pedicle screw implants is radiation-emitting medical imaging. However, solely based on medical imaging, clinicians are not able to reliably identify loose implants in a substantial amount of cases. To complement medical imaging for pedicle screw loosening detection, we propose a new methodology and paradigm for the radiation-free, non-destructive, and easy-to-integrate loosening detection based on vibroacoustic sensing. For the detection of a loose implant, we excite the vertebra of interest with a sine sweep vibration at the spinous process and use a custom highly sensitive piezo vibration sensor attached directly at the screw head to capture the propagated vibration characteristics which are analyzed using a detection pipeline based on spectrogram features and a SE-ResNet-18. To validate the proposed approach, we propose a novel, biomechanically validated simulation technique for pedicle screw loosening, conduct experiments using four human cadaveric lumbar spine specimens, and evaluate our algorithm in a cross-validation experiment. The proposed method reaches a sensitivity of $91.50\pm 6.58\%$ and a specificity of $91.10\pm 2.27\%$ for pedicle screw loosening detection.

Sepsis poses a major global health threat, accounting for millions of deaths annually and significant economic costs. Accurately predicting the risk of mortality in sepsis patients enables early identification, promotes the efficient allocation of medical resources, and facilitates timely interventions, thereby improving patient outcomes. Current methods typically utilize only one type of data-either constant, temporal, or ICD codes. This study introduces a novel approach, the Time-Constant Kolmogorov-Arnold Network (TCKAN), which uniquely integrates temporal data, constant data, and ICD codes within a single predictive model. Unlike existing methods that typically rely on one type of data, TCKAN leverages a multi-modal data integration strategy, resulting in superior predictive accuracy and robustness in identifying high-risk sepsis patients. Validated against the MIMIC-III and MIMIC-IV datasets, TCKAN surpasses existing machine learning and deep learning methods in accuracy, sensitivity, and specificity. Notably, TCKAN achieved AUCs of 87.76% and 88.07%, demonstrating superior capability in identifying high-risk patients. Additionally, TCKAN effectively combats the prevalent issue of data imbalance in clinical settings, improving the detection of patients at elevated risk of mortality and facilitating timely interventions. These results confirm the model's effectiveness and its potential to transform patient management and treatment optimization in clinical practice. Although the TCKAN model has already incorporated temporal, constant, and ICD code data, future research could include more diverse medical data types, such as imaging and laboratory test results, to achieve a more comprehensive data integration and further improve predictive accuracy.

The cortical surface parcellation provides prior guidance for studying mental disorders and human cognition. Graph neural networks (GNNs) have gained popularity in this task to preserve its spatial structure. However, previous GNNs struggled to effectively exploit the information contained in the complex spatial structure of the cortical surface and generally encountered an uneven node distribution issue. Meanwhile, labeling boundary nodes was also identified as a widespread problem in this task. Accordingly, this paper develops a scale-unified spatial learning network with a boundary contrastive loss (SSLNet) for cortical surface parcellation. Its core is the scale-unified spatial learning module. It devises neighbor feature extraction and aggregation strategies by fully integrating spatial coordinates and semantic structure to learn effective spatial features of local neighborhoods. More importantly, spatial scale unification is incorporated into this module to mitigate the negative effect on spatial learning caused by node distribution differences among local areas. Additionally, a universal boundary contrastive loss is constructed, enhancing the feature discriminability of boundary nodes by constraining them to be close to the same class nodes and apart from different class nodes in the feature space. It considerably improves boundary performance without increasing parameters or changing the network structure. Experiments regarding public Mindboggle demonstrate that the dice score and accuracy of SSLNet achieve $89.8\%$ and $90.89\%$ , respectively, surpassing existing methods.

Stroke, a major cause of death and disability worldwide, can be haemorrhagic or ischaemic depending on the type of bleeding in the brain. Rapid and accurate identification of stroke type and lesion segmentation is critical for timely and effective treatment. However, existing research primarily focuses on segmenting a single stroke type, potentially limiting their clinical applicability. This study addresses this gap by exploring multi-type stroke lesion segmentation using deep learning methods. Specifically, we investigate two distinct approaches: a single-stage approach that directly segments all tissue types in one model and a hierarchical approach that first classifies stroke types and then utilises specialised segmentation models for each subtype. Recognising the importance of accurate stroke classification for the hierarchical approach, we evaluate ResNet, ResNeXt and ViT networks, incorporating focal loss and oversampling techniques to mitigate the impact of class imbalance. We further explore the performance of U-Net, U-Net++ and DeepLabV3 models for segmentation within each approach. We use a comprehensive dataset of 6650 images provided by the Ministry of Health of the Republic of Türkiye. This dataset includes 1130 ischaemic strokes, 1093 haemorrhagic strokes and 4427 non-stroke cases. In our comparative experiments, we achieve an AUC score of 0.996 when classifying stroke and non-stroke slices. For lesion segmentation task, while the performance of different architectures is comparable, the hierarchical training approach outperforms the single-stage approach in terms of intersection over union (IoU). The performance of the U-Net model increased significantly from an IoU of 0.788 to 0.875 when the hierarchical approach is used. This comparative analysis aims to identify the most effective approach and deep learning model for multi-type stroke lesion segmentation in brain CT scans, potentially leading to improved clinical decision-making, treatment efficiency and outcomes.

In this study, the impact of mobile phone radiation on blood-brain barrier (BBB) permeability was investigated. A total of 21 New Zealand rabbits were used for the experiments, divided into three groups, each consisting of 7 rabbits. One group served as the control, while the other two were exposed to electromagnetic radiation at frequencies of 1800 MHz with a distance of 14.5 cm and 2100 MHz with a distance of 17 cm, maintaining a constant power intensity of 15 dBm, for a duration equivalent to the current average daily conversation time of 38 min. The exposure was conducted under non-thermal conditions, with RF radiation levels approximately ten times lower than normal values. Evans blue (EB) dye was used as a marker to assess BBB permeability. EB binds to plasma proteins, and its presence in brain tissue indicates a disruption in BBB integrity, allowing for a quantitative evaluation of radiation-induced permeability changes. Left and right brain tissue samples were analyzed using trichloroacetic acid (TCA) and phosphate-buffered solution (PBS) solutions to measure EB amounts at 620 nm via spectrophotometry. After the experiments, BBB tissue samples were collected from the right and left brains of all rabbits in the three groups and subjected to a series of medical procedures. Samples from Group 1 were compared with those from Group 2 and Group 3 using statistical methods to determine if there were any significant differences. As a result, it was found that there was no statistically significant difference in the BBB of rabbits exposed to 1800 MHz radiation, whereas there was a statistically significant difference at a 95% confidence level in the BBB of rabbits exposed to 2100 MHz radiation. A decrease in EB values was observed upon the arithmetic examination of the BBB.

Alzheimer's disease (AD) refers to a neurological disorder that causes damage to brain cells and results in decreasing cognitive abilities and memory. In brain scans, this degeneration can be seen in different ways. The disease can be classified into four stages: Non-demented (ND), moderate demented (MoD), mild demented (MiD), and very mild demented (VMD). To prepare the raw dataset for analysis, the collected magnetic resonance imaging (MRI) images are subjected to several pre-processing techniques in order to improve the performance accuracy of the proposed model. Medical images generally have poor contrast and get affected by noise, which ends up with inaccurate diagnosis. For the different phases of AD to be detected, a clear image is necessary. To address this issue, the influence of the artefacts must be reduced, enhance the contrast, and reduce the loss of information. A novel framework for image enhancement is suggested to increase the accuracy in the detection and identification of AD. In this study, the raw MRI dataset from the Alzheimer's disease neuroimaging initiative (ADNI) database is subjected to skull stripping, contrast enhancement, and image filtering followed by data augmentation to balance the dataset with four types of Alzheimer's classes. The pre-processed data are subjected to five different pre-trained models such as AlexNet, ResNet, VGG 16, EfficientNet, and Inceptionv3 achieving a testing accuracy rate of 91.2%, 88.21%, 92.34%, 93.45%, and 85.12%, respectively. These pre-trained models are compared with the proposed CNN (convolutional neural network) model designed with Adam optimizer and Flatten Swish activation function which reaches the highest accuracy of 96.5% with a learning rate of 0.000001. The five pre-trained CNN models along with the proposed swish-based AD-CNN were tested using various performance metrics to evaluate the model efficiency in classifying and identifying the AD classes. From the result analysis, it is evident that the proposed AD-CNN model outperforms all the other models.

The research focuses on leveraging convolutional neural networks (CNNs) to enhance the analysis of physiological signals, specifically photoplethysmogram (PPG) data which is a valuable tool for non-invasive heart rate prediction. Recognizing the global challenge of heart failure, the study seeks to provide a rapid, accurate, and non-invasive alternative to traditional, uncomfortable blood pressure cuffs. To achieve more accurate and efficient heart rate estimates, a k-fold CNN model with an optimal number of convolutional layers is employed. While the findings show promising results, the study addresses potential sources of error in cuffless PPG-based heart rate measurement, including motion artifacts and skin color variations, emphasizing the need for validation against gold standard methods. The research optimizes a CNN model with optimal layers, operating on 1D arrays of 8-s data slices and employing k-fold cross-validation to mitigate probabilistic uncertainties. Finally, the model yields a remarkable minimum absolute error (MAE) rate of 6.98 beats per minute (bpm), marking a significant 10% improvement over recent studies. The study also advances medical diagnostics and data analysis, then lays a strong foundation for developing cost-effective, reliable devices that offer a more comfortable and efficient way of predicting heart rate.

The purpose of this study is to quantify the three-dimensional (3D) structural morphology, bone mineral density (BMD) distribution, and mechanical properties of different China-Japan Friendship Hospital (CJFH) classification types and assist clinicians in classifying necrotic femurs accurately. In this study, 41 cases were classified as types L2 and L3 based on CT images. Then, 3D Statistical Shape and Appearance Models (SSM and SAM) were established, and 80 principal component (PC) modes were extracted from the SSM and SAM as the candidate features. The bone strength of each case was also calculated as the candidate feature using finite element analysis (FEA). Support vector machine (SVM) and Extreme Gradient Boosting (XGBoost) were used to establish 10 machine learning models. Feature selection methods were used to screen the candidate features. The performance of each model was evaluated based on sensitivity, specificity, accuracy, and the area under the receiver operating characteristic (ROC) curve. This resulted in a SVM model for CJFH classification with the performance: accuracy of 87.5%, sensitivity of 85.0%, specificity of 76.0%, and AUC of 94.2%. This study provided effective machine learning models for assisting in diagnosing CJFH types, increasing the objectivity of the diagnosis. They may have great potential for application in clinical assessments of CJFH classification.

Neck injuries from parachute opening shock (POS) are a concern in skydiving and military operations. This study employs finite element modeling to simulate POS scenarios and assess cervical spine injury risks. Validated against various conditions, including whiplash, the model replicates head/neck kinematics and soft tissue responses. POS simulations capture body/head motions during parachute deployment, indicating minimal risk of severe neck injuries (Abbreviated Injury Score/AIS ≥ 2) and low risk of soft tissue tears. Vertebral stress analysis during a rougher jump highlights high stress at C5/C6 lamina, indicating fracture risk. Comparative analysis with rear impact scenarios reveals distinct strain patterns, with rear impacts showing higher ligament strain, consistent with higher soft tissue damage risk. Though POS simulations exhibit lower strain values, they emphasize similar neck deformation patterns. The model's capability to accurately simulate head and neck movements during parachute openings provides critical validation for its use in assessing injury risks. The study's findings underline the importance of considering specific loading conditions in injury assessments and contribute to refining safety standards for skydiving and military operations. By highlighting the differences in injury mechanisms between POS and rear impacts, this research offers valuable insights into tailored injury mitigation strategies. The results not only enhance our understanding of neck injury mechanisms but also inform the development of protective gear and safety protocols, ultimately aiding in injury prevention for skydivers and military personnel.