Medical & Biological Engineering & Computing最新文献

Precise segmentation of breast tumors from MRI is crucial for breast cancer diagnosis, as it allows for detailed calculation of tumor characteristics such as shape, size, and edges. Current segmentation methodologies face significant challenges in accurately modeling the complex interrelationships inherent in multi-sequence MRI data. This paper presents a hybrid deep network framework with three interconnected modules, aimed at efficiently integrating and exploiting the spatial-temporal features among multiple MRI sequences for breast tumor segmentation. The first module involves an advanced multi-sequence encoder with a densely connected architecture, separating the encoding pathway into multiple streams for individual MRI sequences. To harness the intricate correlations between different sequence features, we propose a sequence-awareness and temporal-awareness method that adeptly fuses spatial-temporal features of MRI in the second multi-scale feature embedding module. Finally, the decoder module engages in the upsampling of feature maps, meticulously refining the resolution to achieve highly precise segmentation of breast tumors. In contrast to other popular methods, the proposed method learns the interrelationships inherent in multi-sequence MRI. We justify the proposed method through extensive experiments. It achieves notable improvements in segmentation performance, with Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and Positive Predictive Value (PPV) scores of 80.57%, 74.08%, and 84.74% respectively.

Right ventricular assist devices (RVADs) have been extensively used to provide hemodynamic support for patients with end-stage right heart (RV) failure. However, conventional in-parallel RVADs can lead to an elevation of pulmonary artery (PA) pressure, consequently increasing the right ventricular (RV) afterload, which is unfavorable for the relaxation of cardiac muscles and reduction of valve complications. The aim of this study is to investigate the hemodynamic effects of the pulsatile frequency of the RVAD on pulmonary artery. Firstly, a mathematical model incorporating heart, systemic circulation, pulmonary circulation, and RVAD is developed to simulate the cardiovascular system. Subsequently, the frequency characteristics of the pulmonary circulation system are analyzed, and the calculated results demonstrate that the pulsatile frequency of the RVAD has a substantive impact on the pulmonary artery pressure. Finally, to verify the analysis results, the hemodynamic effects of the pulsatile frequency of the RVAD on pulmonary artery are compared under diffident support modes. It is found that the pulmonary artery pressure decreases by approximately 6% when the pulsatile frequency changes from 1 to 3 Hz. The increased pulsatile frequency of RA-PA support mode may facilitate the opening of the pulmonary valve, while the RV-PA support mode can more effectively reduce the load of RV. This work provides a useful method to decrease the pulmonary artery pressure during the RVAD supports and may be beneficial for improving myocardial function in patients with end-stage right heart failure, especially those with pulmonary hypertension.

Lumbar disc herniation is one of the most prevalent orthopedic issues in clinical practice. The lumbar spine is a crucial joint for movement and weight-bearing, so back pain can significantly impact the everyday lives of patients and is prone to recurring. The pathogenesis of lumbar disc herniation is complex and diverse, making it difficult to identify and assess after it has occurred. Magnetic resonance imaging (MRI) is the most effective method for detecting injuries, requiring continuous examination by medical experts to determine the extent of the injury. However, the continuous examination process is time-consuming and susceptible to errors. This study proposes an enhanced model, BE-YOLOv5, for hierarchical detection of lumbar disc herniation from MRI images. To tailor the training of the model to the job requirements, a specialized dataset was created. The data was cleaned and improved before the final calibration. A final training set of 2083 data points and a test set of 100 data points were obtained. The YOLOv5 model was enhanced by integrating the attention mechanism module, ECAnet, with a 3 × 3 convolutional kernel size, substituting its feature extraction network with a BiFPN, and implementing structural system pruning. The model achieved an 89.7% mean average precision (mAP) and 48.7 frames per second (FPS) on the test set. In comparison to Faster R-CNN, original YOLOv5, and the latest YOLOv8, this model performs better in terms of both accuracy and speed for the detection and grading of lumbar disc herniation from MRI, validating the effectiveness of multiple enhancement methods. The proposed model is expected to be used for diagnosing lumbar disc herniation from MRI images and to demonstrate efficient and high-precision performance.

The aim of this study was to quantitatively study the effect of anterior cervical discectomy and fusion (ACDF) on the risk of spinal injury under frontal impact. A head-neck finite element model incorporating active neck muscles and soft tissues was developed and validated. Based on the intact head-neck model, three ACDF models (single-level, two-level and three-level) were used to analyze the frontal impact responses of the head-neck. The results revealed that various surgical approaches led to distinct patterns of vertebral damage under frontal impact. For single-level and three-level ACDFs, vertebral destruction was mainly concentrated at the lower end of the fused segment, while the other vertebrae were not significantly damaged. For two-level ACDF, the lowest vertebra was the first to suffer destruction, followed by severe damage to both the upper and lower vertebrae, while the middle vertebra of the cervical spine exhibited only partial damage around the screws. Fusion surgery for cervical spine injuries predominantly influences the vertebral integrity of the directly fused segments when subjected to frontal impact, while exerting a comparatively lesser impact on the cross-sectional properties of adjacent, non-fused segments.

Diastolic vortex ring (VR) plays a key role in the blood-pumping function exerted by the left ventricle (LV), with altered VR structures being associated with LV dysfunction. Herein, we sought to characterize the VR diastolic alterations in ischemic cardiomyopathy (ICM) patients with systo-diastolic LV dysfunction, as compared to healthy controls, in order to provide a more comprehensive understanding of LV diastolic function. 4D Flow MRI data were acquired in ICM patients (n = 15) and healthy controls (n = 15). The λ₂ method was used to extract VRs during early and late diastolic filling. Geometrical VR features, e.g., circularity index (CI), orientation (α), and inclination with respect to the LV outflow tract (ß), were extracted. Kinetic energy (KE), rate of viscous energy loss ( $\dot{\mathrm{EL}}$ ), vorticity (W), and volume (V) were computed for each VR; the ratios with the respective quantities computed for the entire LV were derived. At peak E-wave, the VR was less circular (p = 0.032), formed a smaller α with the LV long-axis (p = 0.003) and a greater ß (p = 0.002) in ICM patients as compared to controls. At peak A-wave, CI was significantly increased (p = 0.034), while α was significantly smaller (p = 0.016) and β was significantly increased (p = 0.036) in ICM as compared to controls. At both peak E-wave and peak A-wave, ${\dot{\mathrm{EL}}}_{\mathrm{VR}}/{\dot{\mathrm{EL}}}_{\mathrm{LV}}$ , W_VR/W_LV, and V_VR/V_LV significantly decreased in ICM patients vs. healthy controls. KE_VR/V_VR showed a significant decrease in ICM patients with respect to controls at peak E-wave, while V_VR remained comparable between normal and pathologic conditions. In the analyzed ICM patients, the diastolic VRs showed alterations in terms of geometry and energetics. These derangements might be attributed to both structural and functional alterations affecting the infarcted wall region and the remote myocardium.

Continuous blood pressure (BP) provides essential information for monitoring one's health condition. However, BP is currently monitored using uncomfortable cuff-based devices, which does not support continuous BP monitoring. This paper aims to introduce a blood pressure monitoring algorithm based on only photoplethysmography (PPG) signals using the deep neural network (DNN). The PPG signals are obtained from 125 unique subjects with 218 records and filtered using signal processing algorithms to reduce the effects of noise, such as baseline wandering, and motion artifacts. The proposed algorithm is based on pulse wave analysis of PPG signals, extracted various domain features from PPG signals, and mapped them to BP values. Four feature selection methods are applied and yielded four feature subsets. Therefore, an ensemble feature selection technique is proposed to obtain the optimal feature set based on major voting scores from four feature subsets. DNN models, along with the ensemble feature selection technique, outperformed in estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) compared to previously reported approaches that rely only on the PPG signal. The coefficient of determination ( $R^2$ ) and mean absolute error (MAE) of the proposed algorithm are 0.962 and 2.480 mmHg, respectively, for SBP and 0.955 and 1.499 mmHg, respectively, for DBP. The proposed approach meets the Advancement of Medical Instrumentation standard for SBP and DBP estimations. Additionally, according to the British Hypertension Society standard, the results attained Grade A for both SBP and DBP estimations. It concludes that BP can be estimated more accurately using the optimal feature set and DNN models. The proposed algorithm has the potential ability to facilitate mobile healthcare devices to monitor continuous BP.

The exponential growth in data volume has necessitated the adoption of alternative storage solutions, and DNA storage stands out as the most promising solution. However, the exorbitant costs associated with synthesis and sequencing impeded its development. Pre-compressing the data is recognized as one of the most effective approaches for reducing storage costs. However, different compression methods yield varying compression ratios for the same file, and compressing a large number of files with a single method may not achieve the maximum compression ratio. This study proposes a multi-file dynamic compression method based on machine learning classification algorithms that selects the appropriate compression method for each file to minimize the amount of data stored into DNA as much as possible. Firstly, four different compression methods are applied to the collected files. Subsequently, the optimal compression method is selected as a label, as well as the file type and size are used as features, which are put into seven machine learning classification algorithms for training. The results demonstrate that k-nearest neighbor outperforms other machine learning algorithms on the validation set and test set most of the time, achieving an accuracy rate of over 85% and showing less volatility. Additionally, the compression rate of 30.85% can be achieved according to k-nearest neighbor model, more than 4.5% compared to the traditional single compression method, resulting in significant cost savings for DNA storage in the range of $0.48 to 3 billion/TB. In comparison to the traditional compression method, the multi-file dynamic compression method demonstrates a more significant compression effect when compressing multiple files. Therefore, it can considerably decrease the cost of DNA storage and facilitate the widespread implementation of DNA storage technology.

The prevalence of epidemics has been studied by researchers in various fields. In the last 2 years, the outbreak of COVID-19 has affected the health, economy, and industry of communities around the world and has caused the death of millions of people. Therefore, many researchers have tried to model and control the prevalence of this disease. In this article, the new SQEIAR model for the spread of the COVID-19 disease is provided, which, compared to previous models, explores the effects of additional interventions on the outbreak and incorporates a wider range of variables and parameters to enhance its accuracy and alignment with reality. These modifications in the model lead to a more rapid eradication and control of the disease. This model includes six variables of the group of susceptible, quarantined, exposed, symptomatic, asymptomatic, and recovered individuals and includes three control inputs such as quarantine of susceptible, vaccination, and treatments. In order to minimize symptomatic infectious individuals and susceptible individuals and also to reduce treatment, vaccination, and quarantine costs, an optimal control approach using the Deep Deterministic Policy Gradient (DDPG) method has been applied to the system. This algorithm is applied to the model in different cases of control inputs, and for each case, optimal control inputs are obtained. In the following, the number of deaths due to the disease and the total number of symptomatic infectious individuals for each of these optimal control cases has been calculated. The results of the implemented control structure demonstrated a reduction of 60% in the number of deaths and 74% in the number of symptomatically infected individuals compared to the uncontrolled model. Finally, to test the performance of the control system, noise was applied to the system in various ways, including three methods: applying noise to observer variables, applying noise to control inputs, and applying uncertainty to model parameters. Therefore, we found that this control system was robust and performed well in different conditions despite the disturbance.

Stroke is a neurological condition that usually results in the loss of voluntary control of body movements, making it difficult for individuals to perform activities of daily living (ADLs). Brain-computer interfaces (BCIs) integrated into robotic systems, such as motorized mini exercise bikes (MMEBs), have been demonstrated to be suitable for restoring gait-related functions. However, kinematic estimation of continuous motion in BCI systems based on electroencephalography (EEG) remains a challenge for the scientific community. This study proposes a comparative analysis to evaluate two artificial neural network (ANN)-based decoders to estimate three lower-limb kinematic parameters: x- and y-axis position of the ankle and knee joint angle during pedaling tasks. Long short-term memory (LSTM) was used as a recurrent neural network (RNN), which reached Pearson correlation coefficient (PCC) scores close to 0.58 by reconstructing kinematic parameters from the EEG features on the delta band using a time window of 250 ms. These estimates were evaluated through kinematic variance analysis, where our proposed algorithm showed promising results for identifying pedaling and rest periods, which could increase the usability of classification tasks. Additionally, negative linear correlations were found between pedaling speed and decoder performance, thereby indicating that kinematic parameters between slower speeds may be easier to estimate. The results allow concluding that the use of deep learning (DL)-based methods is feasible for the estimation of lower-limb kinematic parameters during pedaling tasks using EEG signals. This study opens new possibilities for implementing controllers most robust for MMEBs and BCIs based on continuous decoding, which may allow for maximizing the degrees of freedom and personalized rehabilitation.

There is no effective fall risk screening tool for the elderly that can be integrated into clinical practice. Developing a system that can be easily used in primary care services is a current need. Current studies focus on the use of multiple sensors or activities to achieve higher accuracy. However, multiple sensors and activities reduce the availability of these systems. This study aims to develop a system to perform fall prediction for the elderly by using signals recorded from a single sensor during a short-term activity. A total of 168 features in the time and frequency domains were created using acceleration signals obtained from 71 elderly people. The features were weighted based on the ReliefF algorithm, and the artificial neural networks model was developed using the most important features. The best classification result was obtained using the 17 most important features of those weighted for K = 20 nearest neighbors. The highest accuracy was 82.2% (82.9% Sensitivity, 81.6% Specificity). The partially high accuracy obtained in our study shows that falling can be detected early with a sensor and a simple activity by determining the right features and can be easily applied in the assessment of the elderly during routine follow-ups.