Biocybernetics and Biomedical Engineering最新文献

The second-leading cause of death for women is breast cancer. Consequently, a precise early diagnosis is essential. With the rapid development of artificial intelligence, computer-aided diagnosis can efficiently assist radiologists in diagnosing breast problems. Mammography images, breast thermal images, and breast ultrasound images are the three ways to diagnose breast cancer. The paper will discuss some recent developments in machine learning and deep learning in three different breast cancer diagnosis methods. The three components of conventional machine learning methods are image preprocessing, segmentation, feature extraction, and image classification. Deep learning includes convolutional neural networks, transfer learning, and other methods. Additionally, the benefits and drawbacks of different methods are thoroughly contrasted. Finally, we also provide a summary of the challenges and potential futures for breast cancer diagnosis.

The paper presents an original method for controlling a surface-electromyography-driven (sEMG) prosthesis. A context-dependent recognition system is proposed in which the same class of sEMG signals may have a different interpretation, depending on the context. This allowed the repertoire of performed movements to be increased. The proposed structure of the context-dependent recognition system includes unambiguously defined decision sequences covering the overall action of the prosthesis, i.e. the so-called boxes. Because the boxes are mutually isolated environments, each box has its own interpretation of the recognition result, as well as a separate local-recognition-task-focused classifier.

Due to the freedom to assign contextual meanings to classes of biosignals, the construction procedure of the classifier can be optimised in terms of the local classification quality in a given box or the classification quality of the entire system. In the paper, two optimisation problems are formulated, differing in the adopted constraints on optimisation variables, with the methods of solving the problems based on an exhaustive search and an evolutionary algorithm, being developed.

Experimental studies were conducted using signals from 1 able-bodied person with simulation of amputation and 10 volunteers with transradial amputations. The study compared the classical recognition system and the context-dependent system for various classifier models. An unusual testing strategy was adopted in the research, taking into account the specificity of the considered recognition task, with two original quality measures resulting from this scheme then being applied. The results obtained confirm the hypothesis that the application of the context-dependent classifier led to an improvement in classification quality.

Heart failure is a chronic and progressive condition characterized by the heart’s inability to pump sufficient blood to meet the body’s metabolic demands. It is a significant public health concern worldwide, associated with high morbidity, mortality, and healthcare costs. For advanced heart failure cases not responding to medical therapy, heart transplantation or mechanical circulatory support with ventricular assist devices (VADs) can be considered. In the specific case of bi-ventricular heart failure a replacement of both ventricles is required. In this context a Total Artificial Heart (TAH) may be proposed as a bridge to transplant solution. Additionally, bi-ventricular assist devices (BiVADs) are available to support both ventricles simultaneously. However Bi-ventricular heart failure management is difficult with poor outcomes. New surgical procedures appear to propose solutions after both ventricle failure. One of these intervention uses two continuous-flow VADs as a total artificial heart after cardiac explantation due to myocardial sarcoma. Unfortunately, this procedure makes patient management very difficult as pulmonary pressures and flow rate are no longer measurable after the surgical procedure. The setting of both pumps is hence a complex task for patient management. This article aims at helping clinicians on patient management undergoing double assistance after cardiac explantation by predicting the different outcomes on the vascular grid for all the possible rotational speed combination using a lumped model. Results provide a range of both pump operating conditions suitable for delivering a physiologically adapted flow to the vascular grid when combined with hypotensive treatments.

Spatiotemporal optical coherence tomography (STOC-T) is the novel modality for high-speed, crosstalk- and aberration-free volumetric imaging of biological tissue in vivo. STOC-T extends the Fourier-Domain holographic Optical Coherence Tomography by the spatial phase modulation that enables the reduction of spatial coherence of the tunable laser. By reducing the spatial coherence of the laser, we suppress coherent noise, and, consequently, improve the imaging depth. Furthermore, we remove geometrical aberrations computationally in postprocessing. We recently demonstrated high-speed, high-resolution STOC-T of human retinal imaging in vivo. Here, we show that the dataset produced by STOC-T can be processed differently to reveal blood flow in the human retina in vivo. To render the blood flow, we first pre-process STOC-T holographic data to access the approximated information about the Doppler-shifted optical field backscattered from the sample. Then, we analyze it using methods from the laser Doppler flowmetry, namely, by analyzing the Doppler broadening caused by moving light scatterers (red blood cells). However, contrary to conventional approaches, we use multiple illumination wavelengths. This enables us to render the structural volumetric and blood flow images from the same dataset concurrently. Our method, denoted as multiwavelength laser Doppler holography (MLDH), links laser Doppler flowmetry with multiwavelength holographic detection to enable noninvasive visualization and possible blood flow quantification at different human retina layers at high speeds and high transverse resolution in vivo.

Quantitative analysis of biomarkers in Optical Coherence Tomography (OCT) images plays an import role in the diagnosis and treatment of retinal diseases. However, biomarker segmentation in retinal OCT images is very hard due to the large variations in size and shape of retinal biomarkers, blurred boundaries, low contrast, and speckle interference. We proposed a novel Multi-scale Local-Global Transformer network (MsLGT-Net) for biomarker segmentation in retinal OCT images. The network combines the proposed Multi-scale Fusion Attention (MFA) module, Local-Global Transformer (LGT) module, and Contrastive Learning Enhancement (CLE) module to tackle the challenges of biomarker segmentation. Specifically, the proposed MFA module aims to enhance the network’s ability to learn multi-scale features of retinal biomarkers by effectively combining the local detail information and contextual semantic information of biomarkers at different scales, and improve the representation ability for different classes of biomarkers. The LGT module is designed to learn local and global information adaptively from multi-scale fused features to address the challenge of small biomarker segmentation. In addition, to distinguish features between different types of retinal biomarkers, we propose the CLE module to enhance the feature representation of different biomarkers. Our proposed method is validated on one public dataset and one local dataset. The experimental results show that the proposed method is more effective than other state-of-the-art methods.

Stroke is a leading cause of disability and death worldwide, with acute ischemic stroke (AIS) accounting for the majority of cases. Early and accurate diagnosis of AIS is crucial for improving patient outcomes. Non-invasive monitoring techniques, such as time domain near-infrared spectroscopy (tdNIRS), have shown potential for real-time monitoring of AIS patients at the bedside. However, there is a need for further research to evaluate the effectiveness of tdNIRS in the acute phase of stroke. In this study, we present the results of a case report using tdNIRS to monitor AIS patients without any additional stimulation. The tdNIRS technique allows for non-invasively assessing cerebral oxygenation in absolute units, enabling accurate measurement of changes in oxygenated and deoxygenated hemoglobin concentrations in the brain. Our aim was to determine the feasibility of tdNIRS in monitoring AIS patients.

Plantar pressure distribution offers insights into foot function, gait mechanics, and foot-related issues. This systematic review presents an analysis of the use of artificial neural network techniques in the context of plantar pressure analysis. 60 studies were included in the review. Sample size, pathology, pressure sensor number, data collection device, utilization of other sensor devices, ground-truth methods, pre-processing dataset, neural network type, and evaluation metrics were evaluated. Utilization of customized wearable footwear devices for the acquisition of data was common amongst both healthy participants and patients. Inertial measurement units emerged as an effective compensatory measure to address the limitations associated with the distribution of plantar pressure. Ground truth methods predominantly relied on the usage of both annotations and reference devices. Multilayer perceptron, convolutional neural networks, and recurrent neural networks were identified as the most frequently employed artificial neural network algorithms across the reviewed studies. Finally, the evaluation of performance largely drew upon statistical descriptions and other machine learning methods. This review provides a comprehensive understanding of the use of artificial neural network techniques in plantar pressure analysis, highlighting opportunities for future research.

In this study, we investigated the effects of oxygen toxicity on brain activity and functional connectivity (FC) in divers using a closed-circuit oxygen breathing apparatus. We acquired and analyzed electroencephalographic (EEG) signals from a group of normal professional divers (PD) and a group that developed oxygen intolerance, i.e., oxygen-intolerant professional divers (OPD), to evaluate the potential risk of a dive and understand the physiological mechanisms involved. The results highlighted a significant difference in the baseline levels of $\alpha$ rhythm between PD and OPD, with PD exhibiting a lower level to counteract the effects of increased $O_2$ inhalation, while OPD showed a higher level that resulted in a pathological state. Connectivity analysis revealed a strong correlation between cognitive and motor regions, and high levels of $\alpha$ synchronization at rest in OPDs. Our findings suggest that a pathological condition may underlie the higher $\alpha$ levels observed in these individuals when facing the stress of high $O_2$ inhalation. These findings support the hypothesis that oxygen modulates brain networks, and have important implications for understanding the neural mechanisms involved in oxygen toxicity. The study also provides a unique opportunity to investigate the impact of neurophysiological activity in simulated critical scenarios, and opens up new perspectives in the screening and monitoring of divers.

Driven by the desire for feasible and convenient healthcare, non-contact heart rate (HR) monitoring based on consumer-grade cameras has gained significant recognition among researchers. However, this technology suffers from performance reliability and consistency in realistic situations of motion artifacts, illumination variations, and skin tones, limiting it to emerge as an alternative to conventional methods. Considering these challenges, this paper suggests an effective technique for HR measurement from facial RGB videos. The face being the region of interest (ROI) is divided into several small sub-ROIs of even size. A group of quality sub-ROIs is formed and weighted based on the fundamental periodicity coefficient to handle spatial non-uniform illumination and facial motions. Five different color spaces are considered, and the most suitable color component from each space is chosen to alleviate the influence of temporal illumination variation and other factors. The resultant color signals are denoised using the ensemble empirical mode decomposition and integrated using the principal component analysis to derive a pulsating component representing the blood volumetric changes for HR computation. Experiments are conducted over three standard datasets, namely PURE, UBFC, and COHFACE. The obtained mean absolute error values are 1.16 beats per minute (bpm), 1.56 bpm, and 2.10 bpm for PURE, UBFC, and COHFACE datasets, respectively, indicating the performance of the technique well above the clinically acceptable threshold. In comparison, the technique showed performance superiority over the state-of-art methods. These outcomes substantiate the potential of alternative color spaces for accurate and reliable HR monitoring from facial videos in challenging scenarios.

Insulin resistance (IR) is a multifactorial metabolic disorder associated with the development of cardiometabolic syndrome, cardiovascular diseases and obesity. Factors such as inflammation, hyperinsulinemia, hyperglucagonemia, mitochondrial dysfunction, glucotoxicity and lipotoxicity contribute to the development of IR. Despite being extensively studied for over 60 years, assessing the incidence of IR, developing effective prevention strategies, and implementing appropriate therapeutic approaches remain challenging. This review explores the multifaceted nature of IR, including its association with various conditions such as obesity, primary hypertension, dyslipidemia, obstructive sleep apnea, Alzheimer's disease, non-alcoholic fatty liver disease, polycystic ovary syndrome, chronic kidney disease and cancer. Additionally, we discuss the complexity of diagnosing and quantifying IR, emphasizing the lack of absolute, common criteria for classification. We delve into the use of mathematical models in clinical and epidemiological studies, focusing on the choice between insulin, triglycerides, or waist-to-hip ratio as IR determinants. Furthermore, we highlight the importance of reliable input data and caution in interpreting results when utilizing mathematical models for IR assessment. This narrative review aims to provide insights into the challenges and considerations involved in conducting IR diagnostics, with implications for clinical practice, epidemiological research, and future advancements in this field.