Medical & Biological Engineering & Computing最新文献

Conventional patient monitoring in healthcare has limitations such as delayed identification of deteriorating conditions, disruptions to patient routines, and discomfort due to extensive wiring for bed-bound patients. To address these, we have recently developed an innovative IoT-based healthcare system for real-time wireless patient monitoring. This system includes a flexible epidermal patch that collects vital signs using low power electronics and transmits the data to IoT nodes in hospital beds. The nodes connect to a smart gateway that aggregates the information and interfaces with the hospital information system (HIS), facilitating the exchange of electronic health records (EHR) and enhancing access to patient vital signs for healthcare professionals. Our study validates the proposed smart bed architecture in a clinical setting, assessing its ability to meet healthcare personnel needs, patient comfort, and data transmission reliability. Technical performance assessment involves analyzing key performance indicators for communication across various interfaces, including the wearable device and the smart box, and the link between the gateway and the HIS. Also, a comparative analysis is conducted on data from our architecture and traditional hospital equipment. Usability evaluation involves questionnaires completed by patients and healthcare professionals. Results demonstrate the robustness of the architecture proposed, exhibiting reliable and efficient information flow, while offering significant improvements in patient monitoring over conventional wired methods, including unrestricted mobility and improved comfort to enhance healthcare delivery.

Current research focuses on improving electrocardiogram (ECG) monitoring systems to enable real-time and long-term usage, with a specific focus on facilitating remote monitoring of ECG data. This advancement is crucial for improving cardiovascular health by facilitating early detection and management of cardiovascular disease (CVD). To efficiently meet these demands, user-friendly and comfortable ECG sensors that surpass wet electrodes are essential. This has led to increased interest in ECG capacitive electrodes, which facilitate signal detection without requiring gel preparation or direct conductive contact with the body. This feature makes them suitable for wearables or integrated measurement devices. However, ongoing research is essential as the signals they measure often lack sufficient clinical accuracy due to susceptibility to interferences, particularly Motion Artifacts (MAs). While our primary focus is on studying MAs, we also address other limitations crucial for designing a high Signal-to-Noise Ratio (SNR) circuit and effectively mitigating MAs. The literature on the origins and models of MAs in capacitive electrodes is insufficient, which we aim to address alongside discussing mitigation methods. We bring attention to digital signal processing approaches, especially those using reference signals like Electrode-Tissue Impedance (ETI), as highly promising. Finally, we discuss its challenges, proposed solutions, and offer insights into future research directions.

The estimation of joint contact forces in musculoskeletal multibody dynamics models typically requires the use of expensive and time-consuming technologies, such as reflective marker-based motion capture (Mocap) system. In this study, we aim to propose a more accessible and cost-effective solution that utilizes the dual smartphone videos (SPV)-driven musculoskeletal multibody dynamics modeling workflow to estimate the lower limb mechanics. Twelve participants were recruited to collect marker trajectory data, force plate data, and motion videos during walking and running. The smartphone videos were initially analyzed using the OpenCap platform to identify key joint points and anatomical markers. The markers were used as inputs for the musculoskeletal multibody dynamics model to calculate the lower limb joint kinematics, joint contact forces, and ground reaction forces, which were then evaluated by the Mocap-based workflow. The root mean square error (RMSE), mean absolute deviation (MAD), and Pearson correlation coefficient (ρ) were adopted to evaluate the results. Excellent or strong Pearson correlations were observed in most lower limb joint angles (ρ = 0.74 ~ 0.94). The averaged MADs and RMSEs for the joint angles were 1.93 ~ 6.56° and 2.14 ~ 7.08°, respectively. Excellent or strong Pearson correlations were observed in most lower limb joint contact forces and ground reaction forces (ρ = 0.78 ~ 0.92). The averaged MADs and RMSEs for the joint lower limb joint contact forces were 0.18 ~ 1.07 bodyweight (BW) and 0.28 ~ 1.32 BW, respectively. Overall, the proposed smartphone video-driven musculoskeletal multibody dynamics simulation workflow demonstrated reliable accuracy in predicting lower limb mechanics and ground reaction forces, which has the potential to expedite gait dynamics analysis in a clinical setting.

Retinal image registration is of utmost importance due to its wide applications in medical practice. In this context, we propose ConKeD, a novel deep learning approach to learn descriptors for retinal image registration. In contrast to current registration methods, our approach employs a novel multi-positive multi-negative contrastive learning strategy that enables the utilization of additional information from the available training samples. This makes it possible to learn high-quality descriptors from limited training data. To train and evaluate ConKeD, we combine these descriptors with domain-specific keypoints, particularly blood vessel bifurcations and crossovers, that are detected using a deep neural network. Our experimental results demonstrate the benefits of the novel multi-positive multi-negative strategy, as it outperforms the widely used triplet loss technique (single-positive and single-negative) as well as the single-positive multi-negative alternative. Additionally, the combination of ConKeD with the domain-specific keypoints produces comparable results to the state-of-the-art methods for retinal image registration, while offering important advantages such as avoiding pre-processing, utilizing fewer training samples, and requiring fewer detected keypoints, among others. Therefore, ConKeD shows a promising potential towards facilitating the development and application of deep learning-based methods for retinal image registration.

Data-driven medical image segmentation networks require expert annotations, which are hard to obtain. Non-expert annotations are often used instead, but these can be inaccurate (referred to as "noisy labels"), misleading the network's training and causing a decline in segmentation performance. In this study, we focus on improving the segmentation performance of neural networks when trained with noisy annotations. Specifically, we propose a two-stage framework named "G-T correcting," consisting of "G" stage for recognizing noisy labels and "T" stage for correcting noisy labels. In the "G" stage, a positive feedback method is proposed to automatically recognize noisy samples, using a Gaussian mixed model to classify clean and noisy labels through the per-sample loss histogram. In the "T" stage, a confident correcting strategy and early learning strategy are adopted to allow the segmentation network to receive productive guidance from noisy labels. Experiments on simulated and real-world noisy labels show that this method can achieve over 90% accuracy in recognizing noisy labels, and improve the network's DICE coefficient to 91%. The results demonstrate that the proposed method can enhance the segmentation performance of the network when trained with noisy labels, indicating good clinical application prospects.

The fight against cancer, a relentless global health crisis, emphasizes the urgency for efficient and automated early detection methods. To address this critical need, this review assesses recent advances in non-invasive cancer prediction techniques, comparing conventional machine learning (CML) and deep neural networks (DNNs). Focusing on these seven major cancers, we analyze 310 publications spanning the years 2018 to 2024, focusing on detection accuracy as the key metric to identify the most effective predictive models, highlighting critical gaps in current methodologies, and suggesting directions for future research. We further delved into factors like datasets, features, and modalities to gain a comprehensive understanding of each approach's performance. Separate review tables for each cancer type and approach facilitated comparisons between top performers (accuracy exceeding 99%) and low performers (65.83 to 85.8%). Our exploration of public databases and commonly used classifiers revealed that optimal combinations of features, datasets, and models can achieve up to 100% accuracy for both CML and DNN. However, significant variations in accuracy (up to 35%) were observed, particularly when optimization was lacking. Notably, colorectal cancer exhibited the lowest accuracy (DNN 69%, CML 65.83%). A five-point comparative analysis (best/worst models, performance gap, average accuracy, and research trends) revealed that while DNN research is gaining momentum, CML approaches remain competitive, even outperforming DNN in some cases. This study presents an in-depth comparative analysis of CML and DNN techniques for cancer detection. This knowledge can inform future research directions and contribute to the development of increasingly accurate and reliable cancer detection tools.

Pituitary adenomas (PA) represent the most common type of sellar neoplasm. Extracting relevant information from radiological images is essential for decision support in addressing various objectives related to PA. Given the critical need for an accurate assessment of the natural progression of PA, computer vision (CV) and artificial intelligence (AI) play a pivotal role in automatically extracting features from radiological images. The field of "Radiomics" involves the extraction of high-dimensional features, often referred to as "Radiomic features," from digital radiological images. This survey offers an analysis of the current state of research in PA radiomics. Our work comprises a systematic review of 34 publications focused on PA radiomics and other automated information mining pertaining to PA through the analysis of radiological data using computer vision methods. We begin with a theoretical exploration essential for understanding the theoretical background of radionmics, encompassing traditional approaches from computer vision and machine learning, as well as the latest methodologies in deep radiomics utilizing deep learning (DL). Thirty-four research works under examination are comprehensively compared and evaluated. The overall results achieved in the analyzed papers are high, e.g., the best accuracy is up to 96% and the best achieved AUC is up to 0.99, which establishes optimism for the successful use of radiomic features. Methods based on deep learning seem to be the most promising for the future. In relation to this perspective DL methods, several challenges are remarkable: It is important to create high-quality and sufficiently extensive datasets necessary for training deep neural networks. Interpretability of deep radiomics is also a big open challenge. It is necessary to develop and verify methods that will explain to us how deep radiomic features reflect various physics-explainable aspects.

The segmentation of airway from computed tomography (CT) images plays a vital role in pulmonary disease diagnosis, evaluation, surgical planning, and treatment. Nevertheless, it is still challenging for current methods to handle distal thin and low-contrast airways, leading to mis-segmentation issues. This paper proposes a detail-sensitive 3D-UNet (DS-3D-UNet) that incorporates two new modules into 3D-UNet to segment airways accurately from CT images. The feature recalibration module is designed to give more attention to the foreground airway features through a new attention mechanism. The detail extractor module aims to restore multi-scale detailed features by fusion of features at different levels. Extensive experiments were conducted on the ATM'22 challenge dataset composed of 300 CT scans with airway annotations to evaluate its performance. Quantitative comparisons prove that the proposed model achieves the best performance in terms of Dice similarity coefficient (92.6%) and Intersection over Union (86.3%), outperforming other state-of-the-art methods. Qualitative comparisons further exhibit the superior performance of our method in segmenting thin and confused distal bronchi. The proposed model could provide important references for the diagnosis and treatment of pulmonary diseases, holding promising prospects in the field of digital medicine. Codes are available at https://github.com/nighlevil/DS-3D-UNet/tree/master .

Camptocormia, a severe flexion deformity of the spine, presents challenges in monitoring its progression outside laboratory settings. This study introduces a customized method utilizing four inertial measurement unit (IMU) sensors for continuous recording of the camptocormia angle (CA), incorporating both the consensual malleolus and perpendicular assessment methods. The setup is wearable and mobile and allows measurements outside the laboratory environment. The practicality for measuring CA across various activities is evaluated for both the malleolus and perpendicular method in a mimicked Parkinson disease posture. Multiple activities are performed by a healthy volunteer. Measurements are compared against a camera-based reference system. Results show an overall root mean squared error (RMSE) of 4.13° for the malleolus method and 2.71° for the perpendicular method. Furthermore, patient-specific calibration during the standing still with forward lean activity significantly reduced the RMSE to 2.45° and 1.68° respectively. This study presents a novel approach to continuous CA monitoring outside the laboratory setting. The proposed system is suitable as a tool for monitoring the progression of camptocormia and for the first time implements the malleolus method with IMU. It holds promise for effectively monitoring camptocormia at home.

Percutaneous ventricular assist devices (pVADs) incorporated with admittance electrodes have been validated in animal studies for accurate instantaneous volumetric measurements. Since miniaturization of the pVAD profile is a priority to reduce vascular complications in patients, our study aimed to validate admittance measurements using three electrodes instead of the standard four. Complex admittance was measured between an electrode pair and a pVAD metallic blood-intake tip, both with finite element analysis and on the benchtop. The catheter and electrode arrays were first simulated inside prolate ellipsoid models of the left ventricle (LV) demonstrating current flow throughout all parts of the LV as well as minimal influence of off-center catheter placement in the recorded signal. Admittance measurements were validated in 3D-printed models of healthy and dilated hearts (100-400 mL end-diastolic volumes). Minimal interference between a pVAD motor and the current signal of our admittance system was demonstrated. A modified Wei's equation focused on three electrodes was developed to be compatible with reduced profile pVADs occurring clinically, incorporated with admittance electrodes and wires. The modified equation was compared against Wei's original equation showing improved accuracy of calculated volumes. Reducing electrode footprint can simplify the incorporation of Admittance technology on any pVAD, allowing for instantaneous recognition of native heart recovery and assistance with pVAD weaning.