Journal of Medical Engineering and Technology最新文献

Nowadays, photoplethysmograph (PPG) technology is being used more often in smart devices and mobile phones due to advancements in information and communication technology in the health field, particularly in monitoring cardiac activities. Developing generative models to generate synthetic PPG signals requires overcoming challenges like data diversity and limited data available for training deep learning models. This paper proposes a generative model by adopting a genetic programming (GP) approach to generate increasingly diversified and accurate data using an initial PPG signal sample. Unlike conventional regression, the GP approach automatically determines the structure and combinations of a mathematical model. Given that mean square error (MSE) of 0.0001, root mean square error (RMSE) of 0.01, and correlation coefficient of 0.999, the proposed approach outperformed other approaches and proved effective in terms of efficiency and applicability in resource-constrained environments.

The conventional detection of COVID-19 by evaluating the CT scan images is tiresome, often experiences high inter-observer variability and uncertainty issues. This work proposes the automatic detection and classification of COVID-19 by analysing the chest X-ray images (CXR) with the deep convolutional neural network (DCNN) models through a fine-tuning and pre-training approach. CXR images pertaining to four health scenarios, namely, healthy, COVID-19, bacterial pneumonia and viral pneumonia, are considered and subjected to data augmentation. Two types of input datasets are prepared; in which dataset I contains the original image dataset categorised under four classes, whereas the original CXR images are subjected to image pre-processing via Contrast Limited Adaptive Histogram Equalisation (CLAHE) algorithm and Blackhat Morphological Operation (BMO) for devising the input dataset II. Both datasets are supplied as input to various DCNN models such as DenseNet, MobileNet, ResNet, VGG16, and Xception for achieving multi-class classification. It is observed that the classification accuracies are improved, and the classification errors are reduced with the image pre-processing. Overall, the VGG16 model resulted in better classification accuracies and reduced classification errors while accomplishing multi-class classification. Thus, the proposed work would assist the clinical diagnosis, and reduce the workload of the front-line healthcare workforce and medical professionals.

This study assessed the safety, feasibility, and acceptability of a novel device to monitor ischaemic stroke patients. The device captured electroencephalography (EEG) and electrocardiography (ECG) data to compute an ECG-based metric, termed the Electrocardiography Brain Perfusion index (EBPi), which may function as a proxy for cerebral blood flow (CBF). Seventeen ischaemic stroke patients wore the device for nine hours and reported feedback at 1, 3, 6 and 9 h regarding user experience, comfort, and satisfaction (acceptability). Safety was assessed as the number of adverse events reported. Feasibility was assessed as the percentage of uninterrupted EEG/ECG data recorded (data capture efficiency). No adverse events were reported, only minor incidences of discomfort. Overall device comfort (mean ± 1 standard deviation (SD) (range)) (92.5% ± 10.3% (57.0-100%)) and data capture efficiency (mean ± 1 SD (range)) (95.8% ± 6.8% (54.8-100%)) were very high with relatively low variance. The device didn't restrict participants from receiving clinical care and rarely (n = 6) restricted participants from undertaking routine tasks. This study provides a promising evidence base for the deployment of the device in a clinical setting. If clinically validated, EBPi may be able to detect CBF changes to monitor early neurological deterioration and treatment outcomes, thus filling an important gap in current monitoring options.TRIAL REGISTRATION: The study was prospectively registered with the Australian New Zealand Clinical Trials Registry (ACTRN12622000112763).

Mg alloy is one of the most suitable biodegradable materials for making modern LCP. This is due to the osseointegration property, low elastic modulus, the presence in the human bone, and the excellent biodegradable nature. But it lacks much-needed strength compared to conventional (Ti, SS alloys) implants due to low strength of biodegradable (Mg, Zn alloys) materials. The problem can be solved by either biodegradable material development or by design improvement of existing LCP. Improving the design is a better way to improve the LCP. This paper aims to improve the design of existing LCP through the addition of features and their implications by analysing the stress distribution across the plates for improved biodegradable implant mechanical performance. Various designs have been developed and each has certain advantages over conventional LCP which ACT and 4PBT have been demonstrated via the FEM. They are best suited for femur bone fracture treatment replacing conventional metal alloys LCP. The CTLCP, SLCP, and SELCP have improved performance at stress concentration regions while STLCP especially has 36.74% less stress generation than conventional LCP along with excellent biodegradable performance. The designs are discussed in detail to analyse the effect of added features in conventional LCP.

An early detection of lung tumors is critical for better treatment results, and CT scans can reveal lumps in the lungs which are too small to be picked up by conventional X-rays. CT imaging has advantages, but it also exposes a person to radiation from ions, which raises the possibility of malignancy, particularly when the imaging procedure is done. Access to expensive-quality CT scans and the related sophisticated analytic tools might be restricted in environments with fewer resources due to their high cost and limited availability. It will need an array of creative technological innovations to overcome such weaknesses. This paper aims to design a heuristic and deep learning-aided lung cancer classification using CT images. The collected images are undergone for segmentation, which is performed by Shuffling Atrous Convolutional (SAC) based ResUnet++ (SACRUnet++). Finally, the lung cancer classification is performed by the Adaptive Residual Attention Network (ARAN) by inputting the segmented images. Here the parameters of ARAN are optimally tuned using the Improved Garter Snake Optimization Algorithm (IGSOA). The developed lung cancer classification performance is compared to conventional lung cancer classification models and it showed high accuracy.

This paper delves into the diverse applications and transformative impact of additive manufacturing (AM) in biomedical engineering. A detailed analysis of various AM technologies showcases their distinct capabilities and specific applications within the medical field. Special emphasis is placed on bioprinting of organs and tissues, a revolutionary area where AM has the potential to revolutionize organ transplantation and regenerative medicine by fabricating functional tissues and organs. The review further explores the customization of implants and prosthetics, demonstrating how tailored medical devices enhance patient comfort and performance. Additionally, the utility of AM in surgical planning is examined, highlighting how printed models contribute to increased surgical precision, reduced operating times, and minimized complications. The discussion extends to the 3D printing of surgical instruments, showcasing how these bespoke tools can improve surgical outcomes. Moreover, the integration of AM in drug delivery systems, including the development of innovative drug-loaded implants, underscores its potential to enhance therapeutic efficacy and reduce side effects. It also addresses personalized prosthetic implants, regulatory frameworks, biocompatibility concerns, and the future potential of AM in global health and sustainable practices.