Bioengineering

Platelet-rich plasma (PRP) preparations have recently become widely available in sports medicine, facilitating their use in regenerative therapy for ligament and tendon affections. Quality-oriented regulatory constraints for PRP manufacturing and available clinical experiences have underlined the critical importance of process-based standardization, a pre-requisite for sound and homogeneous clinical efficacy evaluation. This retrospective study (2013–2020) considered the standardized GMP manufacturing and sports medicine-related clinical use of autologous PRP for tendinopathies at the Lausanne University Hospital (Lausanne, Switzerland). This study included 48 patients (18–86 years of age, with a mean age of 43.4 years, and various physical activity levels), and the related PRP manufacturing records indicated a platelet concentration factor most frequently in the range of 2.0–2.5. The clinical follow-up showed that 61% of the patients reported favorable efficacy outcomes (full return to activity, with pain disappearance) following a single ultrasound-guided autologous PRP injection, whereas 36% of the patients required two PRP injections. No significant relationship was found between platelet concentration factor values in PRP preparations and clinical efficacy endpoints of the intervention. The results were in line with published reports on tendinopathy management in sports medicine, wherein the efficacy of low-concentration orthobiologic interventions appears to be unrelated to sport activity levels or to patient age and gender. Overall, this study confirmed the effectiveness of standardized autologous PRP preparations for tendinopathies in sports medicine. The results were discussed in light of the critical importance of protocol standardization for both PRP manufacturing and clinical administration to reduce biological material variability (platelet concentrations) and to enhance the robustness of clinical interventions (comparability of efficacy/patient improvement). Full article

Purpose: The assessment of sleep biomechanics (comprising movement and position during sleep) is of interest in a wide variety of clinical and research settings. However, there is no standard method by which sleep biomechanics are measured. This study aimed to (1) compare the intra- and inter-rater reliability of the current clinical standard, manually coded overnight videography, and (2) compare sleep position recorded using overnight videography to sleep position recorded using the XSENS DOT wearable sensor platform. Methods: Ten healthy adult volunteers slept for one night with XSENS DOT units in situ (on their chest, pelvis, and left and right thighs), with three infrared video cameras recording concurrently. Ten clips per participant were edited from the video. Sleeping position in each clip was coded by six experienced allied health professionals using the novel Body Orientation During Sleep (BODS) Framework, comprising 12 sections in a 360-degree circle. Intra-rater reliability was assessed by calculating the differences between the BODS ratings from repeated clips and the percentage who were rated with a maximum of one section of the XSENS DOT value; the same methodology was used to establish the level of agreement between the XSENS DOT and allied health professional ratings of overnight videography. Bennett’s S-Score was used to assess inter-rater reliability. Results: High intra-rater reliability (90% of ratings with maximum difference of one section) and moderate inter-rater reliability (Bennett’s S-Score 0.466 to 0.632) were demonstrated in the BODS ratings. The raters demonstrated high levels of agreement overall with the XSENS DOT platform, with 90% of ratings from allied health raters being within the range of at least 1 section of the BODS (as compared to the corresponding XSENS DOT produced rating). Conclusions: The current clinical standard for assessing sleep biomechanics, manually rated overnight videography (as rated using the BODS Framework) demonstrated acceptable intra- and inter-rater reliability. Further, the XSENS DOT platform demonstrated satisfactory levels of agreement as compared to the current clinical standard, providing confidence for its use in future studies of sleep biomechanics. Full article

Optical coherence tomography (OCT) is a noninvasive imaging technique that provides high-resolution cross-sectional retina images, enabling ophthalmologists to gather crucial information for diagnosing various retinal diseases. Despite its benefits, manual analysis of OCT images is time-consuming and heavily dependent on the personal experience of the analyst. This paper focuses on using machine learning to analyse OCT images in the clinical interpretation of retinal diseases. The complexity of understanding the biomarkers present in OCT images has been a challenge for many researchers, particularly those from nonclinical disciplines. This paper aims to provide an overview of the current state-of-the-art OCT image processing techniques, including image denoising and layer segmentation. It also highlights the potential of machine learning algorithms to automate the analysis of OCT images, reducing time consumption and improving diagnostic accuracy. Using machine learning in OCT image analysis can mitigate the limitations of manual analysis methods and provide a more reliable and objective approach to diagnosing retinal diseases. This paper will be of interest to ophthalmologists, researchers, and data scientists working in the field of retinal disease diagnosis and machine learning. By presenting the latest advancements in OCT image analysis using machine learning, this paper will contribute to the ongoing efforts to improve the diagnostic accuracy of retinal diseases. Full article

Background: Bio-signals are the essential data that smart healthcare systems require for diagnosing and treating common diseases. However, the amount of these signals that need to be processed and analyzed by healthcare systems is huge. Dealing with such a vast amount of data presents difficulties, such as the need for high storage and transmission capabilities. In addition, retaining the most useful clinical information in the input signal is essential while applying compression. Methods: This paper proposes an algorithm for the efficient compression of bio-signals for IoMT applications. This algorithm extracts the features of the input signal using block-based HWT and then selects the most important features for reconstruction using the novel COVIDOA. Results: We utilized two different public datasets for evaluation: MIT-BIH arrhythmia and EEG Motor Movement/Imagery, for ECG and EEG signals, respectively. The proposed algorithm’s average values for CR, PRD, NCC, and QS are 18.06, 0.2470, 0.9467, and 85.366 for ECG signals and 12.6668, 0.4014, 0.9187, and 32.4809 for EEG signals. Further, the proposed algorithm shows its efficiency over other existing techniques regarding processing time. Conclusions: Experiments show that the proposed method successfully achieved a high CR while maintaining an excellent level of signal reconstruction in addition to its reduced processing time compared with the existing techniques. Full article

Anomaly detection is a significant task in sensors’ signal processing since interpreting an abnormal signal can lead to making a high-risk decision in terms of sensors’ applications. Deep learning algorithms are effective tools for anomaly detection due to their capability to address imbalanced datasets. In this study, we took a semi-supervised learning approach, utilizing normal data for training the deep learning neural networks, in order to address the diverse and unknown features of anomalies. We developed autoencoder-based prediction models to automatically detect anomalous data recorded by three electrochemical aptasensors, with variations in the signals’ lengths for particular concentrations, analytes, and bioreceptors. Prediction models employed autoencoder networks and the kernel density estimation (KDE) method for finding the threshold to detect anomalies. Moreover, the autoencoder networks were vanilla, unidirectional long short-term memory (ULSTM), and bidirectional LSTM (BLSTM) autoencoders for the training stage of the prediction models. However, the decision-making was based on the result of these three networks and the integration of vanilla and LSTM networks’ results. The accuracy as a performance metric of anomaly prediction models showed that the performance of vanilla and integrated models were comparable, while the LSTM-based autoencoder models showed the least accuracy. Considering the integrated model of ULSTM and vanilla autoencoder, the accuracy for the dataset with the lengthier signals was approximately 80%, while it was 65% and 40% for the other datasets. The lowest accuracy belonged to the dataset with the least normal data in its dataset. These results demonstrate that the proposed vanilla and integrated models can automatically detect abnormal data when there is sufficient normal data for training the models. Full article

Artificial intelligence (AI) has the potential to assist in endoscopy and improve decision making, particularly in situations where humans may make inconsistent judgments. The performance assessment of the medical devices operating in this context is a complex combination of bench tests, randomized controlled trials, and studies on the interaction between physicians and AI. We review the scientific evidence published about GI Genius, the first AI-powered medical device for colonoscopy to enter the market, and the device that is most widely tested by the scientific community. We provide an overview of its technical architecture, AI training and testing strategies, and regulatory path. In addition, we discuss the strengths and limitations of the current platform and its potential impact on clinical practice. The details of the algorithm architecture and the data that were used to train the AI device have been disclosed to the scientific community in the pursuit of a transparent AI. Overall, the first AI-enabled medical device for real-time video analysis represents a significant advancement in the use of AI for endoscopies and has the potential to improve the accuracy and efficiency of colonoscopy procedures. Full article

The mechanisms underlying the altered postural control and risk of falling in patients with osteoporosis are not yet fully understood. The aim of the present study was to investigate postural sway in women with osteoporosis and a control group. The postural sway of 41 women with osteoporosis (17 fallers and 24 non-fallers) and 19 healthy controls was measured in a static standing task with a force plate. The amount of sway was characterized by traditional (linear) center-of-pressure (COP) parameters. Structural (nonlinear) COP methods include spectral analysis by means of a 12-level wavelet transform and a regularity analysis via multiscale entropy (MSE) with determination of the complexity index. Patients showed increased body sway in the medial–lateral (ML) direction (standard deviation in mm: 2.63 ± 1.00 vs. 2.00 ± 0.58, p = 0.021; range of motion in mm: 15.33 ± 5.58 vs. 10.86 ± 3.14, p = 0.002) and more irregular sway in the anterior–posterior (AP) direction (complexity index: 13.75 ± 2.19 vs. 11.18 ± 4.44, p = 0.027) relative to controls. Fallers showed higher-frequency responses than non-fallers in the AP direction. Thus, postural sway is differently affected by osteoporosis in the ML and AP directions. Clinically, effective assessment and rehabilitation of balance disorders can benefit from an extended analysis of postural control with nonlinear methods, which may also contribute to the improvement of risk profiles or a screening tool for the identification of high-risk fallers, thereby prevent fractures in women with osteoporosis. Full article

The low bioavailability of orally administered drugs as a result of the instability in the gastrointestinal tract environment creates significant challenges to developing site-targeted drug delivery systems. This study proposes a novel hydrogel drug carrier using pH-responsive materials assisted with semi-solid extrusion 3D printing technology, enabling site-targeted drug release and customisation of temporal release profiles. The effects of material parameters on the pH-responsive behaviours of printed tablets were analysed thoroughly by investigating the swelling properties under both artificial gastric and intestinal fluids. It has been shown that high swelling rates at either acidic or alkaline conditions can be achieved by adjusting the mass ratio between sodium alginate and carboxymethyl chitosan, enabling site-targeted release. The drug release experiments reveal that gastric drug release can be achieved with a mass ratio of 1:3, whilst a ratio of 3:1 allows for intestinal release. Furthermore, controlled release is realised by tuning the infill density of the printing process. The method proposed in this study can not only significantly improve the bioavailability of oral drugs, but also offer the potential that each component of a compound drug tablet can be released in a controlled manner at a target location. Full article

Breast cancer conservative treatment (BCCT) is a form of treatment commonly used for patients with early breast cancer. This procedure consists of removing the cancer and a small margin of surrounding tissue, while leaving the healthy tissue intact. In recent years, this procedure has become increasingly common due to identical survival rates and better cosmetic outcomes than other alternatives. Although significant research has been conducted on BCCT, there is no gold-standard for evaluating the aesthetic results of the treatment. Recent works have proposed the automatic classification of cosmetic results based on breast features extracted from digital photographs. The computation of most of these features requires the representation of the breast contour, which becomes key to the aesthetic evaluation of BCCT. State-of-the-art methods use conventional image processing tools that automatically detect breast contours based on the shortest path applied to the Sobel filter result in a 2D digital photograph of the patient. However, because the Sobel filter is a general edge detector, it treats edges indistinguishably, i.e., it detects too many edges that are not relevant to breast contour detection and too few weak breast contours. In this paper, we propose an improvement to this method that replaces the Sobel filter with a novel neural network solution to improve breast contour detection based on the shortest path. The proposed solution learns effective representations for the edges between the breasts and the torso wall. We obtain state of the art results on a dataset that was used for developing previous models. Furthermore, we tested these models on a new dataset that contains more variable photographs and show that this new approach shows better generalization capabilities as the previously developed deep models do not perform so well when faced with a different dataset for testing. The main contribution of this paper is to further improve the capabilities of models that perform the objective classification of BCCT aesthetic results automatically by improving upon the current standard technique for detecting breast contours in digital photographs. To that end, the models introduced are simple to train and test on new datasets which makes this approach easily reproducible. Full article

Cardiovascular disease (CVD) has become a common health problem of mankind, and the prevalence and mortality of CVD are rising on a year-to-year basis. Blood pressure (BP) is an important physiological parameter of the human body and also an important physiological indicator for the prevention and treatment of CVD. Existing intermittent measurement methods do not fully indicate the real BP status of the human body and cannot get rid of the restraining feeling of a cuff. Accordingly, this study proposed a deep learning network based on the ResNet34 framework for continuous prediction of BP using only the promising PPG signal. The high-quality PPG signals were first passed through a multi-scale feature extraction module after a series of pre-processing to expand the perceptive field and enhance the perception ability on features. Subsequently, useful feature information was then extracted by stacking multiple residual modules with channel attention to increase the accuracy of the model. Lastly, in the training stage, the Huber loss function was adopted to stabilize the iterative process and obtain the optimal solution of the model. On a subset of the MIMIC dataset, the errors of both SBP and DBP predicted by the model met the AAMI standards, while the accuracy of DBP reached Grade A of the BHS standard, and the accuracy of SBP almost reached Grade A of the BHS standard. The proposed method verifies the potential and feasibility of PPG signals combined with deep neural networks in the field of continuous BP monitoring. Furthermore, the method is easy to deploy in portable devices, and it is more consistent with the future trend of wearable blood-pressure-monitoring devices (e.g., smartphones and smartwatches). Full article

In-stent restenosis caused by tumor ingrowth increases the risk of secondary surgery for patients with abdominal aortic aneurysms (AAA) because conventional vascular stent grafts suffer from mechanical fatigue, thrombosis, and endothelial hyperplasia. For that, we report a woven vascular stent-graft with robust mechanical properties, biocompatibility, and drug delivery functions to inhibit thrombosis and the growth of AAA. Paclitaxel (PTX)/metformin (MET)-loaded silk fibroin (SF) microspheres were self-assembly synthesized by emulsification-precipitation technology and layer-by-layer coated on the surface of a woven stent via electrostatic bonding. The woven vascular stent-graft before and after coating drug-loaded membranes were characterized and analyzed systematically. The results show that small-sized drug-loaded microspheres increased the specific surface area and promoted the dissolution/release of drugs. The stent-grafts with drug-loaded membranes exhibited a slow drug-release profile more for than 70 h and low water permeability at 158.33 ± 17.56 mL/cm²·min. The combination of PTX and MET inhibited the growth of human umbilical vein endothelial cells. Therefore, it was possible to generate dual-drug-loaded woven vascular stent-grafts to achieve the more effective treatment of AAA. Full article

Yeast Saccharomyces cerevisiae may be regarded as a cost-effective and environmentally friendly biosorbent for complex effluent treatment. The effect of pH, contact time, temperature, and silver concentration on metal removal from silver-containing synthetic effluents using Saccharomyces cerevisiae was examined. The biosorbent before and after biosorption process was analysed using Fourier-transform infrared spectroscopy, scanning electron microscopy, and neutron activation analysis. Maximum removal of silver ions, which constituted 94–99%, was attained at the pH 3.0, contact time 60 min, and temperature 20 °C. High removal of copper, zinc, and nickel ions (63–100%) was obtained at pH 3.0–6.0. The equilibrium results were described using Langmuir and Freundlich isotherm, while pseudo-first-order and pseudo-second-order models were applied to explain the kinetics of the biosorption. The Langmuir isotherm model and the pseudo-second-order model fitted better experimental data with maximum adsorption capacity in the range of 43.6–108 mg/g. The negative Gibbs energy values pointed at the feasibility and spontaneous character of the biosorption process. The possible mechanisms of metal ions removal were discussed. Saccharomyces cerevisiae have all necessary characteristics to be applied to the development of the technology of silver-containing effluents treatment. Full article

Background: Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise. Objective: This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions. Method: This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications. Results: a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6). Conclusion: Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation. Full article

The segmentation and classification of cell nuclei are pivotal steps in the pipelines for the analysis of bioimages. Deep learning (DL) approaches are leading the digital pathology field in the context of nuclei detection and classification. Nevertheless, the features that are exploited by DL models to make their predictions are difficult to interpret, hindering the deployment of such methods in clinical practice. On the other hand, pathomic features can be linked to an easier description of the characteristics exploited by the classifiers for making the final predictions. Thus, in this work, we developed an explainable computer-aided diagnosis (CAD) system that can be used to support pathologists in the evaluation of tumor cellularity in breast histopathological slides. In particular, we compared an end-to-end DL approach that exploits the Mask R-CNN instance segmentation architecture with a two steps pipeline, where the features are extracted while considering the morphological and textural characteristics of the cell nuclei. Classifiers that are based on support vector machines and artificial neural networks are trained on top of these features in order to discriminate between tumor and non-tumor nuclei. Afterwards, the SHAP (Shapley additive explanations) explainable artificial intelligence technique was employed to perform a feature importance analysis, which led to an understanding of the features processed by the machine learning models for making their decisions. An expert pathologist validated the employed feature set, corroborating the clinical usability of the model. Even though the models resulting from the two-stage pipeline are slightly less accurate than those of the end-to-end approach, the interpretability of their features is clearer and may help build trust for pathologists to adopt artificial intelligence-based CAD systems in their clinical workflow. To further show the validity of the proposed approach, it has been tested on an external validation dataset, which was collected from IRCCS Istituto Tumori “Giovanni Paolo II” and made publicly available to ease research concerning the quantification of tumor cellularity. Full article

The aging process is a multifaceted phenomenon that affects cognitive-affective and physical functioning as well as interactions with the environment. Although subjective cognitive decline may be part of normal aging, negative changes objectified as cognitive impairment are present in neurocognitive disorders and functional abilities are most impaired in patients with dementia. Electroencephalography-based brain–machine interfaces (BMI) are being used to assist older people in their daily activities and to improve their quality of life with neuro-rehabilitative applications. This paper provides an overview of BMI used to assist older adults. Both technical issues (detection of signals, extraction of features, classification) and application-related aspects with respect to the users’ needs are considered. Full article

Tissue-engineered polymeric implants are preferable because they do not cause a significant inflammatory reaction in the surrounding tissue. Three-dimensional (3D) technology can be used to fabricate a customised scaffold, which is critical for implantation. This study aimed to investigate the biocompatibility of a mixture of thermoplastic polyurethane (TPU) and polylactic acid (PLA) and the effects of their extract in cell cultures and in animal models as potential tracheal replacement materials. The morphology of the 3D-printed scaffolds was investigated using scanning electron microscopy (SEM), while the degradability, pH, and effects of the 3D-printed TPU/PLA scaffolds and their extracts were investigated in cell culture studies. In addition, subcutaneous implantation of 3D-printed scaffold was performed to evaluate the biocompatibility of the scaffold in a rat model at different time points. A histopathological examination was performed to investigate the local inflammatory response and angiogenesis. The in vitro results showed that the composite and its extract were not toxic. Similarly, the pH of the extracts did not inhibit cell proliferation and migration. The analysis of biocompatibility of the scaffolds from the in vivo results suggests that porous TPU/PLA scaffolds may facilitate cell adhesion, migration, and proliferation and promote angiogenesis in host cells. The current results suggest that with 3D printing technology, TPU and PLA could be used as materials to construct scaffolds with suitable properties and provide a solution to the challenges of tracheal transplantation. Full article

Nuclei segmentation and classification are two basic and essential tasks in computer-aided diagnosis of digital pathology images, and those deep-learning-based methods have achieved significant success. Unfortunately, most of the existing studies accomplish the two tasks by splicing two related neural networks directly, resulting in repetitive computation efforts and a redundant-and-large neural network. Thus, this paper proposes a lightweight deep learning framework (GSN-HVNET) with an encoder–decoder structure for simultaneous segmentation and classification of nuclei. The decoder consists of three branches outputting the semantic segmentation of nuclei, the horizontal and vertical (HV) distances of nuclei pixels to their mass centers, and the class of each nucleus, respectively. The instance segmentation results are obtained by combing the outputs of the first and second branches. To reduce the computational cost and improve the network stability under small batch sizes, we propose two newly designed blocks, Residual-Ghost-SN (RGS) and Dense-Ghost-SN (DGS). Furthermore, considering the practical usage in pathological diagnosis, we redefine the classification principle of the CoNSeP dataset. Experimental results demonstrate that the proposed model outperforms other state-of-the-art models in terms of segmentation and classification accuracy by a significant margin while maintaining high computational efficiency. Full article

Pentalenene is a ternary cyclic sesquiterpene formed via the ionization and cyclization of farnesyl pyrophosphate (FPP), which is catalyzed by pentalenene synthase (PentS). To better understand the cyclization reactions, it is necessary to identify more key sites and elucidate their roles in terms of catalytic activity and product specificity control. Previous studies primarily relied on the crystal structure of PentS to analyze and verify critical active sites in the active cavity, while this study started with the function of PentS and screened a novel key site through random mutagenesis. In this study, we constructed a pentalenene synthetic pathway in E. coli BL21(DE3) and generated PentS variants with random mutations to construct a mutant library. A mutant, PentS-13, with a varied product diversity, was obtained through shake-flask fermentation and product identification. After sequencing and the functional verification of the mutation sites, it was found that T182A, located in the G2 helix, was responsible for the phenotype of PentS-13. The site-saturation mutagenesis of T182 demonstrated that mutations at this site not only affected the solubility and activity of the enzyme but also affected the specificity of the product. The other products were generated through different routes and via different carbocation intermediates, indicating that the 182 active site is crucial for PentS to stabilize and guide the regioselectivity of carbocations. Molecular docking and molecular dynamics simulations suggested that these mutations may induce changes in the shape and volume of the active cavity and disturb hydrophobic/polar interactions that were sufficient to reposition reactive intermediates for alternative reaction pathways. This article provides rational explanations for these findings, which may generally allow for the protein engineering of other terpene synthases to improve their catalytic efficiency or modify their specificities. Full article

The recent COVID-19 pandemic has highlighted the inadequacies of existing diagnostic techniques and the need for rapid and accurate diagnostic systems. Although molecular tests such as RT-PCR are the gold standard, they cannot be employed as point-of-care testing systems. Hence, a rapid, noninvasive diagnostic technique such as Surface-enhanced Raman scattering (SERS) is a promising analytical technique for rapid molecular or viral diagnosis. Here, we have designed a SERS- based test to rapidly diagnose SARS-CoV-2 from saliva. Physical methods synthesized the nanostructured sensor. It significantly increased the detection specificity and sensitivity by ~ten copies/mL of viral RNA (~femtomolar concentration of nucleic acids). Our technique combines the multiplexing capability of SERS with the sensitivity of novel nanostructures to detect whole virus particles and infection-associated antibodies. We have demonstrated the feasibility of the test with saliva samples from individuals who tested positive for SARS-CoV-2 with a specificity of 95%. The SERS—based test provides a promising breakthrough in detecting potential mutations that may come up with time while also preparing the world to deal with other pandemics in the future with rapid response and very accurate results. Full article