Functional regeneration at the blood-biomaterial interface.

The use of cardiovascular implants is commonplace in clinical practice. However, reproducing the key bioactive and adaptive properties of native cardiovascular tissues with an artificial replacement is highly challenging. Exciting new treatment strategies are under development to regenerate (parts of) cardiovascular tissues directly in situ using immunomodulatory biomaterials. Direct exposure to the bloodstream and hemodynamic loads is a particular challenge, given the risk of thrombosis and adverse remodeling that it brings. However, the blood is also a source of (immune) cells and proteins that dominantly contribute to functional tissue regeneration. This review explores the potential of the blood as a source for the complete or partial in situ regeneration of cardiovascular tissues, with a particular focus on the endothelium, being the natural blood-tissue barrier. We pinpoint the current scientific challenges to enable rational engineering and testing of blood-contacting implants to leverage the regenerative potential of the blood.

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning.

Driver drowsiness is one of the main causes of traffic accidents today. In recent years, driver drowsiness detection has suffered from issues integrating deep learning (DL) with Internet-of-things (IoT) devices due to the limited resources of IoT devices, which pose a challenge to fulfilling DL models that demand large storage and computation. Thus, there are challenges to meeting the requirements of real-time driver drowsiness detection applications that need short latency and lightweight computation. To this end, we applied Tiny Machine Learning (TinyML) to a driver drowsiness detection case study. In this paper, we first present an overview of TinyML. After conducting some preliminary experiments, we proposed five lightweight DL models that can be deployed on a microcontroller. We applied three DL models: SqueezeNet, AlexNet, and CNN. In addition, we adopted two pretrained models (MobileNet-V2 and MobileNet-V3) to find the best model in terms of size and accuracy results. After that, we applied the optimization methods to DL models using quantization. Three quantization methods were applied: quantization-aware training (QAT), full-integer quantization (FIQ), and dynamic range quantization (DRQ). The obtained results in terms of the model size show that the CNN model achieved the smallest size of 0.05 MB using the DRQ method, followed by SqueezeNet, AlexNet MobileNet-V3, and MobileNet-V2, with 0.141 MB, 0.58 MB, 1.16 MB, and 1.55 MB, respectively. The result after applying the optimization method was 0.9964 accuracy using DRQ in the MobileNet-V2 model, which outperformed the other models, followed by the SqueezeNet and AlexNet models, with 0.9951 and 0.9924 accuracies, respectively, using DRQ.

Augmenting healthy brain magnetic resonance images using generative adversarial networks.

Machine learning applications in the medical sector face a lack of medical data due to privacy issues. For instance, brain tumor image-based classification suffers from the lack of brain images. The lack of such images produces some classification problems, i.e., class imbalance issues which can cause a bias toward one class over the others. This study aims to solve the imbalance problem of the "no tumor" class in the publicly available brain magnetic resonance imaging (MRI) dataset. Generative adversarial network (GAN)-based augmentation techniques were used to solve the imbalance classification problem. Specifically, deep convolutional GAN (DCGAN) and single GAN (SinGAN). Moreover, the traditional-based augmentation techniques were implemented using the rotation method. Thus, several VGG16 classification experiments were conducted, including (i) the original dataset, (ii) the DCGAN-based dataset, (iii) the SinGAN-based dataset, (iv) a combination of the DCGAN and SinGAN dataset, and (v) the rotation-based dataset. However, the results show that the original dataset achieved the highest accuracy, 73%. Additionally, SinGAN outperformed DCGAN by a significant margin of 4%. In contrast, experimenting with the non-augmented original dataset resulted in the highest classification loss value, which explains the effect of the imbalance issue. These results provide a general view of the effect of different image augmentation techniques on enlarging the healthy brain dataset.

Deep-Risk: Deep Learning-Based Mortality Risk Predictive Models for COVID-19.

The SARS-CoV-2 virus has proliferated around the world and caused panic to all people as it claimed many lives. Since COVID-19 is highly contagious and spreads quickly, an early diagnosis is essential. Identifying the COVID-19 patients' mortality risk factors is essential for reducing this risk among infected individuals. For the timely examination of large datasets, new computing approaches must be created. Many machine learning (ML) techniques have been developed to predict the mortality risk factors and severity for COVID-19 patients. Contrary to expectations, deep learning approaches as well as ML algorithms have not been widely applied in predicting the mortality and severity from COVID-19. Furthermore, the accuracy achieved by ML algorithms is less than the anticipated values. In this work, three supervised deep learning predictive models are utilized to predict the mortality risk and severity for COVID-19 patients. The first one, which we refer to as CV-CNN, is built using a convolutional neural network (CNN); it is trained using a clinical dataset of 12,020 patients and is based on the 10-fold cross-validation (CV) approach for training and validation. The second predictive model, which we refer to as CV-LSTM + CNN, is developed by combining the long short-term memory (LSTM) approach with a CNN model. It is also trained using the clinical dataset based on the 10-fold CV approach for training and validation. The first two predictive models use the clinical dataset in its original CSV form. The last one, which we refer to as IMG-CNN, is a CNN model and is trained alternatively using the converted images of the clinical dataset, where each image corresponds to a data row from the original clinical dataset. The experimental results revealed that the IMG-CNN predictive model outperforms the other two with an average accuracy of 94.14%, a precision of 100%, a recall of 91.0%, a specificity of 100%, an F1-score of 95.3%, an AUC of 93.6%, and a loss of 0.22.

TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications.

Recently, the Internet of Things (IoT) has gained a lot of attention, since IoT devices are placed in various fields. Many of these devices are based on machine learning (ML) models, which render them intelligent and able to make decisions. IoT devices typically have limited resources, which restricts the execution of complex ML models such as deep learning (DL) on them. In addition, connecting IoT devices to the cloud to transfer raw data and perform processing causes delayed system responses, exposes private data and increases communication costs. Therefore, to tackle these issues, there is a new technology called Tiny Machine Learning (TinyML), that has paved the way to meet the challenges of IoT devices. This technology allows processing of the data locally on the device without the need to send it to the cloud. In addition, TinyML permits the inference of ML models, concerning DL models on the device as a Microcontroller that has limited resources. The aim of this paper is to provide an overview of the revolution of TinyML and a review of tinyML studies, wherein the main contribution is to provide an analysis of the type of ML models used in tinyML studies; it also presents the details of datasets and the types and characteristics of the devices with an aim to clarify the state of the art and envision development requirements.

BrainGAN: Brain MRI Image Generation and Classification Framework Using GAN Architectures and CNN Models.

Deep learning models have been used in several domains, however, adjusting is still required to be applied in sensitive areas such as medical imaging. As the use of technology in the medical domain is needed because of the time limit, the level of accuracy assures trustworthiness. Because of privacy concerns, machine learning applications in the medical field are unable to use medical data. For example, the lack of brain MRI images makes it difficult to classify brain tumors using image-based classification. The solution to this challenge was achieved through the application of Generative Adversarial Network (GAN)-based augmentation techniques. Deep Convolutional GAN (DCGAN) and Vanilla GAN are two examples of GAN architectures used for image generation. In this paper, a framework, denoted as BrainGAN, for generating and classifying brain MRI images using GAN architectures and deep learning models was proposed. Consequently, this study proposed an automatic way to check that generated images are satisfactory. It uses three models: CNN, MobileNetV2, and ResNet152V2. Training the deep transfer models with images made by Vanilla GAN and DCGAN, and then evaluating their performance on a test set composed of real brain MRI images. From the results of the experiment, it was found that the ResNet152V2 model outperformed the other two models. The ResNet152V2 achieved 99.09% accuracy, 99.12% precision, 99.08% recall, 99.51% area under the curve (AUC), and 0.196 loss based on the brain MRI images generated by DCGAN architecture.

The use of statistical and machine learning tools to accurately quantify the energy performance of residential buildings.

Prediction of building energy consumption is key to achieving energy efficiency and sustainability. Nowadays, the analysis or prediction of building energy consumption using building energy simulation tools facilitates the design and operation of energy-efficient buildings. The collection and generation of building data are essential components of machine learning models; however, there is still a lack of such data covering certain weather conditions. Such as those related to arid climate areas. This paper fills this identified gap with the creation of a new dataset for energy consumption of 3,840 records of typical residential buildings of the Saudi Arabia region of Qassim, and investigates the impact of residential buildings' eight input variables (Building Size, Floor Height, Glazing Area, Wall Area, window to wall ratio (WWR), Win Glazing U-value, Roof U-value, and External Wall U-value) on the heating load (HL) and cooling load (CL) output variables. A number of classical and non-parametric statistical tools are used to uncover the most strongly associated input variables with each one of the output variables. Then, the machine learning Multiple linear regression (MLR) and Multilayer perceptron (MLP) methods are used to estimate HL and CL, and their results compared using the Mean Absolute Error (MAE), the Root Mean Square Error (RMSE), and coefficient of determination (R2) performance measures. The use of the IES simulation software on the new dataset concludes that MLP accurately estimates both HL and CL with low MAE, RMSE, and R2, which evidences the feasibility and accuracy of applying machine learning methods to estimate building energy consumption.

Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases.

Corona Virus Disease (COVID-19) has been announced as a pandemic and is spreading rapidly throughout the world. Early detection of COVID-19 may protect many infected people. Unfortunately, COVID-19 can be mistakenly diagnosed as pneumonia or lung cancer, which with fast spread in the chest cells, can lead to patient death. The most commonly used diagnosis methods for these three diseases are chest X-ray and computed tomography (CT) images. In this paper, a multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer from a combination of chest x-ray and CT images is proposed. This combination has been used because chest X-ray is less powerful in the early stages of the disease, while a CT scan of the chest is useful even before symptoms appear, and CT can precisely detect the abnormal features that are identified in images. In addition, using these two types of images will increase the dataset size, which will increase the classification accuracy. To the best of our knowledge, no other deep learning model choosing between these diseases is found in the literature. In the present work, the performance of four architectures are considered, namely: VGG19-CNN, ResNet152V2, ResNet152V2 + Gated Recurrent Unit (GRU), and ResNet152V2 + Bidirectional GRU (Bi-GRU). A comprehensive evaluation of different deep learning architectures is provided using public digital chest x-ray and CT datasets with four classes (i.e., Normal, COVID-19, Pneumonia, and Lung cancer). From the results of the experiments, it was found that the VGG19 +CNN model outperforms the three other proposed models. The VGG19+CNN model achieved 98.05% accuracy (ACC), 98.05% recall, 98.43% precision, 99.5% specificity (SPC), 99.3% negative predictive value (NPV), 98.24% F1 score, 97.7% Matthew's correlation coefficient (MCC), and 99.66% area under the curve (AUC) based on X-ray and CT images.

Nanoengineered shear-thinning and bioprintable hydrogel as a versatile platform for biomedical applications.

The development of bioinks based on shear-thinning and self-healing hydrogels has recently attracted significant attention for constructing complex three-dimensional physiological microenvironments. For extrusion-based bioprinting, it is challenging to provide high structural reliability and resolution of printed structures while protecting cells from shear forces during printing. Herein, we present shear-thinning and printable hydrogels based on silicate nanomaterials, laponite (LA), and glycosaminoglycan nanoparticles (GAGNPs) for bioprinting applications. Nanocomposite hydrogels (GLgels) were rapidly formed within seconds due to the interactions between the negatively charged groups of GAGNPs and the edges of LA. The shear-thinning behavior of the hydrogel protected encapsulated cells from aggressive shear stresses during bioprinting. The bioinks could be printed straightforwardly into shape-persistent and free-standing structures with high aspect ratios. Rheological studies demonstrated fast recovery of GLgels over multiple strain cycles. In vitro studies confirmed the ability of GLgels to support cell growth, proliferation, and spreading. In vitro osteogenic differentiation of pre-osteoblasts murine bone marrow stromal cells encapsulated inside the GLgels was also demonstrated through evaluation of ALP activity and calcium deposition. The subcutaneous implantation of the GLgel in rats confirmed its in vivo biocompatibility and biodegradability. The engineered shear-thinning hydrogel with osteoinductive characteristics can be used as a new bioink for 3D printing of constructs for bone tissue engineering applications.

Deep-Pneumonia Framework Using Deep Learning Models Based on Chest X-Ray Images.

Pneumonia is a contagious disease that causes ulcers of the lungs, and is one of the main reasons for death among children and the elderly in the world. Several deep learning models for detecting pneumonia from chest X-ray images have been proposed. One of the extreme challenges has been to find an appropriate and efficient model that meets all performance metrics. Proposing efficient and powerful deep learning models for detecting and classifying pneumonia is the main purpose of this work. In this paper, four different models are developed by changing the used deep learning method; two pre-trained models, ResNet152V2 and MobileNetV2, a Convolutional Neural Network (CNN), and a Long Short-Term Memory (LSTM). The proposed models are implemented and evaluated using Python and compared with recent similar research. The results demonstrate that our proposed deep learning framework improves accuracy, precision, F1-score, recall, and Area Under the Curve (AUC) by 99.22%, 99.43%, 99.44%, 99.44%, and 99.77%, respectively. As clearly illustrated from the results, the ResNet152V2 model outperforms other recently proposed works. Moreover, the other proposed models-MobileNetV2, CNN, and LSTM-CNN-achieved results with more than 91% in accuracy, recall, F1-score, precision, and AUC, and exceed the recently introduced models in the literature.

Ciprofloxacin-loaded bioadhesive hydrogels for ocular applications.

The management of corneal infections often requires complex therapeutic regimens involving the prolonged and high-frequency application of antibiotics that provide many challenges to patients and impact compliance with the therapeutic regimens. In the context of severe injuries that lead to tissue defects (e.g. corneal lacerations) topical drug regimens are inadequate and suturing is often indicated. There is thus an unmet need for interventions that can provide tissue closure while concurrently preventing or treating infection. In this study, we describe the development of an antibacterial bioadhesive hydrogel loaded with micelles containing ciprofloxacin (CPX) for the management of corneal injuries at risk of infection. The in vitro release profile showed that the hydrogel system can release CPX, a broad-spectrum antibacterial drug, for up to 24 h. Moreover, the developed CPX-loaded hydrogels exhibited excellent antibacterial properties against Staphylococcus aureus and Pseudomonas aeruginosa, two bacterial strains responsible for the most ocular infections. Physical characterization, as well as adhesion and cytocompatibility tests, were performed to assess the effect of CPX loading in the developed hydrogel. Results showed that CPX loading did not affect stiffness, adhesive properties, or cytocompatibility of hydrogels. The efficiency of the antibacterial hydrogel was assessed using an ex vivo model of infectious pig corneal injury. Corneal tissues treated with the antibacterial hydrogel showed a significant decrease in bacterial colony-forming units (CFU) and a higher corneal epithelial viability after 24 h as compared to non-treated corneas and corneas treated with hydrogel without CPX. These results suggest that the developed adhesive hydrogel system presents a promising suture-free solution to seal corneal wounds while preventing infection.

New benzenesulfonamide scaffold-based cytotoxic agents: Design, synthesis, cell viability, apoptotic activity and radioactive tracing studies.

A new series of thiazolidinone (5a-g), thiazinone (9a-g) and dithiazepinone (9a-g) heterocycles bearing a benzenesulfonamide scaffold was synthesized. Cytotoxicity of these derivatives was assessed against MCF-7, HepG2, HCT-116 and A549 cancer cell lines and activity was compared to the known cytotoxic agents doxorubicin and 5-FU where the most active compounds displayed better to nearly similar IC50 values to the reference compounds. For assessing selectivity, the most active derivatives against MCF-7, 5b, 5c and 5e, were also assessed against the normal breast cell line MCF-10 A where they demonstrated high selective cytotoxicity to cancerous cells over that to normal cells. Further, the effect of the most active compounds 5b-e on MCF-7 and HepG2 cell cycle phase distribution was assessed and the tested sulfonamide derivatives were found to induce accumulation of cells in the <2n phase. To further confirm apoptosis induction, caspase 8 and 9 levels in MCF-7 and HepG2 were evaluated before and after treatment with compounds 5b-e and were found to be significantly higher after exposure to the test agents. Since 5c was the most active, its effect on the cell cycle regulation was confirmed where it showed inhibition of the CDK2/cyclin E1. Finally, in vivo biodistribution study using radioiodinated-5c revealed a significant uptake and targeting ability into solid tumor in a xenograft mouse model.

Bioactive and Elastic Nanocomposites with Antimicrobial Properties for Bone Tissue Regeneration.

Bone injuries represent a major challenge in the medical field. The commonly used treatments for bone regeneration rely on the use of bone grafts that are usually associated with complications such as donor site morbidity, disease transmission, high cost, and lack of availability. Bone tissue engineering has become a golden solution for the repair of bone injuries by regenerating the damaged biological tissues using biocompatible scaffolds. However, most of the tissue engineered scaffolds do not possess the combined properties of high elasticity, appropriate stiffness, biocompatibility, osteoinductivity, and antimicrobial properties. In this study, we engineered bioactive and antimicrobial nanocomposites that can promote bone formation while simultaneously provide a barrier against bacterial infections commonly associated with bone implants. We used PEGylated polyglycerol sebacate as nanocomposites base, which was functionalized with Laponite nanosilicates, a synthetic nanoclay, and an antimicrobial peptide (AMP). The successful synthesis of the PEGylated polyglycerol sebacate and Laponite incorporation within the nanocomposites were confirmed through nuclear magnetic resonance (NMR) and Fourier transform infrared spectroscopy (FTIR). The scaffolds had an elastic modulus and ultimate tensile strength within a range of 3.8-4.7 MPa and 1.5-3 MPa, respectively. Furthermore, the scaffolds loaded with antimicrobial peptide exhibited a significant antimicrobial activity against both Gram-negative (Escherichia coli) and Gram-positive (Staphylococcus aureus) bacteria. The in vitro cytocompatibility tests showed >90% viability of preosteoblast (W-20-17) cells. Moreover, in vitro differentiation assays demonstrated the scaffolds' ability to promote osteogenic differentiation of W-20-17. Collectively, the nanocomposites containing Laponite and antimicrobial peptide were proven to have osteoinductive and antimicrobial activity, making them desirable for bone tissue engineering applications.

Design, synthesis and biological evaluation of some novel sulfonamide derivatives as apoptosis inducers.

Several novel thiazolidinone and fused thiazolidinone derivatives bearing benzenesulfonamide moiety were synthesized and confirmed via spectral and elemental analyses. The newly synthesized compounds were evaluated for their cytotoxic activity on colorectal cancer cell line (Caco-2). All the synthesized compounds showed better activity than the reference standards (Doxorubicin and 5-FU). Investigation of the apoptotic activity of the most active compounds revealed that compounds 3a, 5a, 5c and 6c activate both caspase-3 and Fas-ligand in Caco-2 cell line. Compound 3a was the most active compound with caspase-3 concentration of 0.43 nmol/mL and Fas-ligand concentration of 775.2 pg/mL in treated Caco-2 cells. Compound 3a was radiolabeled with 99mTc and its biodistribution pattern was evaluated in vivo using normal Swiss Albino mice. 99mTc-compound 3a complex didn't exhibit any accumulation in any body organs except for its accumulation in the colon; target organ; where it showed 8.97 ± 1.35 %ID/g at 15min p. i. that elevated till 16.02 ± 2.43 %ID/g at 120min p. i.