Ultrasound Image Analysis with Vision Transformers-Review.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges, such as a low imaging quality and high variability. There is a need to develop advanced automatic US image analysis methods to enhance its diagnostic accuracy and objectivity. Vision transformers, a recent innovation in machine learning, have demonstrated significant potential in various research fields, including general image analysis and computer vision, due to their capacity to process large datasets and learn complex patterns. Their suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformers and discusses their applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in their application in medical US image analysis. Vision transformers have shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and are expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

Automatic Diagnosis of Stage of COVID-19 Patients using an Ensemble of Transfer Learning with Convolutional Neural Networks Based on Computed Tomography Images.

Background: Diagnosis of the stage of COVID-19 patients using the chest computed tomography (CT) can help the physician in making decisions on the length of time required for hospitalization and adequate selection of patient care. This diagnosis requires very expert radiologists who are not available everywhere and is also tedious and subjective. The aim of this study is to propose an advanced machine learning system to diagnose the stages of COVID-19 patients including normal, early, progressive, peak, and absorption stages based on lung CT images, using an automatic deep transfer learning ensemble. Methods: Different strategies of deep transfer learning were used which were based on pretrained convolutional neural networks (CNNs). Pretrained CNNs were fine-tuned on the chest CT images, and then, the extracted features were classified by a softmax layer. Finally, we built an ensemble method based on majority voting of the best deep transfer learning outputs to further improve the recognition performance. Results: The experimental results from 689 cases indicate that the ensemble of three deep transfer learning outputs based on EfficientNetB4, InceptionResV3, and NasNetlarge has the highest results in diagnosing the stage of COVID-19 with an accuracy of 91.66%. Conclusion: The proposed method can be used for the classification of the stage of COVID-19 disease with good accuracy to help the physician in making decisions on patient care.

Periodic Mesoporous Organosilica Nanomaterials with Unconventional Structures and Properties.

Periodic mesoporous organosilicas (PMOs) are high surface area organic-inorganic hybrid nanomaterials that have found broad applications in various fields of research such as in (bio)chemistry or material science. By choosing suitable organic groups in the framework of these materials, their surface properties such as polarity, optical/electrical characteristics and adsorption capacity can be tuned. This critical review provides an overview of the current state of the art in the developments and applications of some PMO nanomaterials in diverse fields of research. This is placed in the context of four leading areas of PMO nanomaterials, including chiral PMOs, plugged PMO nanomaterials, Janus PMOs and PMO-based nanomotors. The review briefly discusses the recent and key findings on these PMO nanomaterials as well as their potential applications for future developments.

Task-Specific Janus Materials in Heterogeneous Catalysis.

Janus materials are anisotropic nano- and microarchitectures with two different faces consisting of distinguishable or opposite physicochemical properties. In parallel with the discovery of new methods for the fabrication of these materials, decisive progress has been made in their application, for example, in biological science, catalysis, pharmaceuticals, and, more recently, in battery technology. This Minireview systematically covers recent and significant achievements in the application of task-specific Janus nanomaterials as heterogeneous catalysts in various types of chemical reactions, including reduction, oxidative desulfurization and dye degradation, asymmetric catalysis, biomass transformation, cascade reactions, oxidation, transition-metal-catalyzed cross-coupling reactions, electro- and photocatalytic reactions, as well as gas-phase reactions. Finally, an outlook on possible future applications is given.

Automatic morphological classification of mitral valve diseases in echocardiographic images based on explainable deep learning methods.

PURPOSE: Carpentier's functional classification is a guide to explain the types of mitral valve regurgitation based on morphological features. There are four types of pathological morphologies, regardless of the presence or absence of mitral regurgitation: Type I, normal; Type II, mitral valve prolapse; Type IIIa, mitral valve stenosis; and Type IIIb, restricted mitral leaflet motion. The aim of this study was to automatically classify mitral valves using echocardiographic images. METHODS: In our procedure, after the classification of apical 4-chamber (A4C) and parasternal long-axis (PLA) views, we extracted the systolic/diastolic phase of the cardiac cycle by calculating the left ventricular area. Six typical pre-trained models were fine-tuned with a 4-class model for the PLA and a 3-class model for the A4C views. As an additional contribution, to provide explainability, we applied the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm to visualize areas of echocardiographic images where the different models generated a prediction. RESULTS: This approach conferred a proper understanding of where various networks "look" into echocardiographic images to predict the four types of pathological mitral valve morphologies. Considering the accuracy metric and Grad-CAM maps and by applying the Inception-ResNet-v2 architecture to classify Type II in the PLA view and ResNeXt50 architecture to classify the other three classes in the A4C view, we achieved an 80% rate of model accuracy in the test data set. CONCLUSIONS: We suggest an explainable, fully automated, and rule-based procedure to classify the four types of mitral valve morphologies based on Carpentier's functional classification using deep learning on transthoracic echocardiographic images. Our study results infer the feasibility of the use of deep learning models to prepare quick and precise assessments of mitral valve morphologies in echocardiograms. According to our knowledge, our study is the first one that provides a public data set regarding the Carpentier classification of MV pathologies.

Janus bifunctional periodic mesoporous organosilica.

Synthesis of a Janus periodic mesoporous organosilica material (JPMO) is presented here. In this strategy, the surface of the hollow silica material was selectively functionalized with two different bridged organic-inorganic hybrid groups. It was found that the resulting bifunctional material is able to form a stable Pickering emulsion. This new type of PMO material may be suitable for widespread applications in various fields related to material science and catalysis.

Fast and Selective Aqueous-Phase Oxidation of Styrene to Acetophenone Using a Mesoporous Janus-Type Palladium Catalyst.

A heterogeneous Janus-type palladium interphase catalyst was obtained by selective surface modification of a hollow mesoporous silica material. The catalyst comprises hydrophobic octyl groups on one side of the silica nanosheets and single-site bis-imidazoline dichlorido palladium(II) complexes on the other. The structure of this composite material has been analyzed by means of elemental analysis, atomic absorption spectroscopy, BET surface analysis, TGA, SEM and solid-state CP-MAS 13C and 29Si NMR spectroscopy. The catalyst showed extraordinary activity for the aqueous-phase oxidation of styrene to acetophenone using 30% hydrogen peroxide as the oxidant. An 88% yield of acetophenone could be achieved after 60 min.

Dinuclear Copper Complex Immobilized on a Janus-Type Material as an Interfacial Heterogeneous Catalyst for Green Synthesis.

We herein describe a rational design of a heterogeneous catalyst composed of a dinuclear cuprate anion being immobilized electrostatically on one surface of Janus-type nanosheets while the other surface is decorated with highly hydrophobic octyl groups. The catalyst was found to be well dispersible in the organic phase of a biphasic aqueous/organic mixture. It was characterized by means of elemental analysis, atomic absorption spectroscopy, mass spectrometry, N2 absorption-desorption analysis, thermogravimetric analysis, scanning electron microscopy (SEM), and solid-state 13C and 29Si cross-polarization magic-angle spinning nuclear magnetic resonance spectroscopy. The Janus nature of the catalyst was investigated by employing a selective surface labeling method and by means of SEM. The catalyst shows higher activity compared to a non-Janus analogue in a biphasic synthesis. It was successfully used for the azide-alkyne cycloaddition and the Chan-Lam C-N coupling reaction. In addition, new and simple ways have been established for the production of a coumarin-triazole derivative and for the synthesis of the biologically active compound Monastrol via a solvent-free Biginelli reaction. The role of the dinuclear copper centers is discussed mechanistically.

A deep learning approach for the automatic recognition of prosthetic mitral valve in echocardiographic images.

The first step in the automatic evaluation of the cardiac prosthetic valve is the recognition of such valves in echocardiographic images. This research surveyed whether a deep convolutional neural network (DCNN) could improve the recognition of prosthetic mitral valve in conventional 2D echocardiographic images. An efficient intervention to decrease the misreading rate of the prosthetic mitral valve is required for non-expert cardiologists. This intervention could serve as a section of a fully-automated analysis chain, alleviate the cardiologist's workload, and improve precision and time management, especially in an emergent situation. Additionally, it might be suitable for pre-labeling large databases of unclassified images. We, therefore, introduce a large publicly-available annotated dataset for the purpose of prosthetic mitral valve recognition. We utilized 2044 comprehensive non-stress transthoracic echocardiographic studies. Totally, 1597 patients had natural mitral valves and 447 patients had prosthetic valves. Each case contained 1 cycle of echocardiographic images from the apical 4-chamber (A4C) and the parasternal long-axis (PLA) views. Thirteen versions of the state-of-the-art models were independently trained, and the ensemble predictions were performed using those versions. For the recognition of prosthetic mitral valves from natural mitral valves, the area under the receiver-operating characteristic curve (AUC) made by the deep learning algorithm was similar to that made by cardiologists (0.99). In this research, EfficientNetB3 architecture in the A4C view and the EfficientNetB4 architecture in the PLA view were the best models among the other pre-trained DCNN models.

Automated detection of COVID-19 using ensemble of transfer learning with deep convolutional neural network based on CT scans.

PURPOSE: COVID-19 has infected millions of people worldwide. One of the most important hurdles in controlling the spread of this disease is the inefficiency and lack of medical tests. Computed tomography (CT) scans are promising in providing accurate and fast detection of COVID-19. However, determining COVID-19 requires highly trained radiologists and suffers from inter-observer variability. To remedy these limitations, this paper introduces an automatic methodology based on an ensemble of deep transfer learning for the detection of COVID-19. METHODS: A total of 15 pre-trained convolutional neural networks (CNNs) architectures: EfficientNets(B0-B5), NasNetLarge, NasNetMobile, InceptionV3, ResNet-50, SeResnet 50, Xception, DenseNet121, ResNext50 and Inception_resnet_v2 are used and then fine-tuned on the target task. After that, we built an ensemble method based on majority voting of the best combination of deep transfer learning outputs to further improve the recognition performance. We have used a publicly available dataset of CT scans, which consists of 349 CT scans labeled as being positive for COVID-19 and 397 negative COVID-19 CT scans that are normal or contain other types of lung diseases. RESULTS: The experimental results indicate that the majority voting of 5 deep transfer learning architecture with EfficientNetB0, EfficientNetB3, EfficientNetB5, Inception_resnet_v2, and Xception has the higher results than the individual transfer learning structure and among the other models based on precision (0.857), recall (0.854) and accuracy (0.85) metrics in diagnosing COVID-19 from CT scans. CONCLUSION: Our study based on an ensemble deep transfer learning system with different pre-trained CNNs architectures can work well on a publicly available dataset of CT images for the diagnosis of COVID-19 based on CT scans.

Efficient and reversible CO2 capture by amine functionalized-silica gel confined task-specific ionic liquid system.

Simple, efficient and practical CO2 capture method is reported using task-specific ionic liquid (IL) supported onto the amine-functionalized silica gel. The results have been shown that both the capacity and rate of the CO2 absorption notably increase in the supported IL/molecular sieve 4 Å system in comparison of homogeneous IL. Additionally, it has shown that the prepared material is capable for reversible carbon dioxide absorption for at least 10 cycles without significant loss of efficiency. The presence of the amine-based IL and the surface bonded amine groups increase the capacity of CO2 absorption even in a CO2/CH4 gas mixture through the formation of ammonium carbamate onto the surface of mesoporous material.

Imidazolium-based ionic liquid derivative/Cu(II) complexes as efficient catalysts of the lucigenin chemiluminescence system and its application to H2O 2 and glucose detection.

The effects of six synthetic imidazolium-based ionic liquids (ILs) on the Cu(II)-catalyzed chemiluminescence of lucigenin (Luc-CL) in the pH range 6.0-11 were investigated. Preliminary experiments found that the CL emission was strongly enhanced or inhibited in the presence of the ILs. The degree of enhancement or inhibition of the CL intensity in the presence of each IL was related to the molecular structure of the IL, the medium used, and the pH. The maximum enhancement of the CL intensity was observed at pH 9.0 (amplification factor = 443). This decrease in the pH at which maximum CL enhancement occurred and the substantial signal amplification of the Luc-CL may be related to a strong interaction between Cu(II) and the imidazolium ring of superior ILs at this pH. Additionally, the formation of IL microdomains in semi-aqueous media permitted more solubility of the product yielded by the Luc-CL reaction (N-methylacridone), which could increase the CL intensity. To obtain consistent data on the catalytic efficiency of Cu(II) in the presence of various ILs as well as the corresponding CL emission intensities, fluorescence quantum yields (Φ F) of lucigenin were measured under the same conditions. Comparison of the data pointed to the mechanism that controls the properties of Luc-CL in the presence of the Cu(II)/IL complexes. Based on the catalytic effect of the Cu(II)/IL complex and the measurement of the enzymatically generated H2O2, a novel, simple, and sensitive CL method for determining glucose with a detection limit (LoD) of 6.5 µM was developed. Moreover, this method was satisfactorily applied to the determination of glucose in human serum and urine samples. Graphical Abstract The lucigenin chemiluminescence assay for H2O2 and glucose using imidazolium-based ionic liquid derivatives/Cu(II) complexes as efficient catalysts at pH 9.0.

SBA-15-functionalized sulfonic acid confined acidic ionic liquid: a powerful and water-tolerant catalyst for solvent-free esterifications.

Incorporating a hydrophobic Brønsted acid ionic liquid (HBAIL) inside the nanospaces of SBA-15-Pr-SO(3)H led to a hydrophobic super Brønsted acid catalyst, which showed excellent catalytic performance in direct esterification of alcohols and carboxylic acids at ambient temperature under solvent-free conditions.