Explore the vast range of titles available.

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field.

The present work focuses on the flame–wall interaction (FWI) based on direct numerical simulations (DNS) of a head-on premixed flame quenching configuration at the statistically stationary state. The effects of FWI on the turbulent flame temperature, wall heat flux, flame dynamics and flow structures were investigated. In turbulent head-on quenching, particularly for high turbulence intensity, the distorted flames generally consist of the head-on flame part and the entrained flame part. The flame properties are jointly influenced by turbulence, heat generation from chemical reactions and heat loss to the cold wall boundary. For the present FWI configuration, as the wall is approached, the ‘influence zone’ can be identified as the region within which the flame temperature, scalar gradient and flame dilatation start to decrease, whereas the wall heat flux tends to increase. As the distance to the wall drops below the flame-quenching distance, approximately where the wall heat flux reaches its maximum value, chemical reactions become negligibly weak inside the ‘quenching zone’. A simplified counter-flow model is also proposed. With the reasonably proposed relation between the flame speed and the flame temperature, the model solutions match well with the DNS results, both qualitatively and quantitatively. Moreover, near-wall statistics of some important flame properties, including the flame dilatation, reaction progress variable gradient, tangential strain rate and curvature were analysed in detail under different wall boundary conditions.

Intracranial hemorrhage is a medical emergency that requires urgent diagnosis and immediate treatment to improve patient outcome. Machine learning algorithms can be used to perform medical image classification and assist clinicians in diagnosing radiological scans. In this paper, we apply 3-dimensional convolutional neural networks (3D CNN) to classify computed tomography (CT) brain scans into normal scans (N) and abnormal scans containing subarachnoid hemorrhage (SAH), intraparenchymal hemorrhage (IPH), acute subdural hemorrhage (ASDH) and brain polytrauma hemorrhage (BPH). The dataset used consists of 399 volumetric CT brain images representing approximately 12,000 images from the National Neuroscience Institute, Singapore. We used a 3D CNN to perform both 2-class (normal versus a specific abnormal class) and 4-class classification (between normal, SAH, IPH, ASDH). We apply image thresholding at the image pre-processing step, that improves 3D CNN classification accuracy and performance by accentuating the pixel intensities that contribute most to feature discrimination. For 2-class classification, the F1 scores for various pairs of medical diagnoses ranged from 0.706 to 0.902 without thresholding. With thresholding implemented, the F1 scores improved and ranged from 0.919 to 0.952. Our results are comparable to, and in some cases, exceed the results published in other work applying 3D CNN to CT or magnetic resonance imaging (MRI) brain scan classification. This work represents a direct application of a 3D CNN to a real hospital scenario involving a medically emergent CT brain diagnosis.

Image stitching aims to construct a wide field of view with high spatial resolution, which cannot be achieved in a single exposure. Typically, conventional image stitching techniques, other than deep learning, require complex computation and are thus computationally expensive, especially for stitching large raw images. In this study, inspired by the multiscale feature of fluid turbulence, we developed a fast feature point detection algorithm named local-peak scale-invariant feature transform (LP-SIFT), based on the multiscale local peaks and scale-invariant feature transform method. By combining LP-SIFT and RANSAC in image stitching, the stitching speed can be improved by orders compared with the original SIFT method. Benefiting from the adjustable size of the interrogation window, the LP-SIFT algorithm demonstrates comparable or even less stitching time than the other commonly used algorithms, while achieving comparable or even better stitching results. Nine large images (over 2600 × 1600 pixels), arranged randomly without prior knowledge, can be stitched within 158.94 s. The algorithm is highly practical for applications requiring a wide field of view in diverse application scenes, e.g., terrain mapping, biological analysis, and even criminal investigation.

Geometrical and dynamical properties of turbulent flows have been investigated by streamline segment analysis. Starting from each grid point, a streamline segment is defined as the part of its streamline bounded by the two adjacent extremal points of the velocity magnitude. Physically the streamline segments can be extended into a more meaningful concept, namely the streamtube segments, which are non-overlapping and space filling. This decomposition of the flow allows for new insights into vector-related statistics in turbulence. According to the variation of velocity, the streamline segments can be sorted into positive and negative segments. The overall properties of turbulent flows can be newly understood and explained from the statistics of these segments with simple structures; for instance, the negative skewness of the velocity derivative becomes naturally a kinematic outcome. Furthermore, from direct numerical simulations conditional statistics of pressure and kinetic energy dissipation along the streamline segments are evaluated and discussed.

Transformers were initially introduced for natural language processing, leveraging the self-attention mechanism. They require minimal inductive biases in their design and can function effectively as set-based architectures. Additionally, transformers excel at capturing long-range dependencies and enabling parallel processing, which allows them to outperform traditional models, such as long short-term memory (LSTM) networks, on sequence-based tasks. In recent years, transformers have been widely adopted in computer vision, driving remarkable advancements in the field. Previous surveys have provided overviews of transformer applications across various computer vision tasks, such as object detection, activity recognition, and image enhancement. In this survey, we focus specifically on image classification. We begin with an introduction to the fundamental concepts of transformers and highlight the first successful Vision Transformer (ViT). Building on the ViT, we review subsequent improvements and optimizations introduced for image classification tasks. We then compare the strengths and limitations of these transformer-based models against classic convolutional neural networks (CNNs) through experiments. Finally, we explore key challenges and potential future directions for image classification transformers.

In order to extract small-scale statistical information from passive scalar fields obtained by direct numerical simulation (DNS) a new method of analysis is introduced. It consists of determining local minimum and maximum points of the fluctuating scalar field via gradient trajectories starting from every grid point in the directions of ascending and descending scalar gradients. The ensemble of grid cells from which the same pair of extremal points is reached determines a spatial region which is called a ‘dissipation element’. This region may be highly convoluted but on average it has an elongated shape with, on average, a nearly constant diameter of a few Kolmogorov scales and a variable length that has the mean of a Taylor scale. We parameterize the geometry of these elements by the linear distance between their extremal points and their scalar structure by the absolute value of the scalar difference at these points. The joint p.d.f. of these two parameters contains most of the information needed to reconstruct the statistics of the scalar field. It is decomposed into a marginal p.d.f. of the linear distance and a conditional p.d.f. of the scalar difference. It is found that the conditional mean of the scalar difference follows the 1/3 inertial-range Kolmogorov scaling over a large range of length-scales even for the relatively small Reynolds number of the present simulations. This surprising result is explained by the additional conditioning on minima and maxima points. A stochastic evolution equation for the marginal p.d.f. of the linear distance is derived and solved numerically. The stochastic problem that we consider consists of a Poisson process for the cutting of linear elements and a reconnection process due to molecular diffusion. The resulting length-scale distribution compares well with those obtained from the DNS.

The COVID-19 pandemic has put a huge challenge on the Indian health infrastructure. With a larger number of people getting affected during the second wave, hospitals were overburdened, running out of supplies and oxygen. Hence, predicting new COVID-19 cases, new deaths, and total active cases multiple days in advance can aid better utilization of scarce medical resources and prudent pandemic-related decision-making. The proposed method uses gated recurrent unit networks as the main predicting model. A study is conducted by building four models pre-trained on COVID-19 data from four different countries (United States of America, Brazil, Spain, and Bangladesh) and fine-tuned on India’s data. Since the four countries chosen have experienced different types of infection curves, the pre-training provides a transfer learning to the models incorporating diverse situations into account. Each of the four models then gives 7-day ahead predictions using the recursive learning method for the Indian test data. The final prediction comes from an ensemble of the predictions of the different models. This method with two countries, Spain and Bangladesh, is seen to achieve the best performance amongst all the combinations as well as compared to other traditional regression models.

Single-molecule localization microscopy enables high-resolution imaging of molecular interactions, but discriminating molecular binding types has traditionally relied on complex strategies, such as multiple dyes, time-division techniques, or kinetic analysis, that are asynchronous, invasive, or time-consuming. Here, we uncover previously overlooked spatiotemporal information embedded within diffraction-limited fluorescence, enabling synchronous classification of individual binding event videos using only a single fluorescent dye. Building on this insight, we propose a Temporal-to-Context Convolutional Neural Network (T2C CNN), which integrates long-term spatial convolutions, shallow cross-connected blocks, and a pooling-free structure to enhance contextual representation while preserving fine-grained temporal features. Applied to DNA-PAINT experiments, T2C CNN achieves up to 94.76% classification accuracy and outperforms state-of-the-art video classification models by 15-25 percentage points. Our approach enables rapid and precise binding-type recognition from fluorescence video data, reducing observation time from minutes to seconds and facilitating high-throughput single-molecule imaging without requiring multiple dye channels or extended kinetic measurements. Yin and colleagues propose that diffraction-limited fluorescence videos contain hidden binding-type information. The authors present a deep learning model, T2C CNN, which exploits that hidden information to classify molecular interactions with high accuracy using a single dye in seconds.

Dissipation elements are identified for various direct numerical simulation (DNS) fields of homogeneous shear turbulence. The fields are those of the fluctuations of a passive scalar, of the three components of velocity and vorticity, of the second invariant of the velocity gradient tensor, turbulent kinetic energy and viscous dissipation. In each of these fields trajectories starting from every grid point are calculated in the direction of ascending and descending gradients, reaching a local maximum and minimum point, respectively. Dissipation elements are defined as spatial regions containing all the grid points from which the same pair of minimum and maximum points is reached. They are parameterized by the linear length between these points and the difference of the field variable at these points. In analysing the changes that occur during one time step in the linear length as well as in the number of grid points contained in the elements, it is found that rapid splitting and attachment processes occur between elements. These processes are much more frequent than the previously identified processes of cutting and reconnection. The model for the length-scale distribution function that had previously been proposed is modified to include these additional processes. Comparisons of the length-scale distribution function for the various fields with the proposed model show satisfactory agreement. The conditional mean difference of the field variable at the minimum and maximum points of dissipation elements is calculated for the passive scalar field and the three components of velocity. While the conditional mean difference follows the 1/3 inertial-range Kolmogorov scaling for the passive scalar field, the scaling exponent differs from the 1/3 law for each of the three components of velocity. This is thought to be due to the relatively high shear rate of the DNS calculations. The conditional mean viscous dissipation shows, differently from all other field variables analysed, a pronounced dependence on the linear length of elements. This is explained by intermittency. This finding is used to evaluate the production and the dissipation term of the empirically derived ϵ-equation that is often used in engineering calculations.