Search Results (9)

Single-vesicle molecular profiling of cancer-associated extracellular vesicles (EVs) is increasingly being recognized as a powerful tool for cancer detection and monitoring. Mask and target dual imaging is a facile method to quantify the fraction of the molecularly targeted population of EVs in biofluids at the single-vesicle level. However, accurate and efficient dual imaging vesicle analysis has been challenging due to the interference of false signals on the mask images and the need to analyze a large number of images in clinical samples. In this work, we report a fully automatic dual imaging analysis method based on machine learning and use it with dual imaging single-vesicle technology (DISVT) to detect breast cancer at different stages. The convolutional neural network Resnet34 was used along with transfer learning to produce a suitable machine learning model that could accurately identify areas of interest in experimental data. A combination of experimental and synthetic data were used to train the model. Using DISVT and our machine learning-assisted image analysis platform, we determined the fractions of EpCAM-positive EVs and CD24-positive EVs over captured plasma EVs with CD81 marker in the blood plasma of pilot HER2-positive breast cancer patients and compared to those from healthy donors. The amount of both EpCAM-positive and CD24-positive EVs was found negligible for both healthy donors and Stage I patients. The amount of EpCAM-positive EVs (also CD81-positive) increased from 18% to 29% as the cancer progressed from Stage II to III. No significant increase was found with further progression to Stage IV. A similar trend was found for the CD24-positive EVs. Statistical analysis showed that both EpCAM and CD24 markers can detect HER2-positive breast cancer at Stages II, III, or IV. They can also differentiate individual cancer stages except those between Stage III and Stage IV. Due to the simplicity, high sensitivity, and high efficiency, the DISVT with the AI-assisted dual imaging analysis can be widely used for both basic research and clinical applications to quantitatively characterize molecularly targeted EV subtypes in biofluids. Full article

Salinity management in estuarine systems is crucial for developing effective water-management strategies to maintain compliance and understand the impact of salt intrusion on water quality and availability. Understanding the temporal and spatial variations of salinity is a keystone of salinity-management practices. Process-based numerical models have been traditionally used to estimate the variations in salinity in estuarine environments. Advances in data-driven models (e.g., deep learning models) make them effective and efficient alternatives to process-based models. However, a discernible research gap exists in applying these advanced techniques to salinity modeling. The current study seeks to address this gap by exploring the innovative use of deep learning with data augmentation and transfer learning in salinity modeling, exemplified at 23 key salinity locations in the Sacramento–San Joaquin Delta which is the hub of the water-supply system of California. Historical, simulated (via a hydrodynamics and water quality model), and perturbed (to create a range of hydroclimatic and operational scenarios for data-augmentation purposes) flow, and salinity data are used to train a baseline multi-layer perceptron (MLP) and a deep learning Residual Long-Short-Term Memory (Res-LSTM) network. Four other deep learning models including LSTM, Residual Network (ResNet), Gated Recurrent Unit (GRU), and Residual GRU (Res-GRU) are also examined. Results indicate that models pre-trained using augmented data demonstrate improved performance over models trained from scratch using only historical data (e.g., median Nash–Sutcliffe efficiency increased from around 0.5 to above 0.9). Moreover, the five deep learning models further boost the salinity estimation performance in comparison with the baseline MLP model, though the performance of the latter is acceptable. The models trained using augmented data are then (a) used to develop a web-based Salinity Dashboard (Dashboard) tool that allows the users (including those with no machine learning background) to quickly screen multiple management scenarios by altering inputs and visualizing the resulting salinity simulations interactively, and (b) transferred and adapted to estimate observed salinity. The study shows that transfer learning results more accurately replicate the observations compared to their counterparts from models trained from scratch without knowledge learned and transferred from augmented data (e.g., median Nash–Sutcliffe efficiency increased from around 0.4 to above 0.9). Overall, the study illustrates that deep learning models, particularly when pre-trained using augmented data, are promising supplements to existing process-based models in estuarine salinity modeling, while the Dashboard enables user engagement with those pre-trained models to inform decision-making efficiently and effectively. Full article

Salinity in estuarine environments has been traditionally simulated using process-based models. More recently, data-driven models including artificial neural networks (ANNs) have been developed for simulating salinity. Compared to process-based models, ANNs yield faster salinity simulations with comparable accuracy. However, ANNs are often purely data-driven and not constrained by physical laws, making it difficult to interpret the causality between input and output data. Physics-informed neural networks (PINNs) are emerging machine-learning models to integrate the benefits of both process-based models and data-driven ANNs. PINNs can embed the knowledge of physical laws in terms of the partial differential equations (PDE) that govern the dynamics of salinity transport into the training of the neural networks. This study explores the application of PINNs in salinity modeling by incorporating the one-dimensional advection–dispersion salinity transport equation into the neural networks. Two PINN models are explored in this study, namely PINNs and FoNets. PINNs are multilayer perceptrons (MLPs) that incorporate the advection–dispersion equation, while FoNets are an extension of PINNs with an additional encoding layer. The exploration is exemplified at four study locations in the Sacramento–San Joaquin Delta of California: Pittsburg, Chipps Island, Port Chicago, and Martinez. Both PINN models and benchmark ANNs are trained and tested using simulated daily salinity from 1991 to 2015 at study locations. Results indicate that PINNs and FoNets outperform the benchmark ANNs in simulating salinity at the study locations. Specifically, PINNs and FoNets have lower absolute biases and higher correlation coefficients and Nash–Sutcliffe efficiency values than ANNs. In addition, PINN models overcome some limitations of purely data-driven ANNs (e.g., neuron saturation) and generate more realistic salinity simulations. Overall, this study demonstrates the potential of PINNs to supplement existing process-based and ANN models in providing accurate and timely salinity estimation. Full article

Water resources management in estuarine environments for water supply and environmental protection typically requires estimates of salinity for various flow and operational conditions. This study develops and applies two novel deep learning (DL) models, a residual long short-term memory (Res-LSTM) network, and a residual gated recurrent unit (Res-GRU) model, in estimating the spatial and temporal variations of salinity. Four other machine learning (ML) models, previously developed and reported, consisting of multi-layer perceptron (MLP), residual network (ResNet), LSTM, and GRU are utilized as the baseline models to benchmark the performance of the two novel models. All six models are applied at 23 study locations in the Sacramento–San Joaquin Delta (Delta), the hub of California’s water supply system. Model input features include observed or calculated tidal stage (water level), flow and salinity at model upstream boundaries, salinity control gate operations, crop consumptive use, and pumping for the period of 2001–2019. Meanwhile, field observations of salinity at the study locations during the same period are also utilized for the development of the predictive use of the models. Results indicate that the proposed DL models generally outperform the baseline models in simulating and predicting salinity on both daily and hourly scales at the study locations. The absolute bias is generally less than 5%. The correlation coefficients and Nash–Sutcliffe efficiency values are close to 1. Particularly, Res-LSTM has slightly superior performance over Res-GRU. Moreover, the study investigates the overfitting issues of both the DL and baseline models. The investigation indicates that overfitting is not notable. Finally, the study compares the performance of Res-LSTM against that of an operational process-based salinity model. It is shown Res-LSTM outperforms the process-based model consistently across all study locations. Overall, the study demonstrates the feasibility of DL-based models in supplementing the existing operational models in providing accurate and real-time estimates of salinity to inform water management decision making. Full article

Advances in machine-learning techniques can serve practical water management needs such as salinity level estimation. This study explores machine learning, particularly deep-learning techniques in developing computer emulators for a commonly used process model, the Delta Simulation Model II (DSM2), used for salinity estimation in California’s Sacramento-San Joaquin Delta (Delta). We apply historical daily input data to DSM2 and corresponding salinity simulations at 28 study locations from 1990 to 2019 to train two machine-learning models: a multi-layer perceptron (MLP) and Long-Short-Term Memory (LSTM) networks in a multi-task learning framework. We assess sensitivity of both networks to the amount of antecedent input information (memory) and training data to determine appropriate memory size and training data length. We evaluate network performance according to several statistical metrics as well as visual inspection. The study further investigates two additional networks, the Gated Recurrent Unit (GRU) and Residual Network (ResNet) in salinity modeling, and compares their efficacy against MLP and LSTM. Our results demonstrate strong performance of the four neural network models over the study period, achieving absolute bias below 4%, plus near-perfect correlation coefficients and Nash–Sutcliffe efficiency coefficients. The high complexity LSTM shows slight performance edge. We further show that deeper and wider versions of MLP and LSTM yield only marginal benefit over their baseline counterparts. We also examined issues related to potential overfitting by the proposed models, training data selection strategies, and analytical and practical implications. Overall, this new study indicates that machine-learning-based emulators can efficiently emulate DSM2 in salinity simulation. They exhibit strong potential to supplement DSM2 in salinity modeling and help guide water resource planning and management practices for the Delta region. Full article

We investigate maneuvering superparamagnetic microparticles, or beads, in a remotely-controlled, automated way across arrays of few-micron-diameter permalloy disks. This technique is potentially useful for applying tunable forces to or for sorting biological structures that can be attached to magnetic beads, for example nucleic acids, proteins, or cells. The particle manipulation method being investigated relies on a combination of stray fields emanating from permalloy disks as well as time-varying externally applied magnetic fields. Unlike previous work, we closely examine particle motion during a capture, rotate, and controlled repulsion mechanism for particle transport. We measure particle velocities during short-range motion—the controlled repulsion of a bead from one disk toward another—and compare this motion to a simulation based on stray fields from disk edges. We also observe the phase-slipping and phase-locked motion of particles engaging in long-range transport in this manipulation scheme. Full article

We report the first case of a 294 kb loss, notable for including the entirety of GPD1L, on chromosome 3p22.3—p24 in a 3-year-old girl with multiple congenital anomalies including absent left foot, single umbilical artery, bilateral vesico-ureteral reflux, rectovaginal fistula, and imperforate anus. Although GPD1L mutations have been associated with cardiac arrhythmias, including Brugada syndrome and sudden unexpected infant death syndrome, full deletions in the GPD1L gene have not been reported neither the patient nor her mother, who was later identified to carry the variant, have any signs or symptoms of Brugada syndrome. This may indicate these individuals have findings that have not yet been identified, full gene deletions of GDP1L are not necessarily disease causing, or there is incomplete penetrance of this gene or cardiac manifestations can occur at a later age. Full article

The use of digital accelerometers featuring high sensitivity and low noise levels in wireless smart sensors (WSSs) is becoming increasingly common for structural health monitoring (SHM) applications. Improvements in the design of Micro Electro-Mechanical System (MEMS) based digital accelerometers allow for high resolution sensing required for SHM with low power consumption suitable for WSSs. However, new approaches are needed to synchronize data from these sensors. Data synchronization is essential in wireless smart sensor networks (WSSNs) for accurate condition assessment of structures and reduced false-positive indications of damage. Efforts to achieve synchronized data sampling from multiple WSS nodes with digital accelerometers have been lacking, primarily because these sensors feature an internal Analog to Digital Converter (ADC) to which the host platform has no direct access. The result is increased uncertainty in the ADC startup time and thus worse synchronization among sensors. In this study, a high-sensitivity digital accelerometer is integrated with a next-generation WSS platform, the Xnode. An adaptive iterative algorithm is used to characterize these delays without the need for a dedicated evaluation setup and hardware-level access to the ADC. Extensive tests are conducted to evaluate the performance of the accelerometer experimentally. Overall time-synchronization achieved is under 15 µs, demonstrating the efficacy of this approach for synchronization of critical SHM applications. Full article

The global nutrition transition has contributed to child obesity and dental caries in developing countries, including Vietnam. Few studies have described the nutrition and oral health of mothers and children. This a descriptive study of the nutrition and oral health characteristics of a convenience sample of 571 children aged 2 to 5 years and their mothers from 5 urban preschools in Central and South Vietnam. The mothers completed a written survey, and the children received dental exams and weight/height measurements. High rates of bottle-feeding and the consumption of sweets were reported. One in 4 children were overweight/obese. Dental caries increased in prevalence and severity by age—at 5 years, 86.7% of children had tooth decay in an average of 8.5 teeth, and 70.9% experienced mouth pain. Most mothers and children suffered from untreated dental disease. Public health programs should focus on nutrition and oral health promotion, as well as dental treatment from pregnancy and birth onward. Full article