Jailed high-pressure balloon technique is superior to jailed wire technique in protecting side branch of coronary bifurcation lesions.

Objectives. This study investigated the influence of higher pressure protection with a small diameter balloon of side branch (SB) on bifurcation lesions. Background. Of the different coronary stent implantation techniques, the modified jailed balloon technique has become a viable option for bifurcation lesions. However, there was no detailed study on the relationship between the balloon inflation pressure of the main vessel (MV) and SB. Methods. In this study, we collected information of patients who underwent percutaneous coronary intervention (PCI) for bifurcated lesions between March 2019 and December 2022. They were divided into two groups according to the operation way: active jailed balloon technique (A-JBT) group and jailed wire technique (JWT) group. Results. A total of 216 patients were enrolled. The A-JBT group had a larger SB stenosis diameter (1.53 ± 0.69 vs. 0.95 ± 0.52, p < .001), the lower degree of stenosis (44.34 ± 18.30 vs. 63.69 ± 17.34, p < .001) compared to the JWT group. However, the JWT group had a higher incidence of SB occlusion (18.0% vs. 1.9%, p < .001) compared to the A-JBT group. Nevertheless, the success rate for both groups was 100%. Conclusions. This novel high inflation pressure and small diameter balloon approach we propose has significant advantages. There is a lower rate of SB occlusion and SB dissection, which is more cost-effective and provides better clinical outcomes for the patient. This method should be considered in the future for treating bifurcation lesions.

Applications of nature-inspired metaheuristic algorithms for tackling optimization problems across disciplines.

Nature-inspired metaheuristic algorithms are important components of artificial intelligence, and are increasingly used across disciplines to tackle various types of challenging optimization problems. This paper demonstrates the usefulness of such algorithms for solving a variety of challenging optimization problems in statistics using a nature-inspired metaheuristic algorithm called competitive swarm optimizer with mutated agents (CSO-MA). This algorithm was proposed by one of the authors and its superior performance relative to many of its competitors had been demonstrated in earlier work and again in this paper. The main goal of this paper is to show a typical nature-inspired metaheuristic algorithmi, like CSO-MA, is efficient for tackling many different types of optimization problems in statistics. Our applications are new and include finding maximum likelihood estimates of parameters in a single cell generalized trend model to study pseudotime in bioinformatics, estimating parameters in the commonly used Rasch model in education research, finding M-estimates for a Cox regression in a Markov renewal model, performing matrix completion tasks to impute missing data for a two compartment model, and selecting variables optimally in an ecology problem in China. To further demonstrate the flexibility of metaheuristics, we also find an optimal design for a car refueling experiment in the auto industry using a logistic model with multiple interacting factors. In addition, we show that metaheuristics can sometimes outperform optimization algorithms commonly used in statistics.

Optimal Designs for Nonlinear Mixed-effects Models Using Competitive Swarm Optimizer with Mutated Agents.

Nature-inspired meta-heuristic algorithms are increasingly used in many disciplines to tackle challenging optimization problems. Our focus is to apply a newly proposed nature-inspired meta-heuristics algorithm called CSO-MA to solve challenging design problems in biosciences and demonstrate its flexibility to find various types of optimal approximate or exact designs for nonlinear mixed models with one or several interacting factors and with or without random effects. We show that CSO-MA is efficient and can frequently outperform other algorithms either in terms of speed or accuracy. The algorithm, like other meta-heuristic algorithms, is free of technical assumptions and flexible in that it can incorporate cost structure or multiple user-specified constraints, such as, a fixed number of measurements per subject in a longitudinal study. When possible, we confirm some of the CSO-MA generated designs are optimal with theory by developing theory-based innovative plots. Our applications include searching optimal designs to estimate (i) parameters in mixed nonlinear models with correlated random effects, (ii) a function of parameters for a count model in a dose combination study, and (iii) parameters in a HIV dynamic model. In each case, we show the advantages of using a meta-heuristic approach to solve the optimization problem, and the added benefits of the generated designs.

UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation.

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks. Our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively. Code, pre-trained models, and use case pipeline are available at: https://github.com/MASILab/UNesT.

Evolution and Influencing Mechanisms of the Yili Loess Mechanical Properties under Combined Wetting-Drying and Freeze-Thaw Cycling.

Landslides frequently occur in the loess-rich Yili region of Xinjiang, China, due to the combined effects of wetting-drying and freeze-thaw (WD-FT) cycles, which cause changes in the soil/loess internal structure and shear strength. This paper explores the combined effect of WD-FT cycles on the shear strength evolution of Yili loess through cyclic and triaxial shear tests. The micromechanism of the effect of WD-FT cycles on the loess properties is studied through scanning electron microscopy tests. Finally, the gray correlation analysis method assesses the correlation between relevant macro and micro parameters. The results show that: (1) With the increase in WD-FT cycles, the cohesion of loess decreases first and then gradually stabilizes, while the internal friction angle first grows and then drops before stabilizing. This indicates that the WD-FT cycles cause different degrees of decline in the soil's internal friction angle and cohesion. (2) As the number of WD-FT cycles increases, the average abundance and directional probability entropy fluctuate slightly, gradually decreasing and stabilizing. In contrast, the particle size dimensionality gradually decreases and stabilizes, and the pore area ratio first increases and then gradually stabilizes. (3) Six microstructural parameters (average diameter, average abundance, particle size dimensionality, directional probability entropy, particle roundness, and pore area) are selected for correlation analysis with the shear strength index of loess. The results show that the particle size dimensionality closely correlates with macroscopic internal friction angle under coupled cycling, while the pore area closely correlates with macroscopic cohesion. These findings are instrumental in preventing and controlling loess landslides caused by WD-FT cycles in the Yili region of Xinjiang, China, and similar loess-rich regions.

Spectral Characteristics of Dissolved Organic Matter in Farmland Soils around Urumqi, China.

The dissolved organic matter (DOM) is one of the most sensitive indicators of changes in the soil environment, and it is the most mobile and active soil component that serves as an easily available source of nutrients and energy for microbes and other living organisms. In this paper, DOM structural characteristics and main properties were investigated by three-dimensional fluorescence spectroscopy (EEM) and UV-visible spectrum technology in the farmland soils around Urumqi of China, and its possible sources and pathways were analyzed by spectroscopic indices. The results showed that humic-like substances were the main composition of the soil DOM, and its autogenesis characteristics were not obvious. Main DOM properties such as aromatability, hydrophobicity, molecular weight, molecular size, and humification degree in the southern region of Urumqi were higher than those of the northern region of Urumqi and Fukang in China, and higher on the upper layers of the soil (0-0.1 and 0.2 m) than in the deeper layer (0.2-0.3 m).This may be because the tilled layer is more subjected to fertilization and conducive to microbial activities. The spectroscopic analysis showed that the source of DOM of these regions is mainly from microbial metabolites. These results provide basic scientific data for the further research on the environmental chemical behavior of pollutants and pollution control in this region.

Neurobehavioral Dimensions of Prader Willi Syndrome: Relationships Between Sleep and Psychosis-Risk Symptoms.

Background: Prader Willi Syndrome (PWS) is a genetic disorder caused by the absence of expression of the paternal copies of maternally imprinted gene(s) located at 15q11-q13. While the physical and medical characteristics of PWS, including short stature, hyperphagia and endocrine dysfunction are well-characterized, systematic investigation of the long-recognized psychiatric manifestations has been recent. Methods: Here, we report on the first remote (web-based) assessment of neurobehavioral traits, including psychosis-risk symptoms (Prodromal Questionnaire-Brief Version; PQ-B) and sleep behaviors (Pittsburgh Sleep Quality Index), in a cohort of 128 participants with PWS, of whom 48% had a paternal deletion, 36% uniparental disomy, 2.4% an imprinting mutation and 13% unknown mutation (mean age 19.3 years ± 8.4; 53.9% female). We aimed to identify the most informative variables that contribute to psychosis-risk symptoms. Multiple domains of cognition (accuracy and speed) were also assessed in a subset of PWS participants (n = 39) using the Penn Computerized Neurocognitive Battery (Penn-CNB). Results: Individuals with PWS reported a range of psychosis-risk symptoms, with over half reporting cognitive disorganization (63.1%) and about one third reporting unusual beliefs (38.6%) and/or suspiciousness (33.3%). Subjectively-reported sleep quality, nap frequency, sleep duration, sleep disturbance, and daytime dysfunction were significant predictors of psychosis-risk symptom frequency and severity (all p's < 0.029). Sleep disturbance ratings were the strongest predictors of psychosis-risk symptoms. Regarding cognition, individuals with PWS showed the most prominent deficits in accuracy on measures of social cognition involving faces, namely Face Memory, Age Differentiation and Emotion Recognition, and greatest slowing on measures of Attention and Emotion Recognition. However, there were no significant differences in psychosis-risk symptoms or cognitive performance as a function of PWS genetic subtype. Conclusions: PWS is associated with a high prevalence of distressing psychosis-risk symptoms, which are associated with sleep disturbance. Findings indicate that self/parent-reported neurobehavioral symptoms and cognition can be assessed remotely in individuals with PWS, which has implications for future large-scale investigations of rare neurogenetic disorders.

Multi-cation hybrid stannic oxide electron transport layer for high-efficiency perovskite solar cells.

The performance of perovskite solar cells (PSCs) can be improved by optimizing the perovskite film quality and electron transfer layers (ETLs). In this study, high-efficient PSCs with multi-cation hybrid electron transport layer (SnO2@Na:Cs ETL) were fabricated using continuous spin-coating. Compared to the pristine SnO2, the power conversion efficiency (PCE) of device based on SnO2@Na:Cs ETL have reached 22.06% (with an open circuit voltage of 1.13 V), up approximately 21%. The photovoltaic performance of the device is enhanced due to the increase in the transmission rate, electrical conductivity, electron mobility and surface state owing to the multi-cation hybrid. In addition, because SnO2@Na:Cs ETL can significantly improve interface contact with the perovskite film and improve its crystallinity, the transport defect state and carrier transport efficiency are significantly improved at the ETL/Perovskite interface. Therefore, the open circuit voltage (Voc) and fill factor (FF) of PSCs was significantly increased. The application of SnO2@Na:Cs ETL provides a simple and efficient method to obtain highly-efficient PSCs.

Kullback-Leibler Divergence Metric Learning.

The Kullback-Leibler divergence (KLD), which is widely used to measure the similarity between two distributions, plays an important role in many applications. In this article, we address the KLD metric-learning task, which aims at learning the best KLD-type metric from the distributions of datasets. Concretely, first, we extend the conventional KLD by introducing a linear mapping and obtain the best KLD to well express the similarity of data distributions by optimizing such a linear mapping. It improves the expressivity of data distribution, which means it makes the distributions in the same class close and those in different classes far away. Then, the KLD metric learning is modeled by a minimization problem on the manifold of all positive-definite matrices. To deal with this optimization task, we develop an intrinsic steepest descent method, which preserves the manifold structure of the metric in the iteration. Finally, we apply the proposed method along with ten popular metric-learning approaches on the tasks of 3-D object classification and document classification. The experimental results illustrate that our proposed method outperforms all other methods.

Hypergraph Learning: Methods and Practices.

Hypergraph learning is a technique for conducting learning on a hypergraph structure. In recent years, hypergraph learning has attracted increasing attention due to its flexibility and capability in modeling complex data correlation. In this paper, we first systematically review existing literature regarding hypergraph generation, including distance-based, representation-based, attribute-based, and network-based approaches. Then, we introduce the existing learning methods on a hypergraph, including transductive hypergraph learning, inductive hypergraph learning, hypergraph structure updating, and multi-modal hypergraph learning. After that, we present a tensor-based dynamic hypergraph representation and learning framework that can effectively describe high-order correlation in a hypergraph. To study the effectiveness and efficiency of hypergraph generation and learning methods, we conduct comprehensive evaluations on several typical applications, including object and action recognition, Microblog sentiment prediction, and clustering. In addition, we contribute a hypergraph learning development toolkit called THU-HyperG.

High-efficiency planar heterojunction perovskite solar cell produced by using 4-morpholine ethane sulfonic acid sodium salt doped SnO2.

Perovskite solar cells (PSCs) have become a promising photovoltaic (PV) technology. Meanwhile, developing an electron transport layer (ETL) has been an effective way to promote the power conversion efficiency (PCE) of PSCs. Here, a 4-morpholine ethane sulfonic acid sodium salt (MES Na+) doped SnO2 ETL is utilized in planar heterojunction PSCs. The results show that the MES Na+ doped ETL can improve the crystallinity, and absorbance of perovskite films, and passivate interface defects between the perovskite film and SnO2 ETL. The doping effect accounts for the enhancement of conductivity and the decreasing work function of SnO2. When 10 mg mL-1 MES Na+ was added to the SnO2 precursor solution, the device showed the best performance Jsc, Voc, and FF of the PSCs values, which were 23.88 mA cm-2, 1.12 V and 78.69%, respectively, and the PCE was increased from 17.43% to 21.05%. This doping ETL strategy provides an avenue for defect passivation to further increase the efficiency of perovskite solar cells.

G-optimal designs for hierarchical linear models: an equivalence theorem and a nature-inspired meta-heuristic algorithm.

Hierarchical linear models are widely used in many research disciplines and estimation issues for such models are generally well addressed. Design issues are relatively much less discussed for hierarchical linear models but there is an increasing interest as these models grow in popularity. This paper discusses the G-optimality for predicting individual parameters in such models and establishes an equivalence theorem for confirming the G-optimality of an approximate design. Because the criterion is non-differentiable and requires solving multiple nested optimization problems, it is much harder to find and study G-optimal designs analytically. We propose a nature-inspired meta-heuristic algorithm called competitive swarm optimizer (CSO) to generate G-optimal designs for linear mixed models with different means and covariance structures. We further demonstrate that CSO is flexible and generally effective for finding the widely used locally D-optimal designs for nonlinear models with multiple interacting factors and some of the random effects are correlated. Our numerical results for a few examples suggest that G and D-optimal designs may be equivalent and we establish that D and G-optimal designs for hierarchical linear models are equivalent when the models have only a random intercept only. The challenging mathematical question of whether their equivalence applies more generally to other hierarchical models remains elusive.

Investigation of Changes to Triaxial Shear Strength Parameters and Microstructure of Yili Loess with Drying-Wetting Cycles.

This research examined the drying-wetting cycles induced changes in undrained triaxial shear strength parameters and microstructural changes of Yili loess. The drying-wetting cycles were selected as 0, 1, 3, 5, 10, 20 and 30. Then, we collected Yili loess samples and performed unconsolidated-undrained (U-U) triaxial shearing tests to ascertain the variation in shear strength parameters with drying-wetting cycles. Additionally, we investigated the microstructural changes of Yili loess samples under drying-wetting cycles simultaneously via nuclear magnetic resonance (NMR) and scanning electron electroscopy (SEM). Finally, we established a grey correlation model between shear strength and microstructural parameters. Under U-U conditions, the prime finding was that the loess's shear strength parameters changed overall after drying-wetting cycles; in particular, the internal friction angle φ dropped significantly while the cohesion c changed only slightly during cycles. For all the cycles, the first cycle gave the highest change. Soil morphology deterioration was evident at the initial stage of cycles. During the entire drying-wetting cyclic process, pore size distribution showed progressive variance from two-peak to a single-peak pattern, while both porosity and the fractal dimension of pores increased gradually towards stability. Soil particle morphology became slowly simple and reached the equilibrium state after 20 drying-wetting cycles. Under cyclic drying-wetting stress, the shear strength parameter changes were significantly correlated to microstructural modifications. This investigation was related to loess in the westerly region. The findings were expected to provide new insight into establishment of the connection between microstructure and macro stress-strain state of loess. To some extent, it provided a theoretical basis for the prevention and control of loess engineering geological disasters in Yili, Xinjiang and other areas with similar climate and soil types.

Text-Guided Neural Network Training for Image Recognition in Natural Scenes and Medicine.

Convolutional neural networks (CNNs) are widely recognized as the foundation for machine vision systems. The conventional rule of teaching CNNs to understand images requires training images with human annotated labels, without any additional instructions. In this article, we look into a new scope and explore the guidance from text for neural network training. We present two versions of attention mechanisms to facilitate interactions between visual and semantic information and encourage CNNs to effectively distill visual features by leveraging semantic features. In contrast to dedicated text-image joint embedding methods, our method realizes asynchronous training and inference behavior: a trained model can classify images, irrespective of the text availability. This characteristic substantially improves the model scalability to multiple (multimodal) vision tasks. We also apply the proposed method onto medical imaging, which learns from richer clinical knowledge and achieves attention-based interpretable decision-making. With comprehensive validation on two natural and two medical datasets, we demonstrate that our method can effectively make use of semantic knowledge to improve CNN performance. Our method performs substantial improvement on medical image datasets. Meanwhile, it achieves promising performance for multi-label image classification and caption-image retrieval as well as excellent performance for phrase-based and multi-object localization on public benchmarks.

A Scalable Optimization Mechanism for Pairwise Based Discrete Hashing.

Maintaining the pairwise relationship among originally high-dimensional data into a low-dimensional binary space is a popular strategy to learn binary codes. One simple and intuitive method is to utilize two identical code matrices produced by hash functions to approximate a pairwise real label matrix. However, the resulting quartic problem in term of hash functions is difficult to directly solve due to the non-convex and non-smooth nature of the objective. In this paper, unlike previous optimization methods using various relaxation strategies, we aim to directly solve the original quartic problem using a novel alternative optimization mechanism to linearize the quartic problem by introducing a linear regression model. Additionally, we find that gradually learning each batch of binary codes in a sequential mode, i.e. batch by batch, is greatly beneficial to the convergence of binary code learning. Based on this significant discovery and the proposed strategy, we introduce a scalable symmetric discrete hashing algorithm that gradually and smoothly updates each batch of binary codes. To further improve the smoothness, we also propose a greedy symmetric discrete hashing algorithm to update each bit of batch binary codes. Moreover, we extend the proposed optimization mechanism to solve the non-convex optimization problems for binary code learning in many other pairwise based hashing algorithms. Extensive experiments on benchmark single-label and multi-label databases demonstrate the superior performance of the proposed mechanism over recent state-of-the-art methods on two kinds of retrieval tasks: similarity and ranking order. The source codes are available on https://github.com/xsshi2015/Scalable-Pairwise-based-Discrete-Hashing.

fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning.

A publicly available dataset containing k-space data as well as Digital Imaging and Communications in Medicine image data of knee images for accelerated MR image reconstruction using machine learning is presented.

Competitive Swarm Optimizer with Mutated Agents for Finding Optimal Designs for Nonlinear Regression Models with Multiple Interacting Factors.

This paper proposes a novel enhancement for Competitive Swarm Optimizer (CSO) by mutating loser particles (agents) from the swarm to increase the swarm diversity and improve space exploration capability, namely Competitive Swarm Optimizer with Mutated Agents (CSO-MA). The selection mechanism is carried out so that it does not retard the search if agents are exploring in promising areas. Simulation results show that CSO-MA has a better exploration-exploitation balance than CSO and generally outperforms CSO, which is one of the state-of-the-art metaheuristic algorithms for optimization. We show additionally that it also generally outperforms swarm based types of algorithms and an exemplary and popular non-swarm based algorithm called Cuckoo search, without requiring a lot more CPU time. We apply CSO-MA to find a c-optimal approximate design for a high-dimensional optimal design problem when other swarm algorithms were not able to. As applications, we use the CSO-MA to search various optimal designs for a series of high-dimensional statistical models. The proposed CSO-MA algorithm is a general-purpose optimizing tool and can be directly amended to find other types of optimal designs for nonlinear models, including optimal exact designs under a convex or non-convex criterion.

Correction to: Towards pixel-to-pixel deep nucleus detection in microscopy images.

Following publication of the original article [1], we have been notified of a few errors in the html version.

Towards pixel-to-pixel deep nucleus detection in microscopy images.

BACKGROUND: Nucleus is a fundamental task in microscopy image analysis and supports many other quantitative studies such as object counting, segmentation, tracking, etc. Deep neural networks are emerging as a powerful tool for biomedical image computing; in particular, convolutional neural networks have been widely applied to nucleus/cell detection in microscopy images. However, almost all models are tailored for specific datasets and their applicability to other microscopy image data remains unknown. Some existing studies casually learn and evaluate deep neural networks on multiple microscopy datasets, but there are still several critical, open questions to be addressed. RESULTS: We analyze the applicability of deep models specifically for nucleus detection across a wide variety of microscopy image data. More specifically, we present a fully convolutional network-based regression model and extensively evaluate it on large-scale digital pathology and microscopy image datasets, which consist of 23 organs (or cancer diseases) and come from multiple institutions. We demonstrate that for a specific target dataset, training with images from the same types of organs might be usually necessary for nucleus detection. Although the images can be visually similar due to the same staining technique and imaging protocol, deep models learned with images from different organs might not deliver desirable results and would require model fine-tuning to be on a par with those trained with target data. We also observe that training with a mixture of target and other/non-target data does not always mean a higher accuracy of nucleus detection, and it might require proper data manipulation during model training to achieve good performance. CONCLUSIONS: We conduct a systematic case study on deep models for nucleus detection in a wide variety of microscopy images, aiming to address several important but previously understudied questions. We present and extensively evaluate an end-to-end, pixel-to-pixel fully convolutional regression network and report a few significant findings, some of which might have not been reported in previous studies. The model performance analysis and observations would be helpful to nucleus detection in microscopy images.

Reduction of Autophagic Accumulation in Pompe Disease Mouse Model Following Gene Therapy.

BACKGROUND: Pompe disease is a fatal neuromuscular disorder caused by a deficiency in acid α-glucosidase, an enzyme responsible for glycogen degradation in the lysosome. Currently, the only approved treatment for Pompe disease is enzyme replacement therapy (ERT), which increases patient survival, but does not fully correct the skeletal muscle pathology. Skeletal muscle pathology is not corrected with ERT because low cation-independent mannose-6-phosphate receptor abundance and autophagic accumulation inhibits the enzyme from reaching the lysosome. Thus, a therapy that more efficiently targets skeletal muscle pathology, such as adeno-associated virus (AAV), is needed for Pompe disease. OBJECTIVE: The goal of this project was to deliver a rAAV9-coGAA vector driven by a tissue restrictive promoter will efficiently transduce skeletal muscle and correct autophagic accumulation. METHODS: Thus, rAAV9-coGAA was intravenously delivered at three doses to 12-week old Gaa-/- mice. 1 month after injection, skeletal muscles were biochemically and histologically analyzed for autophagy-related markers. RESULTS: At the highest dose, GAA enzyme activity and vacuolization scores achieved therapeutic levels. In addition, resolution of autophagosome (AP) accumulation was seen by immunofluorescence and western blot analysis of autophagy-related proteins. Finally, mice treated at birth demonstrated persistence of GAA expression and resolution of lysosomes and APs compared to those treated at 3 months. CONCLUSION: In conclusion, a single systemic injection of rAAV9-coGAA ameliorates vacuolar accumulation and prevents autophagic dysregulation.