Search

Background The Blumgart anastomosis has been established as one of the safest anastomoses for pancreas remnant reconstruction, with low rates of postoperative pancreatic fistula (POPF) and postoperative complications. However, how to make laparoscopic pancreaticoenterostomy easier and safer is still a subject to be discussed. Methods Data of patients undergoing laparoscopic pancreaticoduodenectomy from April 2014 to December 2019 were retrospectively analyzed. Results 20 cases of half-invagination anastomosis (Group HI) and 26 cases of Cattell-warren anastomosis (Group CW) were included. Intraoperative blood loss, Operative time and Postoperative drainage tube placement time of Group HI was significantly less than those of Group CW. Patients of Clavien-Dindo grade III and above in Group HI was significantly less than Control Group. Group Incidence of POPF in Group HI was significantly lower than that in Group CW. No high-risk group emerged during Fistula risk score analytical phase, and the highest risk of moderate-risk group was pancreatic leakage. Respectively, incidence of pancreatic leakage in Group HI and Group CW was 7.7% and 46.67%, while incidence of Group HI was significantly lower than that in the Group CW. Conclusions The Blumgart-anastomosis based half-invagination pancreaticoenterostomy with better applicability to laparoscopy can effectively reduce the incidence of postoperative pancreatic leakage.

We focus on unsupervised representation learning for skeleton based action recognition. Existing unsupervised approaches usually learn action representations by motion prediction but they lack the ability to fully learn inherent semantic similarity. In this paper, we propose a novel framework named Prototypical Contrast and Reverse Prediction (PCRP) to address this challenge. Different from plain motion prediction, PCRP performs reverse motion prediction based on encoder-decoder structure to extract more discriminative temporal pattern, and derives action prototypes by clustering to explore the inherent action similarity within the action encoding. Specifically, we regard action prototypes as latent variables and formulate PCRP as an expectation-maximization (EM) task. PCRP iteratively runs (1) E-step as to determine the distribution of action prototypes by clustering action encoding from the encoder while estimating concentration around prototypes, and (2) M-step as optimizing the model by minimizing the proposed ProtoMAE loss, which helps simultaneously pull the action encoding closer to its assigned prototype by contrastive learning and perform reverse motion prediction task. Besides, the sorting can also serve as a temporal task similar as reverse prediction in the proposed framework. Extensive experiments on N-UCLA, NTU 60, and NTU 120 dataset present that PCRP outperforms main stream unsupervised methods and even achieves superior performance over many supervised methods.

Existing no-reference (NR) image quality assessment (IQA) metrics are still not convincing for evaluating the quality of the camera-captured images. Toward tackling this issue, we, in this article, establish a novel NR quality metric for quantifying the quality of the camera-captured images reliably. Since the image quality is hierarchically perceived from the low-level preliminary visual perception to the high-level semantic comprehension in the human brain, in our proposed metric, we characterize the image quality by exploiting both the low-level image properties and the high-level semantics of the image. Specifically, we extract a series of low-level features to characterize the fundamental image properties, including the brightness, saturation, contrast, noiseness, sharpness, and naturalness, which are highly indicative of the camera-captured image quality. Correspondingly, the high-level features are designed to characterize the semantics of the image. The low-level and high-level perceptual features play complementary roles in measuring the image quality. To infer the image quality, we employ the support vector regression (SVR) to map all the informative features to a single quality score. Thorough tests conducted on two standard camera-captured image databases demonstrate the effectiveness of the proposed quality metric in assessing the image quality and its superiority over the state-of-the-art NR quality metrics. The source code of the proposed metric for camera-captured images is released at https://github.com/YT2015?tab=repositories.

Currently, depression has become a common mental disorder, especially among postgraduates. It is reported that postgraduates have a higher risk of depression than the general public, and they are more sensitive to contact with others. Thus, a non-contact and effective method for detecting people at risk of depression becomes an urgent demand. In order to make the recognition of depression more reliable and convenient, we propose a multi-modal gait analysis-based depression detection method that combines skeleton modality and silhouette modality. Firstly, we propose a skeleton feature set to describe depression and train a Long Short-Term Memory (LSTM) model to conduct sequence strategy. Secondly, we generate Gait Energy Image (GEI) as silhouette features from RGB videos, and design two Convolutional Neural Network (CNN) models with a new loss function to extract silhouette features from front and side perspectives. Then, we construct a multi-modal fusion model consisting of fusing silhouettes from the front and side views at the feature level and the classification results of different modalities at the decision level. The proposed multi-modal model achieved accuracy at 85.45% in the dataset consisting of 200 postgraduate students (including 86 depressive ones), 5.17% higher than the best single-mode model. The multi-modal method also shows improved generalization by reducing the gender differences. Furthermore, we design a vivid 3D visualization of the gait skeletons, and our results imply that gait is a potent biometric for depression detection.

Recently, referring image localization and segmentation has aroused widespread interest. However, the existing methods lack a clear description of the interdependence between language and vision. To this end, we present a bidirectional relationship inferring network (BRINet) to effectively address the challenging tasks. Specifically, we first employ a vision-guided linguistic attention module to perceive the keywords corresponding to each image region. Then, language-guided visual attention adopts the learned adaptive language to guide the update of the visual features. Together, they form a bidirectional cross-modal attention module (BCAM) to achieve the mutual guidance between language and vision. They can help the network align the cross-modal features better. Based on the vanilla language-guided visual attention, we further design an asymmetric language-guided visual attention, which significantly reduces the computational cost by modeling the relationship between each pixel and each pooled subregion. In addition, a segmentation-guided bottom-up augmentation module (SBAM) is utilized to selectively combine multilevel information flow for object localization. Experiments show that our method outperforms other state-of-the-art methods on three referring image localization datasets and four referring image segmentation datasets.

Millimeter wave (mmWave) spectrum promises unprecedented data rates in 5G New Radio (NR). However, mmWave links are susceptible to severe path and propagation losses. Implementation of directional antennas that can manifest multiple beams becomes necessary at 5G base stations (gNBs) and User Equipments (UEs). Random access procedure (RAP), which is the first stage to establish connections to gNB, in its current state would be inadequate for such systems. To support RAP, 5G NR introduced mapping of different subsets of preambles in Physical Random Access Channel (PRACH) to different beams. We explore changes in RAP due to preamble-beam mapping and present a novel online algorithm to dynamically distribute preambles amongst beams to achieve fair access opportunities. The proposed algorithm can also eliminate overload problem of the beams with large UE population especially for high arrival rates. We extend the proposed algorithm to be applicable for RAP with access class barring mechanism which enables UEs to transmit a preamble with an optimal probability and, therefore, reduce access congestion. Through extensive simulations, we validate the efficiency of our proposed algorithms in providing fair channel access opportunities, improving throughput (or stability region), and reducing access delay when the system has high rate of UE arrivals and has unbalanced UE arrivals over different beams.

The protection of original achievements including patents and copyrights is a significant and critical issue in today's knowledge-driven economy. In this article, we propose and develop a blockchain service architecture to enhance information traceability and protection effectiveness. Our proposed service architecture is enabled by the core functionalities of blockchain technology including distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Through this blockchain-based traceability system, we can record, secure, validate, and track original achievements’ registrations and other related transactions. The results of our simulation experiments further validate the effectiveness and robustness of the proposed traceability system design. Our experimental analysis shows that the proposed blockchain-based design can effectively enhance original achievements traceability with an embedded automatic incentive rewarding mechanism for both the creation and protection of original achievements. Moreover, our performance analysis and comparative analysis show that the proposed method has more advantages over several other methods. While our study provides an effective solution to address the existing challenges in intellectual property rights and achievements patents protection, the breadth of the blockchain concept and its applications require nuanced investigations in many different contexts. Thus, the proposed blockchain-based traceability system highlights the potential for broader applications of this disruptive technology in many other domains.

Investigating the prognostic value of the Murray law-based quantitative flow ratio (μQFR) on the clinical outcome after treatment of in-stent restenosis (ISR) with a drug-coated balloon (DCB).Patients participating in a previous randomized clinical trial for DCB-ISR were post-hoc analyzed. The primary endpoint was vessel-oriented composite endpoint (VOCE), defined as cardiac death, target vessel-related myocardial infarction, and ischemia-driven target vessel revascularization. μQFRs at baseline and after DCB angioplasty was calculated, and its prognostic value as a predictor of VOCE was explored in Cox regression.A total of 169 lesions in 169 patients were analyzed. At one-year follow-up, 20 VOCEs occurred in 20 patients. Receiver-operating characteristic curve analysis identified a post-procedural μQFR of ≤ 0.89 as the best cut-off to predict VOCE (area under curve [AUC]: 0.74; 95% confidence interval [CI]: 0.67-0.80; p0.001), superior to post-procedural in-stent percent diameter stenosis (DS), which reported an AUC of 0.61 (95% CI: 0.53-0.68; p = 0.18). Post-procedural μQFR was significantly lower in patients with VOCE compared with those without (0.88 [interquartile range: 0.79-0.94] vs. 0.96 [interquartile range: 0.91-0.98], respectively; p0.001). After correction for potential confounders, post-procedural μQFR ≤ 0.89 was associated with a 6-fold higher risk of VOCE than lesions with μQFR0.89 (hazard ratio: 5.94; 95% CI: 2.33-15.09; p0.001).Post-procedural μQFR may become a promising predictor of clinical outcome after treatment of DES-ISR lesions by DCB angioplasty.

In data-driven evolutionary optimization, most existing Gaussian processes (GPs)-assisted evolutionary algorithms (EAs) adopt stationary GPs (SGPs) as surrogate models, which might be insufficient for solving most optimization problems. This article finds that GPs in the optimization problems are nonstationary with great probability. We propose to employ a nonstationary GP (NSGP) surrogate model for data-driven evolutionary optimization, where the mean of the NSGP is allowed to vary with the decision variables, while its residue variance follows an SGP. In this article, the nonstationarity of GPs in the tested functions is theoretically analyzed. In addition, this article constructs an NSGP where the SGP is a degenerate case. Performance comparisons of the NSGP with the SGP and the NSGP-assisted EA (NSGP-MAEA) with the SGP-assisted EA (SGP-MAEA) are carried out on a set of benchmark problems and an antenna design problem. These comparison results demonstrate the competitiveness of the NSGP model.

In our model, a venture seeks capital through an initial coin offering (ICO). The ICO enables the venture to collect demand information from decentralized investors. The venture makes a tradeoff between ensuring the project’s success and forecasting market demand through token size and token price. We find that the higher the demand uncertainty and production cost, the greater the venture’s incentive to learn from its investors. To identify when the venture has an incentive to raise funds through an ICO, we compare it with traditional bank financing and analyze the venture’s preference between the two financing options. The results show that when demand uncertainty is high, an ICO can provide both financing and information benefits, whereas when demand uncertainty is low, although the venture does not collect information through an ICO, it can still get financing benefit. Only when demand uncertainty is intermediate, the venture prefers bank financing. In addition, we find that although the revenue sharing effect of the ICO results in an underinvestment issue, it can also alleviate the loss caused by the increased cost of production. Therefore, with high information accuracy, as production cost goes up, ICOs become more attractive than bank financing for the venture.

With the powerful learning ability of deep convolutional networks, deep clustering methods can extract the most discriminative information from individual data and produce more satisfactory clustering results. However, existing deep clustering methods usually ignore the relationship between the data. Fortunately, the graph convolutional network can handle such relationship, opening up a new research direction for deep clustering. In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks. While the cross-attention fusion module fuses two kinds of heterogeneous representation, the CAE module supplements the content information for the GAE module, which avoids the over-smoothing problem of GCN. In the GAE module, two novel loss functions are proposed that reconstruct the content and relationship between the data, respectively. Finally, the self-supervised module constrains the distributions of the middle layer representations of CAE and GAE to be consistent. Experimental results on different types of datasets prove the superiority and robustness of the proposed CaEGCN.

Freezing of gait (FoG) is identified as a sudden and brief episode of movement cessation despite the intention to continue walking. It is one of the most disabling symptoms of Parkinson's disease (PD) and often leads to falls and injuries. Many computer-aided FoG detection methods have been proposed to use data collected from unimodal sources, such as motion sensors, pressure sensors, and video cameras. However, there are limited efforts of multimodal-based methods to maximize the value of all the information collected from different modalities in clinical assessments and improve the FoG detection performance. Therefore, in this study, a novel end-to-end deep architecture, namely graph fusion neural network (GFN), is proposed for multimodal learning-based FoG detection by combining footstep pressure maps and video recordings. GFN constructs multimodal graphs by treating the encoded features of each modality as vertex-level inputs and measures their adjacency patterns to construct complementary FoG representations, thus reducing the representation redundancy among different modalities. In addition, since GFN is devised to process multimodal graphs of arbitrary structures, it is expected to achieve superior performance with inputs containing missing modalities, compared to the alternative unimodal methods. A multimodal FoG dataset was collected, which included clinical assessment videos and footstep pressure sequences of 340 trials from 20 PD patients. Our proposed GFN demonstrates a great promise of multimodal FoG detection with an area under the curve (AUC) of 0.882. To the best of our knowledge, this is one of the first studies to utilize multimodal learning for automated FoG detection, which offers significant opportunities for better patient assessments and clinical trials in the future.

Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings. This paper presents to amplify the subtle texture difference between camouflaged objects and the background for camouflaged object detection by formulating multiple texture-aware refinement modules to learn the texture-aware features in a deep convolutional neural network. The texture-aware refinement module computes the biased co-variance matrices of feature responses to extract the texture information, adopts an affinity loss to learn a set of parameter maps that help to separate the texture between camouflaged objects and the background, and leverages a boundary-consistency loss to explore the structures of object details. We evaluate our network on the benchmark datasets for camouflaged object detection both qualitatively and quantitatively. Experimental results show that our approach outperforms various state-of-the-art methods by a large margin.

Deep reinforcement learning is confronted with problems of sampling inefficiency and poor task migration capability. Meta-reinforcement learning (meta-RL) enables meta-learners to utilize the task-solving skills trained on similar tasks and quickly adapt to new tasks. However, meta-RL methods lack enough queries toward the relationship between task-agnostic exploitation of data and task-related knowledge introduced by latent context, limiting their effectiveness and generalization ability. In this article, we develop an algorithm for off-policy meta-RL that can provide the meta-learners with self-oriented cognition toward how they adapt to the family of tasks. In our approach, we perform dynamic task-adaptiveness distillation to describe how the meta-learners adjust the exploration strategy in the meta-training process. Our approach also enables the meta-learners to balance the influence of task-agnostic self-oriented adaption and task-related information through latent context reorganization. In our experiments, our method achieves 10%-20% higher asymptotic reward than probabilistic embeddings for actor-critic RL (PEARL).

Introduction: Therapy and immune mediated processes are associated with clonal evolution in multiple myeloma (MM). In this study, we performed whole-exome sequencing (WES) and single cell RNA sequencing (scRNA-seq) on plasma cells (PC) from bone marrow aspirates of the iliac crest (BM) and corresponding osteolytic lesions (OL) to investigate spatial heterogeneity in patients with newly diagnosed (NDMM) and relapsed/refractory MM (RRMM). Next generation flow (NGF) and T-cell receptor sequencing (TCRseq) were performed to investigate the immunogenomic landscape surrounding malignant PC. Methods: In a prospective trial, 18 patients (NDMM: n=10; RRMM: n=8) consented to an imaging-guided biopsy of an OL in addition to the regular BM sampling. At inclusion, 37 different locations were biopsied. Follow-up samples were obtained from 5 patients in remission after therapy. After CD138+ selection, PC were subjected to WES and scRNA-seq (Chromium, 10x genomics). TCRseq was performed using multiplex PCR (ImmunoSEQ, Adaptive biotechnologies) on the CD138- fraction. For scRNA-seq data analyses, Cell Ranger (v3.1.0) and the Seurat R toolkit (v3.1) were used. TCRseq data were analyzed with immunoSEQ ANALYZER (v3.0) and the immunarch R toolkit (v0.6.6.). NGF was performed to study subsets of T-, B-, NK- and dendritic cells (DC). Results: Median PC infiltration was higher in OL compared to random BM (50.0% vs 12.5%, p=0.041). WES revealed more mutations in RRMM compared to NDMM (median; range: 189;120-523 vs 71;23-136, p Conclusion: We report the first prospective clinical trial to investigate spatiotemporal immunogenomic heterogeneity in multiple myeloma as assessed by WES and scRNA-seq of PC and NGF and TCRseq of the non-PC compartment. We demonstrate spatial evolution and reduced TCR diversity especially in patients with RRMM and/or EMD. ScRNA-seq adds another layer of complexity compared to WES and helps identifying how PC create an immune suppressive BM niche. Disclosures Merz: Amgen, BMS, Celgene, Takeda: Honoraria. Block:GlaxoSmithKline LLC: Current Employment. McCarthy:Karyopharm: Consultancy, Honoraria; Magenta: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Advisory Board; Juno Therapeutics, a Bristol-Myers Squibb Company: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Advisory Board , Research Funding is to Roswell Park, Research Funding; AbbVie: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Advisory Board; Takeda: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Advisory Board; Janssen: Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Advisory Board; Starton: Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Advisory Board; Genentech: Consultancy, Honoraria. Hillengass:Adaptive, Amgen, BMS, Celgene, GSK, Janssen, Oncotracker, Takeda: Honoraria.

Battery energy storage effectively staBIlizes the electric grid and aids renewable integration by balancing supply and demand in real time. The importance of such storage is especially crucial in densely populated urban areas, where traditional storage techniques such as pumped hydroelectric energy storage and compressed-air energy storage are often not feasible.

Missing data widely exist in the raw or processed data, implying information loss. In many cases, missing values have to be accurately imputed for further use. In this paper, an extreme case, consecutively missing data in large-length and mainly remaining data in small-length, is discussed for time series varying with operating conditions, very universal in industrial processes. Firstly, to fully utilize the information of remaining data, a similar conditions screening scheme is provided, efficient to improve imputation accuracy. Then, multiple receding imputation via Gaussian process regression (GPR) and long short term memory (LSTM) neural network are proposed, deducing generic multiple combination imputation and bidirectional imputation structures. At last, applied for data imputation of extremely missing wind power data, condition-dependent on wind speed, imputation effects of the proposed methods are carefully compared. Simulation results reveal effectiveness of these methods to impute missing data under the extreme case, laying very important foundation for data-driven applications.

The purpose of this research was to understand the current status of stigma and illness uncertainty in patients with visible burns and explore the correlation between them. Measures to help patients alleviate shame and uncertainty in illness are also discussed. A cross-sectional study was conducted in a tertiary hospital from November 2020 to March 2021 for patients with burns on exposed parts of the face, neck, or limbs. The scales used in this study include demographic data questionnaires, the Social Impact Scale (SIS), and the Mishel Uncertainty in Illness Scale for Adults (MUIS-A). A two-tailed independent t-test was used to evaluate the differences in the respondents' sociodemographic characteristics, stigma, and illness uncertainty. The total stigma and illness uncertainty scores of 146 patients were 57.03 ± 6.762 and 68.59 ± 12.901, respectively. Spearman correlation analysis showed that stigma was positively correlated with illness uncertainty (r = 0.398, p0.01). Multiple regression analysis showed a relationship between stigma and uncertainty of illness (B = 0.215, p = 0.000), itching (B = 2.555, p = 0.01), residence (B = 2.545, p = 0.029), and age (B = 0.074, p = 0.037). The stigma level of patients with visible burns increased with increasing uncertainty regarding illness. Therefore, reducing the patients' uncertainty in illness is a way to intervene in stigma.

Recently, deep learning-based intelligent fault diagnosis methods have been developed rapidly, which rely on massive data to train the diagnosis model. However, it is usually difficult to collect sufficient failure data in practical industrial production, thus limits the application of intelligent diagnosis methods. To address the few-shot fault diagnosis problem, a task-sequencing meta learning (TSML) method is proposed in this paper. Firstly, meta learning model is trained over a series of learning tasks to obtain knowledge about how to diagnosis. Thus, the learned knowledge can help adapt and generalize with a few examples when dealing with new tasks that have never been encountered. Then, considering the difference and connection between different failures and diagnosis tasks, a task-sequencing algorithm is proposed to sort meta training tasks from easy to difficult, which followed the way human acquire knowledge. After evaluating the difficulty of each task, the proposed method learns simple tasks firstly and generalizes the learned knowledge to complex tasks. Better knowledge adaptability is obtained by gradually increasing the task difficulty. Finally, utilizing gradient-based meta learning, the initialization parameters are trained by a small number of gradient steps. The effectiveness of the proposed method is validated by a practice rolling bearing dataset and a power system dataset. The experiment results illustrate that the proposed method can identify new categories within only a few samples. In addition, it also shows advantages in fault diagnosis when the categories are fine-grained according to the working conditions.

Near-infrared and visual (NIR-VIS) face matching, as the most typical task in Heterogeneous Face Recognition (HFR), has attracted increasing attention in recent years. However, due to the large within-class discrepancies, including domain differences and residual discrepancies (i.e., lighting, expressions, occlusion, blurry, pose, etc), this is still a difficult task. Conventional NIR-VIS FR methods only focus on reducing the modality gap between cross-domain images, while neglecting to eliminate the residual variations. To better solve the above problems, this paper proposes a novel Orthogonal Modality Disentanglement and Representation Alignment (OMDRA) approach, which consists of three key components, including Modality-Invariant (MI) loss, Orthogonal Modality Disentanglement (OMD) and Deep Representation Alignment (DRA). Firstly, the MI loss is designed to learn modality-invariant and identity-discriminative representation, by increasing between-class separability and within-class compactness between NIR and VIS heterogeneous data. Secondly, the high-level Hybrid Facial Feature (HFF) layer of the backbone network is projected into two subspaces: the modality-related and identity-related subspaces. The OMD is designed to decouple modal information via an adversarial process, and we further impose Orthogonal Representation Decorrelation (ORD) to the OMD to decrease the correlation between identity representations and domain representations, as well as enhancing their representation capabilities. Finally, the DRA aims to eliminate the residual variations by performing a high-level representation alignment between non-neutral face and neutral face, which can effectively guides the network to learn discriminative and residual-invariant face representation. The joint scheme enables the disentanglement of modality variations, elimination of residual discrepancies, and the purification of identity information. Extensive experiments on challenging cross-domain databases indicate that our OMDRA method is superior to the state-of-the-art methods.