Tolerant Self-Distillation for image classification

Deep neural networks tend to suffer from the overfitting issue when the training data are not enough. In this paper, we introduce two metrics from the intra-class distribution of correct-predicted and incorrect-predicted samples to provide a new perspective on the overfitting issue. Based on it, we propose a knowledge distillation approach without pretraining a teacher model in advance named Tolerant Self-Distillation (TSD) for alleviating the overfitting issue. It introduces an online updating memory and selectively stores the class predictions of the samples from the past iterations, making it possible to distill knowledge across the iterations. Specifically, the class predictions stored in the memory bank serve as the soft labels for supervising the samples from the same class for the current iteration in a reverse way, i.e. the correct-predicted samples are supervised with the incorrect predictions while the incorrect-predicted samples are supervised with the correct predictions. Consequently, the premature convergence issue caused by the over-confident samples would be mitigated, which helps the model to converge to a better local optimum. Extensive experimental results on several image classification benchmarks, including small-scale, large-scale, and fine-grained datasets, demonstrate the superiority of the proposed TSD.

Ischemia-inhibited ferric chelate reductase 1 improves ferroptosis-mediated intestinal ischemia injury via Hippo signaling

The precise mechanism of ferroptosis as a regulatory cell death in intestinal ischemia injury induced by vascular intestinal obstruction (Vio) remains to be elucidated. Here, we evaluated iron levels, glutathione peroxidase 4 (GPX4) and Acyl-CoA synthetase long-chain family member 4 (ACSL4) changes after intestinal ischemia injury to validate ferroptosis. As an enzyme for Fe3+ reduction to Fe2+, Ferric Chelate Reductase 1 (FRRS1) is involved in the electron transport chain and the tricarboxylic acid (TCA) cycle in mitochondria. However, whether it is involved in ferroptosis and its role in intestinal ischemia injury need to be clarified. In the present study, FRRS1 was overexpressed in vivo and in vitro. The results showed that overexpression of FRRS1 prevented ischemia-induced iron levels, reactive oxygen species (ROS) production, lipid peroxidation, inflammatory responses, and cell death. Meanwhile, FRRS1 overexpression promoted GPX4 expression and suppressed ACSL4 levels. Further studies revealed that FRRS1 overexpression inhibited the activity of large tumor suppressor 1 (LATS1) / Yes-associated protein (YAP) / transcriptional co-activator with PDZ-binding motif (TAZ), a key component of Hippo signaling. In conclusion, this study demonstrates that FRRS1 is intimately involved in the inhibition of ferroptosis and thus protection of the intestine from intestinal ischemia injury, its downstream mechanism was related to Hippo signaling. These data provide new sight for the prevention and treatment of intestinal ischemia injury.

Hierarchical matching and reasoning for multi-query image retrieval

As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and text queries, which neglect the hierarchical guidance of multi-level similarities and result in incomplete alignments. Besides, the high-level semantic correlations that intrinsically connect different region-query pairs are rarely considered. To address above limitations, we propose a novel Hierarchical Matching and Reasoning Network (HMRN) for MQIR. It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. HMRN consists of two modules: Scalar-based Matching (SM) module and Vector-based Reasoning (VR) module. Specifically, the SM module characterizes the multi-level alignment similarity, which consists of a fine-grained local-level similarity and a context-aware global-level similarity. Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity. Finally, these three-level similarities are aggregated into a joint similarity space to form the ultimate similarity. Extensive experiments on the benchmark dataset demonstrate that our HMRN substantially surpasses the current state-of-the-art methods. For instance, compared with the existing best method Drill-down, the metric R@1 in the last round is improved by 23.4%. Our source codes will be released at https://github.com/LZH-053/HMRN.

The top 100 most-cited papers in incisional hernia: a bibliometric analysis from 2003 to 2023

PURPOSE

Incisional hernia (IH) is one of the most common complications after abdominal surgeries and may bring great suffering to patients. This study aims to evaluate the global trends in IH research from 2003 to 2023 and visualize the frontiers using bibliometric analysis.

METHODS

The literature search was conducted on the Web of Science for IH studies published from 2003 to 2023 and sorted by citation frequency. The top 100 most-cited articles were analyzed by the annual publication number, prolific countries and institutions, influential author and journal, and the number of citations through descriptive statistics and visualization.

RESULTS

The top paper was cited 1075 times and the median number of citations was 146. All studies were published between 2003 and 2019 and the most prolific year was 2003 with 14 articles. Jeekel J and Rosen M were regarded as the most productive authors with ten articles each and acquired 2738 and 2391 citations, respectively. The top three institutions with the most productive articles were Erasmus Mc, Carolinas Med Ctr, and Univ Utah, while the top three countries were the United States, Netherlands and Germany. The most frequent keyword was "incisional hernia" with 55 occurrences, followed by "mesh repair", "randomized controlled trial", and "polypropylene".

CONCLUSION

The 100 most-cited papers related to IH were published predominantly by USA and European countries, with randomized controlled trial (RCT) and observational study designs, addressing topics related to risk factors, complications, mesh repair, and mesh components.

The causal association between body fat distribution and risk of abdominal wall hernia: a two-sample Mendelian randomization study

PURPOSE

Obesity and a high body mass index (BMI) are considered as risk factors for abdominal wall hernia (AWH). However, anthropometric measures of body fat distribution (BFD) seem to be better indicators in the hernia field. This Mendelian randomization analysis aimed to generate more robust evidence for the impact of waist circumstance (WC), body, trunk, arm, and leg fat percentages (BFP, TFP, AFP, LFP) on AWH.

METHODS

A univariable MR design was employed and the summary statistics allowing for assessment were obtained from the genome-wide association studies (GWASs). An inverse variance weighted (IVW) method was applied as the primary analysis, and the odds ratio value was used to evaluate the causal relationship between BFD and AWH.

RESULTS

None of the MR-Egger regression intercepts deviated from null, indicating no evidence of horizontal pleiotropy (p > 0.05). The Cochran Q test showed heterogeneity between the genetic IVs for WC (p = 0.005; p = 0.005), TFP (p < 0.001; p < 0.001), AFP-L (p = 0.016; p = 0.015), LFP-R (p = 0.012; p = 0.009), and LFP-L (p < 0.001; p < 0.001). Taking the IVW random-effects model as gold standard, each standard deviation increment in genetically determined WC, BFP, TFP, AFP-R, AFP-L, LFP-R, and LFP-L raised the risk of AWH by 70.9%, 70.7%, 56.5%, 69.7%, 78.3%, 87.7%, and 72.5%, respectively.

CONCLUSIONS

This study proves the causal relationship between AWH and BFD, attracting more attention from BMI to BFD. It provides evidence-based medical evidence that healthy figure management can prevent AWH.

High Systemic Inflammatory Protein Index Is Associated with Clinically Ineffective Reperfusion in Acute Anterior Circulation Ischemic Stroke Patients Undergoing Endovascular Treatment

Nearly half of the patients undergoing endovascular treatment (EVT) do not have favorable outcomes despite successful recanalization of the occluded artery, which is also known as clinically ineffective reperfusion. We proposed a novel index-the systemic inflammatory protein index (SIPI), based on albumin, globulin, and C-reaction protein (CRP). We aimed to evaluate the relationship between inflammatory biomarkers at varying time points and the 90-day functional outcomes and investigate inflammatory biomarkers' dynamic changes during hospitalization in acute ischemic stroke (AIS) patients of anterior circulation undergoing EVT. We retrospectively recruited consecutive patients diagnosed with AIS of anterior circulation and treated with EVT from January 2018 to June 2022 in Nanfang Hospital. Albumin, globulin, and CRP were recorded on admission, 1 day, 3 days, and 7 days after EVT. An unfavorable functional outcome was defined as 90-day modified Rankin Scale (mRS) of 3-6. Albumin-to-globulin ratio (AGR), C-reactive protein-to-albumin ratio (CAR), and SIPI were calculated as follows: AGR = albumin/globulin; CAR = CRP/albumin; SIPI = CRP × globulin/albumin. A total of 238 consecutive anterior circulation AIS patients with EVT were included, among which 145 (60.9%) patients had unfavorable outcomes. After adjusting for confounding factors, admission globulin, admission AGR, 1-day AGR, 3-day albumin, 3-day CRP, 3-day CAR, 3-day SIPI, 7-day albumin, 7-day CRP, 7-day CAR, and 7-day SIPI showed an independent association with 90-day functional outcome. Of them, 3-day SIPI had the most robust discriminative ability with an area under the curve of 0.719 (CI 0.630-0.808, p < 0.001). There were differences in the dynamic change of inflammatory biomarkers between the subjects with favorable and unfavorable functional outcomes. Inflammatory biomarkers, including albumin, globulin, CRP, AGR, CAR, and SIPI, are independent predictors of 90-day unfavorable outcomes in anterior circulation AIS patients with EVT. SIPI of day 3 has the highest predictive value.

MCD-Net: Toward RGB-D Video Inpainting in Real-World Scenes

Video inpainting gains an increasing amount of attention ascribed to its wide applications in intelligent video editing. However, despite tremendous progress made in RGB video inpainting, the existing RGB-D video inpainting models are still incompetent to inpaint real-world RGB-D videos, as they simply fuse color and depth via explicit feature concatenation, neglecting the natural modality gap. Moreover, current RGB-D video inpainting datasets are synthesized with homogeneous and delusive RGB-D data, which is far from real-world application and cannot provide comprehensive evaluation. To alleviate these problems and achieve real-world RGB-D video inpainting, on one hand, we propose a Mutually-guided Color and Depth Inpainting Network (MCD-Net), where color and depth are reciprocally leveraged to inpaint each other implicitly, mitigating the modality gap and fully exploiting cross-modal association for inpainting. On the other hand, we build a Video Inpainting with Depth (VID) dataset to supply diverse and authentic RGB-D video data with various object annotation masks to enable comprehensive evaluation for RGB-D video inpainting under real-world scenes. Experimental results on the DynaFill benchmark and our collected VID dataset demonstrate our MCD-Net not only yields the state-of-the-art quantitative performance but successfully achieves high-quality RGB-D video inpainting under real-world scenes. All resources are available at https://github.com/JCATCV/MCD-Net.

Risk factors for incisional hernia after gastrointestinal surgeries in non-tumor patients

PURPOSE

Incisional hernia (IH) is a common secondary ventral hernia after abdominal incisions and there is still little reliable evidence to predict and prevent IH. This study aimed to estimate risk factors of its incidence, especially concentrating on blood results.

METHODS

96 patients received midline laparotomy for gastrointestinal benign diseases and suffered from IH were enrolled in the IH group. A control group of 192 patients were randomly selected from patients underwent midline laparotomy for gastrointestinal benign diseases without IH.

RESULTS

Patients in the IH group exhibited higher age (P < 0.001), BMI (P < 0.001), hernia history (P = 0.001) and laparotomy history (P < 0.001). Rate of coronary heart disease (P = 0.046), hypertension (P < 0.001), diabetes (P = 0.008), incisional infection (P = 0.004) and emergency surgery (P = 0.041) were also higher in the IH group. Patients with IH had lower levels of Hb (P = 0.002), TP (P = 0.013), ALB (P < 0.001), A/G (P = 0.019), PA (P < 0.001), HDL-C (P = 0.008) and ApoA1 (P = 0.005). Meanwhile, patients in the control group bore lower levels of LDH (P = 0.008), GLU (P = 0.007), BUN (P = 0.048), UA (P = 0.021), TG (P = 0.011), TG/HDL-C (P = 0.002), TC/HDL-C (P = 0.013), ApoB/ApoA1 (P = 0.001) and Lp(a) (P = 0.001). A multivariate logistic regression revealed that high BMI, laparotomy history, incisional infection, decreased PA, elevated levels of UA, Lp(a) and ApoB/ApoA1 were independent risk factors of IH.

CONCLUSION

This is the first study to reveal the relationship between IH and serum biochemical levels, and give a prediction through the nomograph model. These results will help surgeons identify high-risk patients, and take measures to prevent IH during the perioperative period.

Conformal Loss-Controlling Prediction

Conformal prediction (CP) is a learning framework controlling prediction coverage of prediction sets, which can be built on any learning algorithm for point prediction. This work proposes a learning framework named conformal loss-controlling prediction, which extends CP to the situation where the value of a loss function needs to be controlled. Different from existing works about risk-controlling prediction sets and conformal risk control with the purpose of controlling the expected values of loss functions, the proposed approach in this article focuses on the loss for any test object, which is an extension of CP from miscoverage loss to some general loss. The controlling guarantee is proved under the assumption of exchangeability of data in finite-sample cases and the framework is tested empirically for classification with a class-varying loss and statistical postprocessing of numerical weather forecasting applications, which are introduced as point-wise classification and point-wise regression problems. All theoretical analysis and experimental results confirm the effectiveness of our loss-controlling approach.

USER: Unified Semantic Enhancement With Momentum Contrast for Image-Text Retrieval

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key challenge is to measure the semantic similarity across different modalities. Although significant progress has been achieved, existing approaches typically suffer from two major limitations: (1) It hurts the accuracy of the representation by directly exploiting the bottom-up attention based region-level features where each region is equally treated. (2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism. To address these limitations, we propose a Unified Semantic Enhancement Momentum Contrastive Learning (USER) method for ITR. Specifically, we delicately design two simple but effective Global representation based Semantic Enhancement (GSE) modules. One learns the global representation via the self-attention algorithm, noted as Self-Guided Enhancement (SGE) module. The other module benefits from the pre-trained CLIP module, which provides a novel scheme to exploit and transfer the knowledge from an off-the-shelf model, noted as CLIP-Guided Enhancement (CGE) module. Moreover, we incorporate the training mechanism of MoCo into ITR, in which two dynamic queues are employed to enrich and enlarge the scale of negative sample pairs. Meanwhile, a Unified Training Objective (UTO) is developed to learn from mini-batch based and dynamic queue based samples. Extensive experiments on the benchmark MSCOCO and Flickr30K datasets demonstrate the superiority of both retrieval accuracy and inference efficiency. For instance, compared with the existing best method NAAF, the metric R@1 of our USER on the MSCOCO 5K Testing set is improved by 5% and 2.4% on caption retrieval and image retrieval without any external knowledge or pre-trained model while enjoying over 60 times faster inference speed. Our source code will be released at https://github.com/zhangy0822/USER.

Imbalance Mitigation for Continual Learning via Knowledge Decoupling and Dual Enhanced Contrastive Learning

Continual learning (CL) aims at studying how to learn new knowledge continuously from data streams without catastrophically forgetting the previous knowledge. One of the key problems is catastrophic forgetting, that is, the performance of the model on previous tasks declines significantly after learning the subsequent task. Several studies addressed it by replaying samples stored in the buffer when training new tasks. However, the data imbalance between old and new task samples results in two serious problems: information suppression and weak feature discriminability. The former refers to the information in the sufficient new task samples suppressing that in the old task samples, which is harmful to maintaining the knowledge since the biased output worsens the consistency of the same sample's output at different moments. The latter refers to the feature representation being biased to the new task, which lacks discrimination to distinguish both old and new tasks. To this end, we build an imbalance mitigation for CL (IMCL) framework that incorporates a decoupled knowledge distillation (DKD) approach and a dual enhanced contrastive learning (DECL) approach to tackle both problems. Specifically, the DKD approach alleviates the suppression of the new task on the old tasks by decoupling the model output probability during the replay stage, which better maintains the knowledge of old tasks. The DECL approach enhances both low-and high-level features and fuses the enhanced features to construct contrastive loss to effectively distinguish different tasks. Extensive experiments on three popular datasets show that our method achieves promising performance under task incremental learning (Task-IL), class incremental learning (Class-IL), and domain incremental learning (Domain-IL) settings.

Risk factors for super-refractory and mortality in generalized convulsive status epilepticus: a 10-year retrospective cohort study

Background

Generalized convulsive status epilepticus (GCSE) is one of the most challenging life-threatening neurological emergencies. If GCSE becomes super-refractory, it is associated with significant mortality. Although aggressive management of prolonged status epilepticus was conducted, the mortality has not decreased since the late 1990s.

Objectives

The present study aimed to explore the risk factors for progression to super-refractory in patients with generalized convulsive status epilepticus (GCSE). Moreover, we illustrated the risk factors for mortality in GCSE patients.

Design

An observational retrospective cohort study.

Methods

We conducted a retrospective study of patients with GCSE admitted to our neurocritical unit, in Guangzhou, China, from October 2010 to February 2021. The data of sociodemographic information, etiology, laboratory results, treatment, and prognosis were collected and analyzed.

Results

A total of 106 patients were enrolled; 51 (48%) of them developed super-refractory status epilepticus (SRSE). Multivariate logistic regression analysis demonstrated that patients with autoimmune encephalitis (p = 0.015) and intracranial infection (p = 0.019) are likely to progress to SRSE. The in-hospital mortality was 11.8% and 9.1% for patients in the SRSE and non-SRSE groups, respectively (p = 0.652). Multivariate logistic regression analysis showed that neutrophil-to-lymphocyte ratios (NLR) at admission were independently associated with in-hospital mortality. Up to 31.4% of SRSE patients and 29.1% of non-SRSE patients died within 6 months after discharge (p = 0.798). Multivariate logistic regression analysis showed that plasma exchange (PE) was a protective factor for 6-month mortality. A high NLR at discharge was a risk factor for 6-month mortality.

Conclusion

In the current study, about 48% of GCSE patients progressed to SRSE. Regarding etiology, autoimmune encephalitis or intracranial infection was prone to SRSE. No significant differences were observed in the in-hospital and 6-month mortality between SRSE and non-SRSE groups. Multivariate logistic regression analysis showed that NLR at admission and discharge was an independent predictor of in-hospital and 6-month mortality, respectively. Moreover, PE significantly reduced the 6-month mortality.

[The efficacy of chemotherapy re-challenge in third-line setting for metastatic colorectal cancer patients: a real-world study]

Objective: To explore the efficacy of chemotherapy re-challenge in the third-line setting for patients with metastatic colorectal cancer (mCRC) in the real world. Methods: The clinicopathological data, treatment information, recent treatment efficacy, adverse events and survival data of mCRC patients who had disease progression after treatment with oxaliplatin-based and/or irinotecan-based chemotherapy and received third-line chemotherapy re-challenge from January 2013 to December 2020 at Tianjin Medical University Cancer Institute and Hospital were retrospectively collected. Survival curves were plotted with the Kaplan-Meier method, and the Cox proportional hazard model was used to analyze the prognostic factors. Results: A total of 95 mCRC patients were included. Among them, 32 patients (33.7%) received chemotherapy alone and 63 patients (66.3%) received chemotherapy combined with targeted drugs. Eighty-three patients were treated with dual-drug chemotherapy (87.4%), including oxaliplatin re-challenge in 35 patients and irinotecan re-challenge in 48 patients. The remaining 12 patients were treated with triplet chemotherapy regimens (12.6%). Among them, as 5 patients had sequential application of oxaliplatin and irinotecan in front-line treatments, their third-line therapy re-challenged both oxaliplatin and irinotecan; 7 patients only had oxaliplatin prescription before, and these patients re-challenged oxaliplatin in the third-line treatment. The overall response rate (ORR) and disease control rate (DCR) reached 8.6% (8/93) and 61.3% (57/93), respectively. The median progression free survival (mPFS) and median overall survival (mOS) were 4.9 months and 13.0 months, respectively. The most common adverse events were leukopenia (34.7%) and neutropenia (34.7%), followed by gastrointestinal adverse reactions such as nausea (32.6%) and vomiting (31.6%). Grade 3-4 adverse events were mostly hematological toxicity. Cox multivariate analysis showed that gender (HR=1.609, 95% CI: 1.016-2.548) and the PFS of front-line treatments (HR=0.598, 95% CI: 0.378-0.947) were independent prognostic factors. Conclusion: The results suggested that it is safe and effective for mCRC patients to choose third-line chemotherapy re-challenge, especially for patients with a PFS of more than one year in front-line treatments.

Balancing Feature Alignment and Uniformity for Few-Shot Classification

In Few-Shot Learning (FSL), the objective is to correctly recognize new samples from novel classes with only a few available samples per class. Existing methods in FSL primarily focus on learning transferable knowledge from base classes by maximizing the information between feature representations and their corresponding labels. However, this approach may suffer from the "supervision collapse" issue, which arises due to a bias towards the base classes. In this paper, we propose a solution to address this issue by preserving the intrinsic structure of the data and enabling the learning of a generalized model for the novel classes. Following the InfoMax principle, our approach maximizes two types of mutual information (MI): between the samples and their feature representations, and between the feature representations and their class labels. This allows us to strike a balance between discrimination (capturing class-specific information) and generalization (capturing common characteristics across different classes) in the feature representations. To achieve this, we adopt a unified framework that perturbs the feature embedding space using two low-bias estimators. The first estimator maximizes the MI between a pair of intra-class samples, while the second estimator maximizes the MI between a sample and its augmented views. This framework effectively combines knowledge distillation between class-wise pairs and enlarges the diversity in feature representations. By conducting extensive experiments on popular FSL benchmarks, our proposed approach achieves comparable performances with state-of-the-art competitors. For example, we achieved an accuracy of 69.53% on the miniImageNet dataset and 77.06% on the CIFAR-FS dataset for the 5-way 1-shot task.

Safety and efficacy of glibenclamide combined with rtPA in acute cerebral ischemia with occlusion/stenosis of anterior circulation (SE-GRACE): a randomized, double-blind, placebo-controlled trial

Background

Glibenclamide alleviates brain edema and improves neurological outcomes in experimental models of stroke. We aimed to assess whether glibenclamide improves functional outcomes in patients with acute ischemic stroke treated with recombinant tissue plasminogen activator (rtPA).

Methods

In this randomized, double-blind, placebo-controlled trial, patients with acute ischemic stroke were recruited to eight academic hospitals in China. Patients were eligible if they were aged 18-74 years, presented with a symptomatic anterior circulation occlusion with a deficit on the NIHSS of 4-25, and had been treated with rtPA within 4.5 h of symptom onset. We used web-based randomization (1:1) to allocate eligible participants to the glibenclamide or placebo group, stratified according to endovascular treatment and baseline stroke severity. Glibenclamide or placebo was taken orally or via tube feeding at a loading dose of 1.25 mg within 10 h after symptom onset, followed by 0.625 mg every 8 h for 5 days. The primary outcome was the proportion of patients with good outcomes (modified Rankin Scale of 0-2) at 90 days, assessed in all randomly assigned patients who had been correctly diagnosed and had begun study medication. The study is registered with ClinicalTrials.gov, NCT03284463, and is closed to new participants.

Findings

Between January 1, 2018, and May 28, 2022, 305 patients were randomly assigned, of whom 272 (142 received glibenclamide and 130 received placebo) were included in the primary efficacy analysis. 103 (73%) patients in the glibenclamide group and 94 (72%) in the placebo group had a good outcome (adjusted risk difference 0.002, 95% CI -0.098 to 0.103; p = 0.96). 12 (8%) patients allocated to glibenclamide and seven (5%) patients allocated to placebo died from any cause at 90 days (p = 0.35). The number and type of adverse events were similar between the two groups. There were no drug-related adverse events and no drug-related deaths.

Interpretation

The addition of glibenclamide to thrombolytic therapy did not increase the proportion of patients who achieved good outcomes after stroke compared with placebo, but it did not lead to any safety concerns.

Funding

Southern Medical University and Nanfang Hospital.

Visual-quality-driven unsupervised image dehazing

Most of the existing learning-based dehazing methods require a diverse and large collection of paired hazy/clean images, which is intractable to obtain. Therefore, existing dehazing methods resort to training on synthetic images. This may result in a possible domain shift when treating real scenes. In this paper, we propose a novel unsupervised dehazing (lightweight) network without any reference images to directly predict clear images from the original hazy images, which consists of an interactive fusion module (IFM) and an iterative optimization module (IOM). Specifically, IFM interactively fuses multi-level features to make up for the missing information among deep and shallow features while IOM iteratively optimizes dehazed results to obtain pleasing visual effects. Particularly, based on the observation that hazy images usually suffer from quality degradation, four non-reference visual-quality-driven loss functions are designed to enable the network trained in an unsupervised way, including dark channel loss, contrast loss, saturation loss, and edge sharpness loss. Extensive experiments on two synthetic datasets and one real-world dataset demonstrate that our method performs favorably against the state-of-the-art unsupervised dehazing methods and even matches some supervised methods in terms of metrics such as PSNR, SSIM, and UQI.

Self-powered and broadband CuSCN/Si heterojunction photodetector for multi-color imaging based on diffuse reflection mode

Copper thiocyanate (CuSCN) has been widely used in photodetectors (PDs). However, the reported CuSCN-based PDs are suffered from narrow operating wavelength range and relatively low photodetection performance. Here, we fabricate an CuSCN/Si heterojunction PD by a simple low-temperature solution spin-coating method achieving excellent performance. Our designed CuSCN/Si PD exhibits a broadband response range covering ultraviolet-visible-infrared, a high detectivity of 2.26 × 1012Jones coming from an ultralow dark current of 23 pA, and a decent responsivity of 11 mA W-1, a high linear dynamic range of 122 dB, and short response time of 25/150μ(rise and decay time). Moreover, we demonstrate multi-color imaging across the wide wavelength range, indicating the CuSCN/Si PD has a promising potential in the imaging field. This work may pave the way for fabricating low-cost, nontoxicity, and high-performance CuSCN-based PD and broadening its applications.

Dual Distillation Discriminator Networks for Domain Adaptive Few-Shot Learning

Domain Adaptive Few-Shot Learning (DA-FSL) aims at accomplishing few-shot classification tasks on a novel domain with the aid of a large number of source-style samples and several target-style samples. It is essential for DA-FSL to transfer task knowledge from the source domain to the target domain and overcome the asymmetry amount of labeled data in both domains. To this end, we propose Dual Distillation Discriminator Networks (D3Net) from the perspective of the lack of labeled target domain style samples in DA-FSL. Specifically, we employ the idea of distillation discrimination to avoid the over-fitting caused by the unequal number of samples in the target and source domains, which trains the student discriminator by the soft labels from the teacher discriminator. Meanwhile, we design the task propagation stage and the mixed domain stage respectively from the level of feature space and instances to generate more target-style samples, which apply the task distributions and the sample diversity of the source domain to enhance the target domain. Our D3Net realizes the distribution alignment between the source domain and the target domain and constraints the FSL task distribution by prototype distributions on the mixed domain. Extensive experiments on three DA-FSL benchmark datasets, i.e., mini-ImageNet, tiered-ImageNet, and DomainNet, demonstrate that our D3Net achieves competitive performance.

Parents of preschoolers use multiple strategies to feed their children: Findings from an observational video pilot study

The current study leveraged observational data collection methods to fill gaps in our understanding of parent approach to feeding as well as child responses to various parental approaches. Specifically, the study aimed to: 1) characterize the broad range of food parenting practices used by parents of preschoolers during shared mealtimes at home, including differences by child gender, and 2) describe child responses to specific parent feeding practices. Forty parent-child dyads participated by recording two in-home shared meals. Meals were coded using a behavioral coding scheme that coded the occurrence of 11 distinct food parenting practices (e.g. indirect and direct commands, praise, bribes) and eight child responses (e.g., eat, refuse, cry/whine) to food parenting practices. Results revealed that parents engaged in a broad range of food parenting practices at meals. On average, parents in our sample used 10.51 (SD 7.83; Range 0-30) total food parenting practices per mealtime with a mean use of 3.38 (SD 1.67; Range 0-8) unique food parenting practices per mealtime. Use of indirect and direct commands to eat were most common; direct and indirect commands were used by 97.5% (n = 39) and 87.5% (n = 35) of parents at meals, respectively. No statistically significant differences were observed by child gender. No one specific feeding practice consistently yielded compliance or refusal to eat from the child, instead child responses were often mixed (e.g., compliance followed by refusal and/or refusal followed by compliance). However, use of praise to prompt eating was the practice that most often resulted in child compliance; 80.8% of children complied following parent's use of praise as a prompt to eat. Findings deepen our understanding of the types and frequency of food parenting practices used by parents of preschoolers during meals eaten at home and illuminate child responses to specific food parenting practices.

Measurement of Direct-Photon Cross Section and Double-Helicity Asymmetry at sqrt[s]=510 GeV in p[over →]+p[over →] Collisions

We present measurements of the cross section and double-helicity asymmetry A_{LL} of direct-photon production in p[over →]+p[over →] collisions at sqrt[s]=510  GeV. The measurements have been performed at midrapidity (|η|<0.25) with the PHENIX detector at the Relativistic Heavy Ion Collider. At relativistic energies, direct photons are dominantly produced from the initial quark-gluon hard scattering and do not interact via the strong force at leading order. Therefore, at sqrt[s]=510  GeV, where leading-order-effects dominate, these measurements provide clean and direct access to the gluon helicity in the polarized proton in the gluon-momentum-fraction range 0.02<x<0.08, with direct sensitivity to the sign of the gluon contribution.

[Clinical efficacy and safety analysis of 125I seed implantation in the treatment of mediastinal lymph node metastasis of lung cancer]

Objective: To investigate the clinical efficacy and safety of ¹²⁵I seed implantation in the treatment of mediastinal lymph node metastasis of lung cancer. Methods: Clinical data of 36 patients who underwent CT-guided ¹²⁵I seed implantation for mediastinal lymph node metastasis of lung cancer from August 2013 to April 2020 in three hospitals of the Northern radioactive particle implantation treatment collaboration group were retrospectively collected, including 24 males and 12 females, aged 46 to 84 years. Cox regression model was used to analyze the relationship between local control rate, survival rate and tumor stage, pathological type, postoperative D90, postoperative D100 and other variables, and to analyze the occurrence of complications. Results: The objective response rate of CT-guided ¹²⁵I seed implantation in the treatment of mediastinal lymph node metastasis of lung cancer was 75% (27/36), the median control time was 12 months, the 1-year local control rate was 47.2% (17/36), and the median survival time was 17 months. The 1-year and 2-year survival rates were 61.1% (22/36) and 22.2% (8/36) respectively. Univariate analysis showed that in the treatment of mediastinal lymph node metastasis with CT-guided ¹²⁵I implantation, factors related to local control included tumor stage (HR=5.246, 95%CI: 2.243-12.268, P<0.001), postoperative D90 (HR=0.191, 95%CI: 0.085-0.431, P<0.001), postoperative D100 (HR=0.240, 95%CI: 0.108-0.533, P<0.001); The factors affecting survival were tumor stage (HR=2.712, 95%CI: 1.356-5.425, P=0.005), postoperative D90 (HR=0.110, 95%CI: 0.041-0.294, P<0.001), postoperative D100 (HR=0.212, 95%CI: 0.092-0.489, P<0.001). Multivariate analysis showed that tumor stage (HR=5.305, 95%CI: 2.187-12.872, P<0.001) and postoperative D100 (HR=0.237, 95%CI: 0.099-0.568, P<0.001) were correlated with local control rate. Tumor stage (HR=2.347, 95%CI: 1.095-5.032, P=0.028) and postoperative D90 (HR=0.144, 95%CI: 0.051-0.410, P<0.001) were correlated with survival. In terms of complications, 9 of the 36 patients had pneumothorax, and 1 of them was cured by closed thoracic drainage for severe pneumothorax; 5 cases developed pulmonary hemorrhage and 5 cases developed hemoptysis, which recovered after hemostasis treatment. One case developed pulmonary infection and recovered after anti-inflammatory treatment. No radiation esophagitis and radiation pneumonia occurred; No grade 3 or higher complications occurred. Conclusion: ¹²⁵I seed implantation in the treatment of lung cancer mediastinal lymph node metastasis has a high local control rate and controllable adverse effects.

Knowledge Distillation Classifier Generation Network for Zero-Shot Learning

In this article, we present a conceptually simple but effective framework called knowledge distillation classifier generation network (KDCGN) for zero-shot learning (ZSL), where the learning agent requires recognizing unseen classes that have no visual data for training. Different from the existing generative approaches that synthesize visual features for unseen classifiers' learning, the proposed framework directly generates classifiers for unseen classes conditioned on the corresponding class-level semantics. To ensure the generated classifiers to be discriminative to the visual features, we borrow the knowledge distillation idea to both supervise the classifier generation and distill the knowledge with, respectively, the visual classifiers and soft targets trained from a traditional classification network. Under this framework, we develop two, respectively, strategies, i.e., class augmentation and semantics guidance, to facilitate the supervision process from the perspectives of improving visual classifiers. Specifically, the class augmentation strategy incorporates some additional categories to train the visual classifiers, which regularizes the visual classifier weights to be compact, under supervision of which the generated classifiers will be more discriminative. The semantics-guidance strategy encodes the class semantics into the visual classifiers, which would facilitate the supervision process by minimizing the differences between the generated and the real-visual classifiers. To evaluate the effectiveness of the proposed framework, we have conducted extensive experiments on five datasets in image classification, i.e., AwA1, AwA2, CUB, FLO, and APY. Experimental results show that the proposed approach performs best in the traditional ZSL task and achieves a significant performance improvement on four out of the five datasets in the generalized ZSL task.

Sb2Se3/CdS/ZnO photodetectors based on physical vapor deposition for color imaging applications

The reported antimony selenide (Sb₂Se₃) photodetectors (PDs) are still far away from color camera applications mainly due to the high operation temperature required in chemical vapor deposition (CVD) and the lack of high-density PD arrays. In this work, we propose a Sb₂Se₃/CdS/ZnO PD created by physical vapor deposition (PVD) operated at room temperature. Using PVD, a uniform film can be obtained, so the optimized PD has excellent photoelectric performance with high responsivity (250 mA/W), high detectivity (5.6 × 10¹² Jones), low dark current (∼10^-9 A), and short response time (rise: < 200 μs; decay: < 200 μs). With the help of advanced computational imaging technology, we successfully demonstrate color imaging applications by the single Sb₂Se₃ PD; thus, we expect this work can bring Sb₂Se₃ PDs in color camera sensors closer.

Automatic Classification Method of Arrhythmias Based on 12-Lead Electrocardiogram

Cardiovascular disease is one of the main causes of death worldwide. Arrhythmias are an important group of cardiovascular diseases. The standard 12-lead electrocardiogram signals are an important tool for diagnosing arrhythmias. Although 12-lead electrocardiogram signals provide more comprehensive arrhythmia information than single-lead electrocardiogram signals, it is difficult to effectively fuse information between different leads. In addition, most of the current researches working on automatic diagnosis of cardiac arrhythmias are based on modeling and analysis of single-mode features extracted from one-dimensional electrocardiogram sequences, ignoring the frequency domain features of electrocardiogram signals. Therefore, developing an automatic arrhythmia detection algorithm based on 12-lead electrocardiogram with high accuracy and strong generalization ability is still challenging. In this paper, a multimodal feature fusion model based on the mechanism is developed. This model utilizes a dual channel deep neural network to extract different dimensional features from one-dimensional and two-dimensional electrocardiogram time-frequency maps, and combines attention mechanism to effectively fuse the important features of 12-lead, thereby obtaining richer arrhythmia information and ultimately achieving accurate classification of nine types of arrhythmia signals. This study used electrocardiogram signals from a mixed dataset to train, validate, and evaluate the model, with an average of F1 score and average accuracy reached 0.85 and 0.97, respectively. Experimental results show that our algorithm has stable and reliable performance, so it is expected to have good practical application potential.

High-Performance Solar-Blind UV Phototransistors Based on ZnO/Ga2O3 Heterojunction Channels

High-performance phototransistor-based solar-blind (200-280 nm) ultraviolet (UV) photodetectors (PDs) are constructed with a low-cost thin-film ZnO/Ga₂O₃ heterojunction. The optimized PD shows high spectral selectivity (R254/R365 > 1 × 10³) with a photo-to-dark current ratio of ∼10⁴, a responsivity of 113 mA/W, a detectivity of 1.25 × 10¹² Jones, and a response speed of 41 ms under 254 nm UV light irradiation. It is found that the gate electrode of a three-terminal phototransistor can amplify the responsivity and increase the photo-to-dark current ratio because of the different densities of field-induced electrons at different gate biases. In addition, the built-in electric field at the ZnO/Ga₂O₃ heterojunction interface can control the distribution of the photoinduced electrons and the total conductivity of the heterojunction, which can further enhance device performance. Together with the simple fabrication process, the achieved results suggest that the three-terminal ZnO/Ga₂O₃ heterojunction phototransistor is a promising candidate for highly sensitive solar-blind PDs.

Semantic-Aware Dynamic Generation Networks for Few-Shot Human-Object Interaction Recognition

Recognizing human-object interaction (HOI) aims at inferring various relationships between actions and objects. Although great progress in HOI has been made, the long-tail problem and combinatorial explosion problem are still practical challenges. To this end, we formulate HOI as a few-shot task to tackle both challenges and design a novel dynamic generation method to address this task. The proposed approach is called semantic-aware dynamic generation networks (SADG-Nets). Specifically, SADG-Net first assigns semantic-aware task representations for different batches of data, which further generates dynamic parameters. It obtains the features that highlight intercategory discriminability and intracategory commonality adaptively. In addition, we also design a dual semantic-aware encoder module (DSAE-Module), that is, verb-aware and noun-aware branches, to yield both action and object prototypes of HOI for each task space, which generalizes to novel combinations by transferring similarities among interactions. Extensive experimental results on two benchmark datasets, that is, humans interacting with common objects (HICO)-FS and trento universal HOI (TUHOI)-FS, illustrate that our SADG-Net achieves superior performance over state-of-the-art approaches, which proves its impressive effectiveness on few-shot HOI recognition.

Perovskite-based color camera inspired by human visual cells

There are two primary types of photoreceptor cells in the human eye: cone cells and rod cells that enable color vision and night vision, respectively. Herein, inspired by the function of human visual cells, we develop a high-resolution perovskite-based color camera using a set of narrowband red, green, blue, and broadband white perovskite photodetectors as imaging sensors. The narrowband red, green, and blue perovskite photodetectors with color perceptions mimic long-, medium-, and short-wavelength cones cells to achieve color imaging ability. Also, the broadband white perovskite photodetector with better detectivity mimics rod cells to improve weak-light imaging ability. Our perovskite-based camera, combined with predesigned pattern illumination and image reconstruction technology, is demonstrated with high-resolution color images (up to 256 × 256 pixels) in diffuse mode. This is far beyond previously reported advanced perovskite array image sensors that only work in monochrome transmission mode. This work shows a new approach to bio-inspired cameras and their great potential to strongly mimic the ability of the natural eye.

[Validation of calculation method for dose distribution around radioactive iodine-125 particles based on AAPM TG43 report]

Objective: According to the formula provided by the TG43 report [AAPM TG43 (2004)] proposed by the American Association of Physicists in Medicine (AAPM) in 2004, we calculated the dose distribution around the radioactive iodine-125 particles, and verified the calculation accuracy of the radioactive iodine-125 particles treatment planning system. Methods: AAPM TG43 (2004) report provides two calculation methods when calculating the dose around a single radioactive source. The calculation method that does not consider the geometric structure of the radioactive source is called point source calculation method, and the calculation method that considers the geometric structure of the radioactive source is called line source calculation method. Assuming a single Amersham 6711 radioactive iodine-125 particle with an activity of 100 U, the following point doses were calculated according to the two calculation methods provided by AAPM TG43 (2004) report, at 0°, 90° directions, distances 0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 5.5 and 6 cm; In the direction of 45°, the doses at 0.71, 1.41, 2.12, 2.83, 3.54, 4.24, 4.95, 5.66, 6.36, 7.07, 7.78 and 8.49 cm. On the clinically used brachytherapy planning system variseeds 8.0, the above two calculation methods are used to calculate the corresponding activity and the dose around the corresponding type of radioactive iodine-125 particles, and the function of capturing points to templates built in the planning system is used to accurately find the above corresponding point position, using a single measurement of the above corresponding point dose; and comparation of the results were performed to see if there is a statistical difference. Results: The AAPM TG43 report uses point source calculation method to calculate the dose of single Amersham 6711 radioactive iodine-125 particles with activity of 100 U at 0° and 90° directions. The points with the same distance and the same dose are 8 082.18, 1 870.08, 756.58, 381.47, 217.11, 131.91, 86.55, 58.32, 39.97, 27.42, 19.74, 14.13 Gy, respectively, at 0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 5.5 and 6 cm away from them. In the 45° direction, the doses at the distances of 0.71, 1.41, 2.12, 2.83, 3.54, 4.24, 4.95, 5.66, 6.36, 7.07, 7.78 and 8.49 cm are 3 957.37, 865.83, 329.99, 155.69, 84.10, 48.50, 28.49, 17.80, 11.37, 7.38, 4.98 and 3.39 Gy, respectively; For line source calculation method, radioactive particles are at the same distance as above. The doses at each point in the direction of 0° are 3 128.71, 755.44, 330.30, 180.53, 107.74, 68.56, 46.40, 32.22, 22.70, 16.00, 11.51, 8.24 Gy, respectively. The doses at each point in the direction of 90° are 8 306.46, 1 981.01, 802.74, 405.38, 230.60, 140.03, 91.83, 61.84, 42.36, 29.05, 20.91, 14.97 Gy; In the 45° direction, the dose at the corresponding distance as above is 4 020.78, 877.43, 333.49, 156.93, 84.69, 48.81, 28.65, 17.89, 11.42, 7.41, 4.99 and 3.40 Gy, respectively. The maximum dose difference (0.3%) between the two methods is 7.78 cm in the 45° direction, the maximum difference (-0.3%) between the two methods is 8.49 cm in the 45° direction, and the value of other sampling points is less than 0.3%. The closer the Amersham 6711 iodine-125 particles are to the source in the directions of 0°, 45°, and 90°, the faster the dose will drop, and the dose will drop gradually as the distance increases. Conclusion: The brachytherapy planning system variseeds 8.0 and the AAPM TG43 report calculate a maximum dose difference of 0.3%, which can accurately calculate the dose distribution around radioactive iodine-125 seeds, and provide a reliable tool for the clinical implementation of radioactive iodine-125 particles implantation for tumor treatment.

Memorizing Complementation Network for Few-Shot Class-Incremental Learning

Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old classes and the scarcity of the novel samples make it formidable to realize the trade-off between retaining old knowledge and learning novel concepts. Inspired by that different models memorize different knowledge when learning novel concepts, we propose a Memorizing Complementation Network (MCNet) to ensemble multiple models that complements the different memorized knowledge with each other in novel tasks. Additionally, to update the model with few novel samples, we develop a Prototype Smoothing Hard-mining Triplet (PSHT) loss to push the novel samples away from not only each other in current task but also the old distribution. Extensive experiments on three benchmark datasets, e.g., CIFAR100, miniImageNet and CUB200, have demonstrated the superiority of our proposed method.

Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision

General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We reveal that the relation and feature deviations are crucial problems for catastrophic forgetting, in which relation deviation refers to the deficiency of the relationship among all classes in knowledge distillation, and feature deviation refers to indiscriminative feature representations. To this end, we propose a Complementary Calibration (CoCa) framework by mining the complementary model's outputs and features to alleviate the two deviations in the process of GCL. Specifically, we propose a new collaborative distillation approach for addressing the relation deviation. It distills model's outputs by utilizing ensemble dark knowledge of new model's outputs and reserved outputs, which maintains the performance of old tasks as well as balancing the relationship among all classes. Furthermore, we explore a collaborative self-supervision idea to leverage pretext tasks and supervised contrastive learning for addressing the feature deviation problem by learning complete and discriminative features for all classes. Extensive experiments on six popular datasets show that our CoCa framework achieves superior performance against state-of-the-art methods. Code is available at https://github.com/lijincm/CoCa.

Mosaic-free compound eye camera based on multidirectional photodetectors and single-pixel imaging

Compound-eye wide field-of-view (FOV) imaging generally faces the disadvantages of a complex system, low resolution, and complicated image mosaic. Single-pixel imaging has proven to very beneficial in building a high-resolution and simple wide-FOV camera, but its ability to overcome the problem of image mosaics still needs to be demonstrated. In this Letter, we propose a novel, to the best of our knowledge, kind of artificial compound eye based on multidirectional photodetectors (PDs) and demonstrate theoretically and experimentally that mosaics are unnecessary in multidirectional PD-based single-pixel imaging. In addition, we show experimentally that only nine multidirectional PDs are needed to obtain wide-angle images in a hemisphere to realize wide-FOV mosaic-free imaging. This work greatly simplifies the concept of compound-eye cameras and is very enlightening for detector design in wide-FOV single-pixel imaging, plausibly leading to the development of single-pixel endoscopic imaging.

Endovascular treatment of acute ischemic stroke with a fully radiopaque retriever: A randomized controlled trial

Objective

The Neurohawk retriever is a new fully radiopaque retriever. A randomized controlled non-inferiority trial was conducted to compare the Neurohawk and the Solitaire FR in terms of safety and efficacy. In order to evaluate the efficacy and safety of endovascular treatment in acute ischemic stroke (AIS) caused by intracranial atherosclerotic disease (ICAD) larger vessel occlusion (LVO), a sub-analysis was performed.

Methods

Acute ischemic stroke patients aged 18-80 years with LVO in the anterior circulation were randomly assigned to undergo thrombectomy with either the Neurohawk or the Solitaire FR. The primary efficacy endpoint was successful reperfusion (mTICI 2b-3) rate by the allocated retriever. A relevant non-inferiority margin was 12.5%. Safety outcomes were symptomatic intracranial hemorrhage (sICH) and all-cause mortality within 90 days. Secondary endpoints included first-pass effect (FPE), modified FPE, and favorable outcomes at 90 days. In subgroup analysis, the patients were divided into the ICAD group and non-ICAD group according to etiology, and baseline characteristics, angiographic, and clinical outcomes were compared.

Results

A total of 232 patients were involved in this analysis (115 patients in the Neurohawk group and 117 in the Solitaire group). The rates of successful reperfusion with the allocated retriever were 88.70% in the Neurohawk group and 90.60% in the Solitaire group (95%CI of the difference, -9.74% to 5.94%; p = 0.867). There were similar results in FPE and mFPE in both groups. The rate of sICH seemed higher in the Solitaire group (13.16% vs. 7.02%, p = 0.124). All-cause mortality and favorable outcome rates were comparable as well. In subgroup analysis, 58 patients were assigned to the ICAD group and the remaining 174 to the non-ICAD group. The final successful reperfusion and favorable outcome rates showed no statistically significant differences in two groups. Mortality within 90 days was relatively lower in the ICAD group (6.90% vs. 17.24%; p = 0.054).

Conclusion

The Neurohawk retriever is non-inferior to the Solitaire FR in the mechanical thrombectomy of large vessel occlusion-acute ischemic stroke (LVO-AIS). The sub-analysis suggested that endovascular treatment including thrombectomy with the retriever and essential rescue angioplasty is effective and safe in AIS patients with intracranial atherosclerotic disease-larger vessel occlusion (ICAD-LVO).

Clinical trial registration

https://clinicaltrials.gov/ct2/show/NCT04995757, number: NCT04995757.

Mechanical thrombectomy combined with stenting for radiation-induced carotid stenosis-related stroke with high-load embolization: A case report

Radiation therapy in patients with nasopharyngeal carcinoma can cause chronic progressive carotid artery injury, but acute ischemic stroke caused by carotid artery high-load thrombosis rarely occurs in patients with tandem lesions. We performed carotid mechanical thrombectomy combined with angioplasty in a 57-year-old man who received radiotherapy for nasopharyngeal carcinoma more than 10 years before presentation. He presented with acute-onset left hemiplegia, confusion, and mixed aphasia. Head CT revealed a hyper-dense sign in the right middle cerebral artery M1 region, and angiography disclosed occlusion in the right internal carotid artery C5 region with extremely severe stenosis in the middle C1 region. Intra-arterial mechanical thrombectomy with carotid stenting was performed, and re-canalization was achieved. Re-examination angiography after 3 months revealed worsening of ulcerative plaques and pseudoaneurysms in the left common carotid artery. Consequently, we performed carotid stenting over the left common carotid artery, and the patient recovered well postoperatively. Our experience suggests that early detection of large blood vessel damage and intervention are necessary to prevent large-vessel ischemic stroke in patients who received radiotherapy for nasopharyngeal carcinoma.

Perovskite Wide-Angle Field-Of-View Camera

Researchers have attempted to create wide-angle field-of-view (FOV) cameras inspired by the structure of the eyes of animals, including fisheye and compound eye cameras. However, realizing wide-angle FOV cameras simultaneously exhibiting low distortion and high spatial resolution remains a significant challenge. In this study, a novel wide-angle FOV camera is developed by combining a single large-area flexible perovskite photodetector (FP-PD) using computational technology. With this camera, the proposed single-photodetector imaging technique can obtain high-spatial-resolution images using only a single detector, and the large-area FP-PD can be bent further to collect light from a wide-angle FOV. The proposed camera demonstrates remarkable features of an extraordinarily tunable wide FOV (greater than 150°), high spatial resolution of 256 × 256 pixels, and low distortion. It is believed that the proposed compatible and extensible camera prototype will promote the development of high-performance versatile FOV cameras.

Glibenclamide Directly Prevents Neuroinflammation by Targeting SUR1-TRPM4-Mediated NLRP3 Inflammasome Activation In Microglia

Glibenclamide (GLB) reduces brain edema and improves neurological outcome in animal experiments and preliminary clinical studies. Recent studies also suggested a strong anti-inflammatory effect of GLB, via inhibiting nucleotide-binding oligomerization domain-like receptor containing pyrin domain 3 (NLRP3) inflammasome activation. However, it remains unknown whether the anti-inflammatory effect of GLB is independent of its role in preventing brain edema, and how GLB inhibits the NLRP3 inflammasome is not fully understood. Sprague-Dawley male rats underwent 10-min asphyxial cardiac arrest and cardiopulmonary resuscitation or sham-operation. The Trpm4 siRNA and GLB were injected to block sulfonylurea receptor 1-transient receptor potential M4 (SUR1-TRPM4) channel in rats. Western blotting, quantitative real-time polymerase chain reaction, behavioral analysis, and histological examination were used to evaluate the role of GLB in preventing NLRP3-mediated neuroinflammation through inhibiting SUR1-TRPM4, and corresponding neuroprotective effect. To further explore the underlying mechanism, BV2 cells were subjected to lipopolysaccharides, or oxygen-glucose deprivation/reperfusion. Here, in rat model of cardiac arrest with brain edema combined with neuroinflammation, GLB significantly alleviated neurocognitive deficit and neuropathological damage, via the inhibition of microglial NLRP3 inflammasome activation by blocking SUR1-TRPM4. Of note, the above effects of GLB could be achieved by knockdown of Trpm4. In vitro under circumstance of eliminating distractions from brain edema, SUR1-TRPM4 and NLRP3 inflammasome were also activated in BV2 cells subjected to lipopolysaccharides, or oxygen-glucose deprivation/reperfusion, which could be blocked by GLB or 9-phenanthrol, a TRPM4 inhibitor. Importantly, activation of SUR1-TRPM4 in BV2 cells required the P2X7 receptor-mediated Ca2+ influx, which in turn magnified the K+ efflux via the Na+ influx-driven opening of K+ channels, leading to the NLRP3 inflammasome activation. These findings suggest that GLB has a direct anti-inflammatory neuroprotective effect independent of its role in preventing brain edema, through inhibition of SUR1-TRPM4 which amplifies K+ efflux and promotes NLRP3 inflammasome activation.