المؤلفون: Dong, Bo, Pei, Jialun, Gao, Rongrong, Xiang, Tian-Zhu, Wang, Shuo, Xiong, Huan

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation. To this end, inspired by query-based transformers, we propose a unified query-based multi-task learning framework for camouflaged instance segmentation, termed UQFormer, which builds a set of mask queries and a set of boundary queries to learn a shared composed query representation and efficiently integrates global camouflaged object region and boundary cues, for simultaneous instance segmentation and instance boundary detection in camouflaged scenarios. Specifically, we design a composed query learning paradigm that learns a shared representation to capture object region and boundary features by the cross-attention interaction of mask queries and boundary queries in the designed multi-scale unified learning transformer decoder. Then, we present a transformer-based multi-task learning framework for simultaneous camouflaged instance segmentation and camouflaged instance boundary detection based on the learned composed query representation, which also forces the model to learn a strong instance-level query representation. Notably, our model views the instance segmentation as a query-based direct set prediction problem, without other post-processing such as non-maximal suppression. Compared with 14 state-of-the-art approaches, our UQFormer significantly improves the performance of camouflaged instance segmentation. Our code will be available at https://github.com/dongbo811/UQFormerTest.
Comment: This paper has been accepted by ACM MM2023

الوصول الحر: http://arxiv.org/abs/2308.07392Test

المؤلفون: Chen, Zhennan, Gao, Rongrong, Xiang, Tian-Zhu, Lin, Fan

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: Camouflaged object detection is a challenging task that aims to identify objects that are highly similar to their background. Due to the powerful noise-to-image denoising capability of denoising diffusion models, in this paper, we propose a diffusion-based framework for camouflaged object detection, termed diffCOD, a new framework that considers the camouflaged object segmentation task as a denoising diffusion process from noisy masks to object masks. Specifically, the object mask diffuses from the ground-truth masks to a random distribution, and the designed model learns to reverse this noising process. To strengthen the denoising learning, the input image prior is encoded and integrated into the denoising diffusion model to guide the diffusion process. Furthermore, we design an injection attention module (IAM) to interact conditional semantic features extracted from the image with the diffusion noise embedding via the cross-attention mechanism to enhance denoising learning. Extensive experiments on four widely used COD benchmark datasets demonstrate that the proposed method achieves favorable performance compared to the existing 11 state-of-the-art methods, especially in the detailed texture segmentation of camouflaged objects. Our code will be made publicly available at: https://github.com/ZNan-Chen/diffCODTest.
Comment: Accepted by ECAI2023

الوصول الحر: http://arxiv.org/abs/2308.00303Test

المؤلفون: WANG Jie, SUN Guozhen, BAO Zhipeng, WANG Lin, GAO Min, LIU Shenxinyu, YU Tianxi, WANG Qin, GAO Rongrong

المصدر: Zhongguo quanke yixue, Vol 27, Iss 02, Pp 168-176 (2024)

مصطلحات موضوعية: atrial fibrillation, radiofrequency ablation, home-based exercise rehabilitation, adherence, root cause analysis, longitudinal study, Medicine

الوصف: Background The prevalence of atrial fibrillation (AF) in China is increasing year by year, and the prognosis and quality of life of patients urgently need attention. Current studies have confirmed that exercise rehabilitation is a beneficial way to improve the prognosis and poor quality of life in patients with AF after radiofrequency catheter ablation (RFCA). Adherence is a key measure of whether the benefits of exercise rehabilitation persist, but its trajectory remains unknown. Objective To examine the development trajectory and predictors of strength-duration adherence to home-based exercise rehabilitation among patients with AF after RFCA using five-period follow-up data based on prospective longitudinal observation. Methods Convenience sampling method was used to select 246 patients with AF who attended the Department of Cardiology, the First Affiliated Hospital of Nanjing Medical University for RFCA from May to November 2020 for follow-up. The baseline survey was conducted 1 week after enrollment, and the follow-up survey was conducted at 3, 6, 9 and 12 months after enrollment. The general and clinical data of patients were collected. The strength-duration adherence was monitored and recorded using smart devices or fitness log to assess exercise adherence in terms of strength-duration adherence; Self-efficacy for Exercise Scale (SEE), Fear of Activity in Patients with Chronic Heart Failure (Fact-CHF), Perceived Social Support Scale (PSSS), Patient Activation Measure 13 (PAM13) were used for assessing self-efficacy of exercise, fear of activity, social support and motivation level. Mplus tool was used to construct latent class growth model (LCGM), and the optimal fitting model was selected to determine the development trajectory of strength-duration adherence to home-based exercise rehabilitation among patients with AF after RFCA. Logistic regression analysis was used to identify the predictors of trajectory categories. Results A total of 202 patients were included in the final analysis with 44 patients lost to follow-up. The number of patients at baseline, 3 months, 6 months, 9 months, and 12 months after exercise were 202, 201, 185, 174 and 159, respectively, and the strength-duration adherence were (0.83±0.55), (1.07±0.54), (0.99±0.57), (0.91±0.55) and (0.89±0.60). The LCGM results showed group heterogeneity in the process of change in strength-duration adherence to exercise rehabilitation in patients, which was divided into 3 latent classes based on their development trajectories, including 69 in slow decline-low level group (34.2%), 14 in rapid increase-high level group (6.9%), and 119 in sustained adherence group (58.9%). Multinomial unordered Logistic regression showed higher levels of intensity-time adherence in the rapid increase-high level group and sustained adherence group using the slow decline-low level group as the reference group (P

وصف الملف: electronic resource

العلاقة: https://www.chinagp.net/fileup/1007-9572/PDF/1698029664933-1863239645.pdfTest; https://doaj.org/toc/1007-9572Test

الوصول الحر: https://doaj.org/article/25e95d1e62084a7eb88aadafb9c1ae77Test

المؤلفون: Gao, Rongrong, Fan, Na, Li, Changlin, Liu, Wentao, Chen, Qifeng

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Computer Science - Robotics

الوصف: We present a novel approach to joint depth and normal estimation for time-of-flight (ToF) sensors. Our model learns to predict the high-quality depth and normal maps jointly from ToF raw sensor data. To achieve this, we meticulously constructed the first large-scale dataset (named ToF-100) with paired raw ToF data and ground-truth high-resolution depth maps provided by an industrial depth camera. In addition, we also design a simple but effective framework for joint depth and normal estimation, applying a robust Chamfer loss via jittering to improve the performance of our model. Our experiments demonstrate that our proposed method can efficiently reconstruct high-resolution depth and normal maps and significantly outperforms state-of-the-art approaches. Our code and data will be available at \url{https://github.com/hkustVisionRr/JointlyDepthNormalEstimationTest}
Comment: IROS 2021

الوصول الحر: http://arxiv.org/abs/2108.03649Test

المؤلفون: Yang, Mei, Chen, Tingting, Chen, Xin, Pan, Hongxian, Zhao, Guoli, Chen, Zhongxing, Zhao, Nan, Ye, Qianfang, Chen, Ming, Zhang, Shenrong, Gao, Rongrong, Meek, Keith M., Hayes, Sally, Ma, Xiaowei, Li, Xin, Wu, Yue, Zhang, Yiming, Kong, Na, Tao, Wei, Zhou, Xingtao, Huang, Jinhai

الوصف: Keratoconus, a disorder characterized by corneal thinning and weakening, results in vision loss. Corneal crosslinking (CXL) can halt the progression of keratoconus. The development of accelerated corneal crosslinking (A-CXL) protocols to shorten the treatment time has been hampered by the rapid depletion of stromal oxygen when higher UVA intensities are used, resulting in a reduced cross-linking effect. It is therefore imperative to develop better methods to increase the oxygen concentration within the corneal stroma during the A-CXL process. Photocatalytic oxygen-generating nanomaterials are promising candidates to solve the hypoxia problem during A-CXL. Biocompatible graphitic carbon nitride (g-C3N4) quantum dots (QDs)-based oxygen self-sufficient platforms including g-C3N4 QDs and riboflavin/g-C3N4 QDs composites (RF@g-C3N4 QDs) have been developed in this study. Both display excellent photocatalytic oxygen generation ability, high reactive oxygen species (ROS) yield, and excellent biosafety. More importantly, the A-CXL effect of the g-C3N4 QDs or RF@g-C3N4 QDs composite on male New Zealand white rabbits is better than that of the riboflavin 5’-phosphate sodium (RF) A-CXL protocol under the same conditions, indicating excellent strengthening of the cornea after A-CXL treatments. These lead us to suggest the potential application of g-C3N4 QDs in A-CXL for corneal ectasias and other corneal diseases.

وصف الملف: application/pdf

العلاقة: https://orca.cardiff.ac.uk/id/eprint/170224/1/41467_2024_Article_49645.pdfTest; Yang, Mei, Chen, Tingting, Chen, Xin, Pan, Hongxian, Zhao, Guoli, Chen, Zhongxing, Zhao, Nan, Ye, Qianfang, Chen, Ming, Zhang, Shenrong, Gao, Rongrong, Meek, Keith M. https://orca.cardiff.ac.uk/view/cardiffauthors/A032669F.htmlTest orcid:0000-0002-9948-7538 orcid:0000-0002-9948-7538, Hayes, Sally https://orca.cardiff.ac.uk/view/cardiffauthors/A017127Q.htmlTest orcid:0000-0001-8550-0108 orcid:0000-0001-8550-0108, Ma, Xiaowei, Li, Xin, Wu, Yue, Zhang, Yiming, Kong, Na, Tao, Wei, Zhou, Xingtao and Huang, Jinhai 2024. Development of graphitic carbon nitride quantum dots-based oxygen self-sufficient platforms for enhanced corneal crosslinking. Nature Communications 15 , 5508. 10.1038/s41467-024-49645-8 https://doi.org/10.1038/s41467-024-49645-8Test file https://orca.cardiff.ac.uk/id/eprint/170224/1/41467_2024_Article_49645.pdfTest

الإتاحة: https://doi.org/10.1038/s41467-024-49645-8Test
https://orca.cardiff.ac.uk/id/eprint/170224Test/
https://orca.cardiff.ac.uk/id/eprint/170224/1/41467_2024_Article_49645.pdfTest

المؤلفون: Zhang, Xu, Gao, Rongrong, Yang, Liuke, Zhu, Youwei, Zhang, Tiancheng, Shen, Xiaorong, Gu, Wenwen, Yang, Long, Peng, Shenjie

المصدر: Clinical and Translational Discovery ; volume 4, issue 2 ; ISSN 2768-0622 2768-0622

الوصف: Background The brain is a central key organ of the body containing the second highest lipid content only after adipose tissue. Lipids as the main structural components of biological membranes play important roles in a vast number of biological processes within the brain such as energy homeostasis, material transport, signal transduction, neurogenesis and synaptogenesis, providing a balanced cellular environment required for proper functioning of brain cells. Lipids and their metabolism are of great physiological importance in view of the crucial roles of lipids in brain development and function. Astrocytes are the most abundant glial cells in the brain and involved in various processes including metabolic homeostasis, blood brain barrier maintenance, neuronal support and crosstalk. Results Disturbances in lipid metabolism and astrocytic functions may lead to pathological alterations associated with numerous neurological diseases like Alzheimer's disease (AD) recognised as the most frequent cause of dementia leading to major progressive memory and cognitive deficits as well as glioblastoma (GBM) known as the most aggressive malignant brain tumour with a poor prognosis. Conclusions Herein, we not only review the level and role of altered lipid metabolism in correlation with astrocytic function and astrocyte‐neuron crosstalk in AD and GBM, but also discuss important lipid‐related metabolites and proteins participating in possible mechanisms of pathologically dysregulated lipid metabolism, offering potential therapeutic targets in targeted molecular therapies for AD and GBM.

الإتاحة: https://doi.org/10.1002/ctd2.287Test

المؤلفون: Zhang, Xu, Gao, Rongrong, Yang, Liuke, Zhu, Youwei, Zhang, Tiancheng, Shen, Xiaorong, Gu, Wenwen, Yang, Long, Peng, Shenjie

المصدر: Clinical and Translational Discovery ; volume 4, issue 2 ; ISSN 2768-0622 2768-0622

الوصف: Background Single‐cell sequencing (SCS) marks the advent of a transformative period in biomedical studies, enabling unprecedented insight into the cellular intricacies of health and disease. Methods By dissecting the genetic, epigenetic and proteomic landscapes at the single‐cell level, SCS transcends traditional bulk sequencing methodologies, illuminating the heterogeneity and dynamics of individual cells. Results This analytical leap facilitates a deeper understanding of disease mechanisms, offers novel diagnostic and therapeutic targets and underpins the development of precision medicine across diverse fields such as neurology, oncology and immunology. Conclusions Despite its profound potential, SCS encounters challenges, including complex sample preparation, sophisticated data analysis and cost considerations. Nevertheless, ongoing advancements promise to overcome these barriers, integrating SCS with other omics data and leveraging machine learning to enhance biological understanding and clinical application. With the advancement of SCS technologies, personalised healthcare might be fundamentally altered, facilitating tailored and efficacious treatment strategies.

الإتاحة: https://doi.org/10.1002/ctd2.293Test

المؤلفون: Wu, Yue, Gao, Rongrong, Park, Jaesik, Chen, Qifeng

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: We present an approach to predict future video frames given a sequence of continuous video frames in the past. Instead of synthesizing images directly, our approach is designed to understand the complex scene dynamics by decoupling the background scene and moving objects. The appearance of the scene components in the future is predicted by non-rigid deformation of the background and affine transformation of moving objects. The anticipated appearances are combined to create a reasonable video in the future. With this procedure, our method exhibits much less tearing or distortion artifact compared to other approaches. Experimental results on the Cityscapes and KITTI datasets show that our model outperforms the state-of-the-art in terms of visual quality and accuracy.
Comment: CVPR 2020

الوصول الحر: http://arxiv.org/abs/2004.00542Test

المؤلفون: Gao, Fei, Gao, Rongrong, Liu, Hao, Yang, Zhou, Hua, Xiaodong, Wu, Xin, Shengzhong, Liu

مصطلحات موضوعية: Physics - Applied Physics, Condensed Matter - Materials Science

الوصف: Usually, single-crystal material has a longer carrier diffusion length due to fewer defects. Here, we report a nano/amorphous copper oxide and selenium (COS) composite film prepared by radio frequency magnetron co-sputtering of CuO and Se and post annealing. The photo-generated carriers in the COS film can diffuse very far (3.147 mm). Additionally, the COS film can strongly absorb light over the entire solar spectrum region (250-2500 nm) (average absorptance is ~80%). These results indicate that the COS composite is an excellent material and can be used in solar cells and other photo-electric devices.
Comment: 8 pages,4 figures

الوصول الحر: http://arxiv.org/abs/1905.03432Test

المؤلفون: Gao, Rongrong, Qu, Qiang, Guo, Qixin, Sun, Jinyu, Liao, Shengen, Zhu, Qingqing, Zhu, Xu, Cheang, Iokfai, Yao, Wenming, Zhang, Haifeng, Li, Xinli, Zhou, Yanli

المصدر: ESC Heart Failure ; volume 10, issue 4, page 2248-2261 ; ISSN 2055-5822 2055-5822

الوصف: Aims The early identification and appropriate management may provide clinically meaningful and substained benefits in patients with acute heart failure (AHF). This study aimed to develop an integrative nomogram with myocardial perfusion imaging (MPI) for predicting the risk of all‐cause mortality in AHF patients. Methods and results Prospective study of 147 patients with AHF who received gated MPI (59.0 [47.5, 68.0] years; 78.2% males) were enrolled and followed for the primary endpoint of all‐cause mortality. We analysed the demographic information, laboratory tests, electrocardiogram, and transthoracic echocardiogram by the least absolute shrinkage and selection operator (LASSO) regression for selection of key features. A multivariate stepwise Cox analysis was performed to identify independent risk factors and construct a nomogram. The predictive values of the constructed model were compared by Kaplan–Meier curve, area under the curves (AUCs), calibration plots, continuous net reclassification improvement, integrated discrimination improvement, and decision curve analysis. The 1, 3, and 5 year cumulative rates of death were 10%, 22%, and 29%, respectively. Diastolic blood pressure [hazard ratio (HR) 0.96, 95% confidence interval (CI) 0.93–0.99; P = 0.017], valvular heart disease (HR 3.05, 95% CI 1.36–6.83; P = 0.007), cardiac resynchronization therapy (HR 0.37, 95% CI 0.17–0.82; P = 0.014), N‐terminal pro‐B‐type natriuretic peptide (per 100 pg/mL; HR 1.02, 95% CI 1.01–1.03; P < 0.001), and rest scar burden (HR 1.03, 95% CI 1.01–1.06; P = 0.008) were independent risk factors for patients with AHF. The cross‐validated AUCs (95% CI) of nomogram constructed by diastolic blood pressure, valvular heart disease, cardiac resynchronization therapy, N‐terminal pro‐B‐type natriuretic peptide, and rest scar burden were 0.88 (0.73–1.00), 0.83 (0.70–0.97), and 0.79 (0.62–0.95) at 1, 3, and 5 years, respectively. Continuous net reclassification improvement and integrated discrimination improvement were also ...

الإتاحة: https://doi.org/10.1002/ehf2.14371Test