Browsing by Author "Chen, Wei"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Deep learning methods for solving linear inverse problems: Research directions and paradigms
    (Elsevier, 2020-08-07) Bai, Yanna; Chen, Wei; Chen, Jie; Guo, Weisi
    The linear inverse problem is fundamental to the development of various scientific areas. Innumerable attempts have been carried out to solve different variants of the linear inverse problem in different applications. Nowadays, the rapid development of deep learning provides a fresh perspective for solving the linear inverse problem, which has various well-designed network architectures results in state-of-the-art performance in many applications. In this paper, we present a comprehensive survey of the recent progress in the development of deep learning for solving various linear inverse problems. We review how deep learning methods are used in solving different linear inverse problems, and explore the structured neural network architectures that incorporate knowledge used in traditional methods. Furthermore, we identify open challenges and potential future directions along this research line.
  • Thumbnail Image
    ItemOpen Access
    Molecular epidemiology and antimicrobial resistance of outbreaks of Klebsiella pneumoniae clinical mastitis in Chinese dairy farms
    (American Society for Microbiology, 2022-11-14) Fu, Shaodong; Wen, Chen; Wang, Zhenglei; Qiu, Yawei; Zhang, Yihao; Zuo, Jiakun; Xu, Yuanyuan; Han, Xiangan; Luo, Zhenhua; Chen, Wei; Miao, Jinfeng
    Klebsiella pneumoniae is an opportunistic pathogen that causes serious infections in humans and animals. However, the availability of epidemiological information on clinical mastitis due to K. pneumoniae is limited. To acquire new information regarding K. pneumoniae mastitis, data were mined about K. pneumoniae strains on dairy cattle farms (farms A to H) in 7 Chinese provinces in 2021. Hypermucoviscous strains of K. pneumoniae were obtained by the string test. MICs of antimicrobial agents were determined via the broth microdilution method. Ten antimicrobial resistance genes and virulence genes were identified by PCR. The prevalence of K. pneumoniae was 35.91% (65/181), and 100% of the bacteria were sensitive to enrofloxacin. Nine antimicrobial resistance genes and virulence genes were identified and compared among farms. The hypermucoviscous phenotype was present in 94.44% of isolates from farm B, which may be a function of the rmpA virulence gene. Based on these data, the multidrug-resistant strains SD-14 and HB-21 were chosen and sequenced. Genotypes were assayed for K. pneumoniae isolates from different countries and different hosts using multilocus sequence typing (MLST). Ninety-four sequence types (STs) were found, and 6 STs present a risk for spreading in specific regions. Interestingly, ST43 was observed in bovine isolates for the first time. Our study partially reveals the current distribution characteristics of bovine K. pneumoniae in China and may provide a theoretical basis for the prevention and treatment of bovine K. pneumoniae mastitis.
  • Thumbnail Image
    ItemOpen Access
    Randomness-restricted diffusion model for ocular surface structure segmentation
    (Institute of Electrical and Electronics Engineers (IEEE), 2024) Guo, Xinyu; Wen, Han; Hao, Huaying; Zhao, Yifan; Meng, Yanda; Liu, Jiang; Zheng, Yalin; Chen, Wei; Zhao, Yitian
    Ocular surface diseases affect a significant portion of the population worldwide. Accurate segmentation and quantification of different ocular surface structures are crucial for the understanding of these diseases and clinical decision-making. However, the automated segmentation of the ocular surface structure is relatively unexplored and faces several challenges. Ocular surface structure boundaries are often inconspicuous and obscured by glare from reflections. In addition, the segmentation of different ocular structures always requires training of multiple individual models. Thus, developing a one-model-fits-all segmentation approach is desirable. In this paper, we introduce a randomness-restricted diffusion model for multiple ocular surface structure segmentation. First, a time-controlled fusion-attention module (TFM) is proposed to dynamically adjust the information flow within the diffusion model, based on the temporal relationships between the network's input and time. TFM enables the network to effectively utilize image features to constrain the randomness of the generation process. We further propose a low-frequency consistency filter and a new loss to alleviate model uncertainty and error accumulation caused by the multi-step denoising process. Extensive experiments have shown that our approach can segment seven different ocular surface structures. Our method performs better than both dedicated ocular surface segmentation methods and general medical image segmentation methods. We further validated the proposed method over two clinical datasets, and the results demonstrated that it is beneficial to clinical applications, such as the meibomian gland dysfunction grading and aqueous deficient dry eye diagnosis.