Scholarlink

<p>The presence of veterinary drug residues, particularly enrofloxacin, in food products constitutes a serious public health concern. To address this issue, it is imperative to develop highly sensitive detection methods for accurate identification of enrofloxacin residues. This study introduces a deep learning-assisted immunosensor based on dual-sized microspheres (DLIDM) for the sensitive quantification of enrofloxacin. The sensor employs two types of polystyrene microspheres: 500&#xa0;μm microspheres (PS<sub>500</sub>) functionalized with enrofloxacin antibodies as separation carriers, and 3&#xa0;μm particles (PS<sub>3</sub>) conjugated with enrofloxacin antigens as the signaling probes. After the immunoreaction, the system quickly separates immunocomplexes from uncaptured signal probes based on their different settling times. The uncaptured probes are then counted using optical microscopy and a YOLOv11-based algorithm. Finally, a quantitative relationship was established between the number of free signal probes and enrofloxacin concentration. The results demonstrate that the DLIDM achieves sensitive detection with a wide linear range (0.5&#xa0;ng/mL to 1&#xa0;μg/mL) and a low limit of detection (0.11&#xa0;ng/mL). In spiked egg samples, the DLIDM enables accurate detection for enrofloxacin with recoveries from 92.1% to 111.4%, and relative standard deviations were 7.96%–12.08%. With its combination of operational simplicity, high sensitivity, and speediness, this immunosensor presents a promising new platform for food safety monitoring.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-Assisted Immunosensor Based on Dual-Sized Microspheres for Sensitive Detection of Enrofloxacin Residues in Food Samples

  • 期刊论文

  • 发表日期：

    2025年11月24日

查看全文
  • Jia Tu,
  • Dongyang Deng,
  • Zihan Hu,
  • Jia Feng,
  • Yongzhen Dong,
  • Long Wu,
  • Dubang Mao,
  • Yiping Chen

摘要

The presence of veterinary drug residues, particularly enrofloxacin, in food products constitutes a serious public health concern. To address this issue, it is imperative to develop highly sensitive detection methods for accurate identification of enrofloxacin residues. This study introduces a deep learning-assisted immunosensor based on dual-sized microspheres (DLIDM) for the sensitive quantification of enrofloxacin. The sensor employs two types of polystyrene microspheres: 500 μm microspheres (PS500) functionalized with enrofloxacin antibodies as separation carriers, and 3 μm particles (PS3) conjugated with enrofloxacin antigens as the signaling probes. After the immunoreaction, the system quickly separates immunocomplexes from uncaptured signal probes based on their different settling times. The uncaptured probes are then counted using optical microscopy and a YOLOv11-based algorithm. Finally, a quantitative relationship was established between the number of free signal probes and enrofloxacin concentration. The results demonstrate that the DLIDM achieves sensitive detection with a wide linear range (0.5 ng/mL to 1 μg/mL) and a low limit of detection (0.11 ng/mL). In spiked egg samples, the DLIDM enables accurate detection for enrofloxacin with recoveries from 92.1% to 111.4%, and relative standard deviations were 7.96%–12.08%. With its combination of operational simplicity, high sensitivity, and speediness, this immunosensor presents a promising new platform for food safety monitoring.