Scholarlink

<p>The integration of artificial intelligence with bone marrow cytology represents a significant trend in the application of AI image recognition technology within the medical sector. Despite the current high accuracy of AI in cell identification, there remains a clinical need for fully automated AI cell recognition equipment that spans from sample processing to result generation. The source of the sample’s origin as an influencing factor on the final results is a crucial consideration in equipment design. In this research, patient bone marrow fluid samples were processed into various types of anticoagulated bone marrow smears—EDTAK anticoagulated, sodium citrate anticoagulated, heparin lithium anticoagulated, and sodium citrate anticoagulated—and non-anticoagulated, and subsequently analyzed by AI devices. The findings revealed a significant lack of consistency in cell classification ratios and the total number of cells recognized between anticoagulated and non-anticoagulated bone marrow smear samples. This aspect must be taken into account when designing a fully automated AI-based bone marrow cell recognition device. </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

Consistency analysis of AI cell recognition results between non anticoagulant and anticoagulant marrow smear after Wright’s staining

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月8日

查看全文
  • Siheng Liu,
  • Cenxia Ran,
  • Jia Li,
  • Wuchen Yang,
  • Shuiqing Liu,
  • Xi Zhang,
  • Xiangui Peng,
  • Cheng Zhang

摘要

The integration of artificial intelligence with bone marrow cytology represents a significant trend in the application of AI image recognition technology within the medical sector. Despite the current high accuracy of AI in cell identification, there remains a clinical need for fully automated AI cell recognition equipment that spans from sample processing to result generation. The source of the sample’s origin as an influencing factor on the final results is a crucial consideration in equipment design. In this research, patient bone marrow fluid samples were processed into various types of anticoagulated bone marrow smears—EDTAK anticoagulated, sodium citrate anticoagulated, heparin lithium anticoagulated, and sodium citrate anticoagulated—and non-anticoagulated, and subsequently analyzed by AI devices. The findings revealed a significant lack of consistency in cell classification ratios and the total number of cells recognized between anticoagulated and non-anticoagulated bone marrow smear samples. This aspect must be taken into account when designing a fully automated AI-based bone marrow cell recognition device.