Scholarlink

<p>Although artificial intelligence enhances medical image classification to effectively improve lesion diagnosis accuracy and efficiency, it still faces generalization challenges in breast ultrasound and its clinical potential remains underutilized in complex real-world scenarios. Here, we develop and test an end-to-end breast intelligent recognition device (BIRD) for women across diverse institution/population datasets. The accuracy of BIRD in the internal test set is 0.837 (95% confidence interval: 0.827–0.846), which significantly improves radiologists’ accuracy in 2 reader studies (<i>P</i> &lt; 0.05). BIRD is applied in breast cancer screening for 6,817 individuals and shows high consistency (Cohen’s kappa: 0.702 (95% confidence interval: 0.628-0.777)) with clinical assessments in real-world application across 107 hospitals. Pathological and molecular subtype models developed using data from five hospitals also exhibit satisfactory classification performance. These findings confirm BIRD’s ability to improve diagnostic accuracy, assist screening, and characterize breast lesions, facilitating clinical adoption in breast health practice. The Chinese Clinical Trial Register: ChiCTR2300073777.</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

A non-invasive end-to-end intelligent assistance system for breast ultrasound

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月20日

查看全文
  • Jun Zhou,
  • Pilei Si,
  • Yan Zhang,
  • Jianqiong Song,
  • Tao He,
  • Qin Liu,
  • Shaoqi Chen,
  • Mengjie Tu,
  • Han Wang,
  • Qiang Guo,
  • Xiaofeng Qi,
  • Danli Zhang,
  • Qi Zhang,
  • Tingting Zhang,
  • Linlin Pan,
  • Shilin Li,
  • Zhengzhong Tang,
  • Julie Guo,
  • Haitao Lan,
  • Xue Li,
  • Yan Tang,
  • Min Tang,
  • Qingyang Shen,
  • Haiying Luo,
  • Zhongbing Lang,
  • Xiangqian Hu,
  • Hui Du,
  • Rongmei Tian,
  • Xiaoxue Yang,
  • Xiaoqin Gan,
  • Fang Chen,
  • Xuebin Liu,
  • Wenqin Zhang,
  • Qianrong Xie,
  • Jie Zhang,
  • Hang Yang,
  • Xue Yang,
  • Yuanli Kang,
  • Minghao Xiong,
  • Yuwei Zhang,
  • Hengyan Liu,
  • Meihua Wan,
  • Yu Xiong,
  • Tianhui Li,
  • Chian Zhao,
  • Hong Zhao,
  • Xinwu Cui,
  • Zhang Yi,
  • Fanxin Zeng

摘要

Although artificial intelligence enhances medical image classification to effectively improve lesion diagnosis accuracy and efficiency, it still faces generalization challenges in breast ultrasound and its clinical potential remains underutilized in complex real-world scenarios. Here, we develop and test an end-to-end breast intelligent recognition device (BIRD) for women across diverse institution/population datasets. The accuracy of BIRD in the internal test set is 0.837 (95% confidence interval: 0.827–0.846), which significantly improves radiologists’ accuracy in 2 reader studies (P < 0.05). BIRD is applied in breast cancer screening for 6,817 individuals and shows high consistency (Cohen’s kappa: 0.702 (95% confidence interval: 0.628-0.777)) with clinical assessments in real-world application across 107 hospitals. Pathological and molecular subtype models developed using data from five hospitals also exhibit satisfactory classification performance. These findings confirm BIRD’s ability to improve diagnostic accuracy, assist screening, and characterize breast lesions, facilitating clinical adoption in breast health practice. The Chinese Clinical Trial Register: ChiCTR2300073777.