Scholarlink

<p>Lymph node micro-metastasis represents the initial stage of breast cancer spread or metastasis. However, the limited size of these hidden lesions restricts dataset expansion, presenting a significant challenge for manual examination and conventional deep learning techniques. By harnessing the power of meta-learning on limited datasets, we developed a novel network named MetaTrans, equipped with a 34-category dataset (MT-MCD) to effectively pinpoint micro-metastases in lymph nodes from pathological images. MetaTrans demonstrated superior performance on two different multi-center datasets and excelled in the 0-shot task for intraoperative frozen section diagnosis. Beyond breast cancer, MetaTrans efficiently identifies micro-metastases in thyroid and colorectal cancers and can be directly applied to recognize images captured by digital cameras under a microscope. Across all clinical validation scenarios, our method surpasses state-of-the-art baselines, exhibiting robust cross-domain adaptation and task-specific reliability, which highlight its translational potential in diverse pathological settings.</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

Transformer optimization with meta learning on pathology images for breast cancer lymph node micrometastasis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月9日

查看全文
  • Jing Huang,
  • Jingtao Wang,
  • Junhai Shi,
  • Hengli Ni,
  • Shan Xu,
  • Ping Wu,
  • Yuexiang Ren,
  • Lijuan Bian,
  • Chenhan Su,
  • Yuxuan Xu,
  • Xinyu He,
  • Xinjian Chen,
  • Jianming Li

摘要

Lymph node micro-metastasis represents the initial stage of breast cancer spread or metastasis. However, the limited size of these hidden lesions restricts dataset expansion, presenting a significant challenge for manual examination and conventional deep learning techniques. By harnessing the power of meta-learning on limited datasets, we developed a novel network named MetaTrans, equipped with a 34-category dataset (MT-MCD) to effectively pinpoint micro-metastases in lymph nodes from pathological images. MetaTrans demonstrated superior performance on two different multi-center datasets and excelled in the 0-shot task for intraoperative frozen section diagnosis. Beyond breast cancer, MetaTrans efficiently identifies micro-metastases in thyroid and colorectal cancers and can be directly applied to recognize images captured by digital cameras under a microscope. Across all clinical validation scenarios, our method surpasses state-of-the-art baselines, exhibiting robust cross-domain adaptation and task-specific reliability, which highlight its translational potential in diverse pathological settings.