人工智能在乳腺癌组织病理学中的应用
本文是一篇关于人工智能用于数字乳腺病理学的综述。通过系统检索PubMed共识别17324篇乳腺癌病理相关研究论文,经半人工筛选后纳入664篇。文章按病理学家执行的六项主要任务分组:分子与激素分析、分级、核分裂象计数、ki-67指数、肿瘤浸润淋巴细胞评估及淋巴结转移识别,并在每项任务下列出用于构建AI工具的开源数据集。许多AI工具展现出前景并在常规病理检查自动化中证明可行性。
要点
- 综述按六项病理任务分组汇总乳腺病理AI工具。
- 每项任务下列出可用于构建AI工具的开源数据集。
- 许多AI工具在常规病理检查自动化中展现前景与可行性。
核心结论
- 许多AI工具在乳腺病理常规检查自动化中展现出前景并证明可行性。
- 随着新算法成熟,预期AI在该领域的应用将持续增长。
研究设计与样本
- 综述:在PubMed进行系统检索,识别出17324篇乳腺癌病理相关研究论文。
- 经半人工筛选后检索并追踪664篇论文。
主要发现
- 论文按病理学家执行的六项主要任务分组:分子与激素分析、分级、核分裂象计数、ki-67指数、肿瘤浸润淋巴细胞评估、淋巴结转移识别。
- 每项任务下均列出用于构建AI工具的开源数据集。
临床怎么用
- 可按六项病理任务分类参考乳腺病理AI工具的进展与可用开源数据集。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
This is a review on the use of artificial intelligence for digital breast pathology. A systematic search on PubMed was conducted, identifying 17,324 research papers related to breast cancer pathology. Following a semimanual screening, 664 papers were retrieved and pursued. The papers are grouped into six major tasks performed by pathologists-namely, molecular and hormonal analysis, grading, mitotic figure counting, ki-67 indexing, tumour-infiltrating lymphocyte assessment, and lymph node metastases identification. Under each task, open-source datasets for research to build artificial intelligence (AI) tools are also listed. Many AI tools showed promise and demonstrated feasibility in the automation of routine pathology investigations. We expect continued growth of AI in this field as new algorithms mature.
引用
- Chan RC, To CKC, Cheng KCT, et al. Artificial intelligence in breast cancer histopathology. Histopathology. 2023. PMID: 36482271. doi:10.1111/his.14820
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。