Department of Pathology, The Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei, China.
AI Lab, Tencent, Shenzhen, Guangdong, China.
Histopathology. 2021 Oct;79(4):544-555. doi: 10.1111/his.14383. Epub 2021 Jun 24.
The nuclear proliferation biomarker Ki67 plays potential prognostic and predictive roles in breast cancer treatment. However, the lack of interpathologist consistency in Ki67 assessment limits the clinical use of Ki67. The aim of this article was to report a solution utilising an artificial intelligence (AI)-empowered microscope to improve Ki67 scoring concordance.
We developed an AI-empowered microscope in which the conventional microscope was equipped with AI algorithms, and AI results were provided to pathologists in real time through augmented reality. We recruited 30 pathologists with various experience levels from five institutes to assess the Ki67 labelling index on 100 Ki67-stained slides from invasive breast cancer patients. In the first round, pathologists conducted visual assessment on a conventional microscope; in the second round, they were assisted with reference cards; and in the third round, they were assisted with an AI-empowered microscope. Experienced pathologists had better reproducibility and accuracy [intraclass correlation coefficient (ICC) = 0.864, mean error = 8.25%] than inexperienced pathologists (ICC = 0.807, mean error = 11.0%) in visual assessment. Moreover, with reference cards, inexperienced pathologists (ICC = 0.836, mean error = 10.7%) and experienced pathologists (ICC = 0.875, mean error = 7.56%) improved their reproducibility and accuracy. Finally, both experienced pathologists (ICC = 0.937, mean error = 4.36%) and inexperienced pathologists (ICC = 0.923, mean error = 4.71%) improved the reproducibility and accuracy significantly with the AI-empowered microscope.
The AI-empowered microscope allows seamless integration of the AI solution into the clinical workflow, and helps pathologists to obtain higher consistency and accuracy for Ki67 assessment.
核增殖标志物 Ki67 在乳腺癌治疗中具有潜在的预后和预测作用。然而，Ki67 评估中缺乏病理学家间的一致性限制了 Ki67 的临床应用。本文旨在报告一种利用人工智能（AI）赋能显微镜提高 Ki67 评分一致性的解决方案。
我们开发了一种 AI 赋能显微镜，在传统显微镜上配备了 AI 算法，并通过增强现实实时向病理学家提供 AI 结果。我们从五家机构招募了 30 名具有不同经验水平的病理学家，对 100 例浸润性乳腺癌患者的 Ki67 染色切片进行 Ki67 标记指数评估。在第一轮中，病理学家在传统显微镜下进行视觉评估；在第二轮中，他们使用参考卡进行辅助；在第三轮中，他们使用 AI 赋能显微镜进行辅助。有经验的病理学家比无经验的病理学家（ICC=0.807，平均误差=11.0%）具有更好的可重复性和准确性（ICC=0.864，平均误差=8.25%）在视觉评估中。此外，使用参考卡后，无经验的病理学家（ICC=0.836，平均误差=10.7%）和有经验的病理学家（ICC=0.875，平均误差=7.56%）提高了他们的可重复性和准确性。最后，有经验的病理学家（ICC=0.937，平均误差=4.36%）和无经验的病理学家（ICC=0.923，平均误差=4.71%）都通过 AI 赋能显微镜显著提高了可重复性和准确性。
AI 赋能显微镜允许将 AI 解决方案无缝集成到临床工作流程中，帮助病理学家获得更高的 Ki67 评估一致性和准确性。
