Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology
Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology
复制标题
数字病理学中的人工智能——用于诊断和精准肿瘤学的新工具
DOI：
10.1038/s41571-019-0252-y
复制
发表时间：
2019-11-01
影响因子：
78.8
通讯作者：
Madabhushi, Anant
中科院分区：
文献类型：
--
作者：
Bera, Kaustav;Schalper, Kurt A.;Madabhushi, Anant
在过去的十年中，精确肿瘤学的进步导致对预测分析的需求增加，这些分析能够选择和分层患者进行治疗。介导癌症、基质细胞和免疫细胞之间串扰的信号传导和转录网络的巨大差异使基于单个基因或蛋白质的功能相关生物标志物的开发复杂化。然而，这些复杂过程的结果可以在染色组织标本的形态特征中被唯一地捕获。数字化组织的全切片图像的可能性导致了数字病理学中人工智能（AI）和机器学习工具的出现，这使得能够挖掘亚视觉形态学表型，并最终改善患者管理。在这个视角中，我们批判性地评估了各种基于人工智能的数字病理学计算方法，重点关注深度神经网络和“手工制作”的基于特征的方法。我们的目标是提供一个广泛的框架，将人工智能和机器学习工具纳入临床肿瘤学，重点是生物标志物的开发。我们讨论了与使用人工智能相关的一些挑战，包括需要精心策划的验证数据集、监管批准和公平的报销策略。最后，我们提出了精确肿瘤学的潜在未来机会。
In the past decade, advances in precision oncology have resulted in an increased demand for predictive assays that enable the selection and stratification of patients for treatment. The enormous divergence of signalling and transcriptional networks mediating the crosstalk between cancer, stromal and immune cells complicates the development of functionally relevant biomarkers based on a single gene or protein. However, the result of these complex processes can be uniquely captured in the morphometric features of stained tissue specimens. The possibility of digitizing whole-slide images of tissue has led to the advent of artificial intelligence (Al) and machine learning tools in digital pathology, which enable mining of subvisual morphometric phenotypes and might, ultimately, improve patient management. In this Perspective, we critically evaluate various AI-based computational approaches for digital pathology, focusing on deep neural networks and 'hand-crafted' feature-based methodologies. We aim to provide a broad framework for incorporating Al and machine learning tools into clinical oncology, with an emphasis on biomarker development. We discuss some of the challenges relating to the use of Al, including the need for well-curated validation datasets, regulatory approval and fair reimbursement strategies. Finally, we present potential future opportunities for precision oncology.