Center for Computational Molecular Biology, Brown University, Providence, RI, USA.
The Warren Alpert Medical School, Brown University, Providence, RI, USA.
Histopathology. 2024 Jul;85(1):116-132. doi: 10.1111/his.15180. Epub 2024 Mar 31.
Deep learning holds immense potential for histopathology, automating tasks that are simple for expert pathologists and revealing novel biology for tasks that were previously considered difficult or impossible to solve by eye alone. However, the extent to which the visual strategies learned by deep learning models in histopathological analysis are trustworthy or not has yet to be systematically analysed. Here, we systematically evaluate deep neural networks (DNNs) trained for histopathological analysis in order to understand if their learned strategies are trustworthy or deceptive.
We trained a variety of DNNs on a novel data set of 221 whole-slide images (WSIs) from lung adenocarcinoma patients, and evaluated their effectiveness at (1) molecular profiling of KRAS versus EGFR mutations, (2) determining the primary tissue of a tumour and (3) tumour detection. While DNNs achieved above-chance performance on molecular profiling, they did so by exploiting correlations between histological subtypes and mutations, and failed to generalise to a challenging test set obtained through laser capture microdissection (LCM). In contrast, DNNs learned robust and trustworthy strategies for determining the primary tissue of a tumour as well as detecting and localising tumours in tissue.
Our work demonstrates that DNNs hold immense promise for aiding pathologists in analysing tissue. However, they are also capable of achieving seemingly strong performance by learning deceptive strategies that leverage spurious correlations, and are ultimately unsuitable for research or clinical work. The framework we propose for model evaluation and interpretation is an important step towards developing reliable automated systems for histopathological analysis.
深度学习在病理组织学中具有巨大的潜力，可以自动化专家病理学家认为简单的任务，并揭示以前仅凭肉眼认为困难或不可能解决的任务的新生物学。然而，深度学习模型在病理组织学分析中学习的视觉策略的可信度程度尚未得到系统分析。在这里，我们系统地评估了用于病理组织学分析的深度神经网络（DNN），以了解它们的学习策略是否可信或具有欺骗性。
我们在一个新的肺腺癌患者的全幻灯片图像（WSI）数据集上训练了各种 DNN，并评估了它们在以下方面的有效性：（1）KRAS 与 EGFR 突变的分子分析，（2）确定肿瘤的原发组织，以及（3）肿瘤检测。虽然 DNN 在分子分析方面取得了高于平均水平的表现，但它们是通过利用组织学亚型和突变之间的相关性来实现的，并且无法推广到通过激光捕获微切割（LCM）获得的具有挑战性的测试集。相比之下，DNN 学习了用于确定肿瘤原发组织以及在组织中检测和定位肿瘤的强大而可信的策略。
我们的工作表明，DNN 在辅助病理学家分析组织方面具有巨大的潜力。然而，它们也能够通过学习利用虚假相关性的欺骗性策略来实现看似强大的性能，最终不适合研究或临床工作。我们提出的模型评估和解释框架是开发用于病理组织学分析的可靠自动化系统的重要一步。
