Zhu Jin, Wu Wangwei, Zhang Yuting, Lin Shiyun, Jiang Yukang, Liu Ruixian, Zhang Heping, Wang Xueqin
Southern China Center for Statistical Science, School of Mathematics, Sun Yat-Sen University, Guangzhou, China.
Center for Statistical Science, School of Mathematical Sciences, Peking University, Beijing, China.
Front Oncol. 2022 Jul 22;12:825353. doi: 10.3389/fonc.2022.825353. eCollection 2022.
Microsatellite instability (MSI) is associated with several tumor types and has become increasingly vital in guiding patient treatment decisions; however, reasonably distinguishing MSI from its counterpart is challenging in clinical practice.
In this study, interpretable pathological image analysis strategies are established to help medical experts to identify MSI. The strategies only require ubiquitous hematoxylin and eosin-stained whole-slide images and perform well in the three cohorts collected from The Cancer Genome Atlas. Equipped with machine learning and image processing technique, intelligent models are established to diagnose MSI based on pathological images, providing the rationale of the decision in both image level and pathological feature level.
The strategies achieve two levels of interpretability. First, the image-level interpretability is achieved by generating localization heat maps of important regions based on deep learning. Second, the feature-level interpretability is attained through feature importance and pathological feature interaction analysis. Interestingly, from both the image-level and feature-level interpretability, color and texture characteristics, as well as their interaction, are shown to be mostly contributed to the MSI prediction.
The developed transparent machine learning pipeline is able to detect MSI efficiently and provide comprehensive clinical insights to pathologists. The comprehensible heat maps and features in the intelligent pipeline reflect extra- and intra-cellular acid-base balance shift in MSI tumor.
微卫星不稳定性（MSI）与多种肿瘤类型相关，在指导患者治疗决策中变得越来越重要；然而，在临床实践中合理区分MSI与其对应物具有挑战性。
在本研究中，建立了可解释的病理图像分析策略，以帮助医学专家识别MSI。这些策略仅需要普遍存在的苏木精和伊红染色的全切片图像，并且在从癌症基因组图谱收集的三个队列中表现良好。配备机器学习和图像处理技术，基于病理图像建立智能模型来诊断MSI，在图像层面和病理特征层面都提供决策依据。
这些策略实现了两个层面的可解释性。首先，通过基于深度学习生成重要区域的定位热图来实现图像层面的可解释性。其次，通过特征重要性和病理特征相互作用分析来实现特征层面的可解释性。有趣的是，从图像层面和特征层面的可解释性来看，颜色和纹理特征及其相互作用在MSI预测中贡献最大。
所开发的透明机器学习流程能够有效地检测MSI，并为病理学家提供全面的临床见解。智能流程中可理解的热图和特征反映了MSI肿瘤细胞内外酸碱平衡的变化。
