Department of Liver Surgery and Transplantation, Liver Cancer Institute, Zhongshan Hospital, and Key Laboratory of Carcinogenesis and Cancer Invasion of Ministry of Education, Fudan University, No.180, Feng Lin Road, Shanghai, 200032, China.
School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, No.2005, Song Hu Road, Shanghai, 200433, China.
BMC Med. 2024 Jul 8;22(1):282. doi: 10.1186/s12916-024-03482-0.
The advances in deep learning-based pathological image analysis have invoked tremendous insights into cancer prognostication. Still, lack of interpretability remains a significant barrier to clinical application.
We established an integrative prognostic neural network for intrahepatic cholangiocarcinoma (iCCA), towards a comprehensive evaluation of both architectural and fine-grained information from whole-slide images. Then, leveraging on multi-modal data, we conducted extensive interrogative approaches to the models, to extract and visualize the morphological features that most correlated with clinical outcome and underlying molecular alterations.
The models were developed and optimized on 373 iCCA patients from our center and demonstrated consistent accuracy and robustness on both internal (n = 213) and external (n = 168) cohorts. The occlusion sensitivity map revealed that the distribution of tertiary lymphoid structures, the geometric traits of the invasive margin, the relative composition of tumor parenchyma and stroma, the extent of necrosis, the presence of the disseminated foci, and the tumor-adjacent micro-vessels were the determining architectural features that impacted on prognosis. Quantifiable morphological vector extracted by CellProfiler demonstrated that tumor nuclei from high-risk patients exhibited significant larger size, more distorted shape, with less prominent nuclear envelope and textural contrast. The multi-omics data (n = 187) further revealed key molecular alterations left morphological imprints that could be attended by the network, including glycolysis, hypoxia, apical junction, mTORC1 signaling, and immune infiltration.
We proposed an interpretable deep-learning framework to gain insights into the biological behavior of iCCA. Most of the significant morphological prognosticators perceived by the network are comprehensible to human minds.
基于深度学习的病理图像分析技术的进步为癌症预后预测提供了新的见解。然而，缺乏可解释性仍然是其临床应用的一个重大障碍。
我们建立了一个用于肝内胆管癌（iCCA）的综合预后神经网络，以全面评估全切片图像的结构和细粒度信息。然后，利用多模态数据，我们对模型进行了广泛的询问式分析，以提取和可视化与临床结果和潜在分子改变最相关的形态特征。
该模型是在我们中心的 373 名 iCCA 患者中开发和优化的，在内部（n=213）和外部（n=168）队列中均表现出一致的准确性和稳健性。遮挡敏感图显示，三级淋巴结构的分布、浸润边缘的几何特征、肿瘤实质和基质的相对组成、坏死程度、弥散灶的存在以及肿瘤相邻的微血管是影响预后的决定性结构特征。CellProfiler 提取的可量化形态向量表明，高危患者的肿瘤细胞核体积显著增大，形状更不规则，核膜和纹理对比度减小。来自 187 名患者的多组学数据进一步揭示了关键的分子改变在形态学上留下的印记，这些印记可以被网络所关注，包括糖酵解、缺氧、顶端连接、mTORC1 信号和免疫浸润。
我们提出了一种可解释的深度学习框架，以深入了解 iCCA 的生物学行为。网络感知到的大多数重要形态预后因素都是可以被人类理解的。
