[论文解读] Prediction of overall survival and molecular markers in gliomas via analysis of digital pathology images using deep learning

Saima Rathore, Muhammad Aksam Iftikhar+1 more|arXiv (Cornell University)|Sep 19, 2019

Radiomics and Machine Learning in Medical Imaging参考文献 27被引用 9

一句话总结

本研究开发了一种深度学习模型，通过分析胶质母细胞瘤活检的全切片数字病理图像，预测总生存期和分子标志物（IDH状态和1p/19q状态）。该模型采用双头神经网络结构，其中生存风险预测使用Cox模型，二分类任务则采用Sigmoid输出层，最终在生存预测中获得0.82的c统计量，在分子亚型分类中AUC达0.86（准确率88%）。

ABSTRACT

Cancer histology reveals disease progression and associated molecular processes, and contains rich phenotypic information that is predictive of outcome. In this paper, we developed a computational approach based on deep learning to predict the overall survival and molecular subtypes of glioma patients from microscopic images of tissue biopsies, reflecting measures of microvascular proliferation, mitotic activity, nuclear atypia, and the presence of necrosis. Whole-slide images from 663 unique patients [IDH: 333 IDH-wildtype, 330 IDH-mutants, 1p/19q: 201 1p/19q non-codeleted, 129 1p/19q codeleted] were obtained from TCGA. Sub-images that were free of artifacts and that contained viable tumor with descriptive histologic characteristics were extracted, which were further used for training and testing a deep neural network. The output layer of the network was configured in two different ways: (i) a final Cox model layer to output a prediction of patient risk, and (ii) a final layer with sigmoid activation function, and stochastic gradient decent based optimization with binary cross-entropy loss. Both survival prediction and molecular subtype classification produced promising results using our model. The c-statistic was estimated to be 0.82 (p-value=4.8x10-5) between the risk scores of the proposed deep learning model and overall survival, while accuracies of 88% (area under the curve [AUC]=0.86) were achieved in the detection of IDH mutational status and 1p/19q codeletion. These findings suggest that the deep learning techniques can be applied to microscopic images for objective, accurate, and integrated prediction of outcome for glioma patients. The proposed marker may contribute to (i) stratification of patients into clinical trials, (ii) patient selection for targeted therapy, and (iii) personalized treatment planning.

研究动机与目标

• 开发一种计算方法，利用数字病理图像预测胶质瘤患者的总生存期和分子亚型。
• 利用深度学习从全切片图像中提取与临床结局和分子标志物相关的表型特征。
• 实现从组织学切片中对患者预后和分子状态进行客观、自动化且一体化的预测。
• 通过识别适合临床试验、靶向治疗或个性化治疗方案的患者，支持临床决策制定。

提出的方法

• 使用来自The Cancer Genome Atlas（TCGA）的663例胶质瘤患者的全切片图像作为输入数据。
• 提取包含存活肿瘤组织、伪影最少且富含组织学特征（如有丝分裂活性、核异型、坏死）的子图像用于训练。
• 训练一个深度神经网络，包含两个输出头：一个使用最终的Cox模型层进行生存风险预测，另一个使用Sigmoid激活函数和二元交叉熵损失进行分子标志物分类。
• 分类头采用随机梯度下降进行优化，而生存头则使用Cox比例风险模型输出风险评分。
• 在组织学模式上端到端训练模型，以学习与生存和分子状态相关的预测特征。
• 通过c统计量评估生存预测性能，通过AUC/准确率评估分子标志物检测性能。

实验结果

研究问题

• RQ1 在胶质瘤患者中，基于数字病理图像训练的深度学习模型能否实现高精度的总生存期预测？
• RQ2 同一模型能否准确分类胶质瘤的分子亚型，特别是IDH突变状态和1p/19q共缺失状态？
• RQ3 全切片图像中可见的组织学特征是否与临床结局和分子标志物存在强相关性？
• RQ4 一个单一的深度学习模型能否仅通过一张组织学切片同时预测生存期和分子标志物？
• RQ5 该模型在不同胶质瘤亚型（IDH野生型与突变型，1p/19q共缺失与非共缺失）中的性能表现是否具有鲁棒性？

主要发现

• 该深度学习模型在预测总生存期方面获得0.82的c统计量（p值 = 4.8×10⁻⁵），表明具有强大的区分能力。
• 在IDH突变状态分类中，模型准确率达88%，受试者工作特征曲线下面积（AUC）为0.86。
• 对于1p/19q共缺失状态，模型AUC达0.86，显示出高预测准确性。
• 该模型成功识别出微血管增生、有丝分裂活性、核异型和坏死等关键组织学特征，这些特征与预后显著相关。
• 结果表明，深度学习能够从常规组织学切片中提取出具有生物学和临床意义的表型模式。
• 该模型的性能支持其在临床分层、靶向治疗选择及个性化治疗方案制定中的潜在应用价值。