Department of Radiation Oncology, Shandong University Cancer Center, Jinan, Shandong, China.
Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China.
Front Immunol. 2024 Sep 20;15:1453232. doi: 10.3389/fimmu.2024.1453232. eCollection 2024.
Develop a predictive model utilizing weakly supervised deep learning techniques to accurately forecast major pathological response (MPR) in patients with resectable non-small cell lung cancer (NSCLC) undergoing neoadjuvant chemoimmunotherapy (NICT), by leveraging whole slide images (WSIs).
This retrospective study examined pre-treatment WSIs from 186 patients with non-small cell lung cancer (NSCLC), using a weakly supervised learning framework. We employed advanced deep learning architectures, including DenseNet121, ResNet50, and Inception V3, to analyze WSIs on both micro (patch) and macro (slide) levels. The training process incorporated innovative data augmentation and normalization techniques to bolster the robustness of the models. We evaluated the performance of these models against traditional clinical predictors and integrated them with a novel pathomics signature, which was developed using multi-instance learning algorithms that facilitate feature aggregation from patch-level probability distributions.
Univariate and multivariable analyses confirmed histology as a statistically significant prognostic factor for MPR (-value< 0.05). In patch model evaluations, DenseNet121 led in the validation set with an area under the curve (AUC) of 0.656, surpassing ResNet50 (AUC = 0.626) and Inception V3 (AUC = 0.654), and showed strong generalization in external testing (AUC = 0.611). Further evaluation through visual inspection of patch-level data integration into WSIs revealed XGBoost's superior class differentiation and generalization, achieving the highest AUCs of 0.998 in training and robust scores of 0.818 in validation and 0.805 in testing. Integrating pathomics features with clinical data into a nomogram yielded AUC of 0.819 in validation and 0.820 in testing, enhancing discriminative accuracy. Gradient-weighted Class Activation Mapping (Grad-CAM) and feature aggregation methods notably boosted the model's interpretability and feature modeling.
The application of weakly supervised deep learning to WSIs offers a powerful tool for predicting MPR in NSCLC patients treated with NICT.
利用弱监督深度学习技术，通过全切片图像（WSI）为接受新辅助化疗免疫治疗（NICT）的可切除非小细胞肺癌（NSCLC）患者开发一种准确预测主要病理反应（MPR）的预测模型。
本回顾性研究使用弱监督学习框架对 186 名非小细胞肺癌（NSCLC）患者的治疗前 WSI 进行了检查。我们采用了先进的深度学习架构，包括 DenseNet121、ResNet50 和 Inception V3，以在微观（斑块）和宏观（幻灯片）水平上分析 WSI。训练过程结合了创新的数据增强和归一化技术，以增强模型的稳健性。我们评估了这些模型对传统临床预测因子的性能，并将其与使用多实例学习算法开发的新型病理组学特征进行了整合，该算法促进了从斑块级概率分布中进行特征聚合。
单变量和多变量分析均证实组织学是 MPR 的统计学显著预后因素（-值<0.05）。在斑块模型评估中，DenseNet121 在验证集中表现最佳，曲线下面积（AUC）为 0.656，超过了 ResNet50（AUC=0.626）和 Inception V3（AUC=0.654），并且在外部测试中具有很强的泛化能力（AUC=0.611）。通过对斑块级数据集成到 WSI 的可视化检查进一步评估，发现 XGBoost 在分类和泛化方面具有优势，在训练中达到了最高的 AUC 为 0.998，在验证和测试中分别为稳健的 0.818 和 0.805。将病理组学特征与临床数据整合到列线图中，在验证和测试中分别得到 AUC 为 0.819 和 0.820，提高了判别准确性。梯度加权类激活映射（Grad-CAM）和特征聚合方法显著提高了模型的可解释性和特征建模能力。
将弱监督深度学习应用于 WSI 为预测接受 NICT 治疗的 NSCLC 患者的 MPR 提供了一种强大的工具。
