Huang Xiaoxiao, Huang Xiaoxin, Xie Yurun, Wang Kui, Bai Housheng, Ning Ruiling, Zhu Xiqi, Huang Deyou, Jin Guanqiao
Medical Imaging Center, Guangxi Medical University Cancer Hospital, Nanning, Guangxi, China.
Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, Guangxi, China.
BMC Med Imaging. 2025 Jul 17;25(1):288. doi: 10.1186/s12880-025-01828-5.
PD-1/PD-L1 immunotherapy represents the primary treatment for advanced NSCLC patients; however, response rates to this therapy vary among individuals. This dual-center study aimed to integrate habitat radiomics and multi-instance deep learning to predict durable clinical benefits from immunotherapy.
We retrospectively collected 590 NSCLC patients from two medical centers who received PD-1/PD-L1 inhibitor immunotherapy. Patients from the GMU center were divided into a training cohort (n = 375) and an internal validation cohort (n = 161) for habitat analysis and multi-instance deep learning model development. Patients from the YJ center formed an external testing cohort (n = 54) for model validation. We implemented a DenseNet121-based architecture extracting radiomics features from triplanar (axial/coronal/sagittal) tumor sequences to construct a 2.5D deep-learning dataset. Then, we fuse 2.5D features through multi-instance learning. Additionally, we use K-means clustering to divide the tumor VOI into three subregions to extract radiological features for building a Habitat model. Finally, we use the Extra-Trees classifier to construct MIL, Habitat, and Combined models, the Combined model integrating age factors into the analysis. The primary endpoint was durable clinical benefit. Finally, a separate PD-L1 expression dataset was used to compare the predictive performance of imaging models against PD-L1 status (positive/negative) and expression levels (high/low) to identify the optimal model for predicting immunotherapy clinical benefit.
The Combined model combining Habitat, MIL, and patient age demonstrated robust DCB prediction with AUCs of 0.906(95% CI: 0.874-0.936), 0.889(95% CI: 0.826-0.948), and 0.831 (95% CI: 0.710-0.927)in training, validation, and testing cohorts respectively. Comparative analysis revealed all imaging models outperformed PD-L1 expression status (positive/negative) and levels (high/low) in predicting therapeutic response, with Habitat analysis showing superior performance to MIL alone. Notably, peritumoral structural features emerged as significant predictors of treatment efficacy.
This non-invasive predictive framework provides clinically actionable insights for immunotherapy stratification, potentially overcoming limitations of current biomarker testing while highlighting the prognostic value of spatial tumor heterogeneity analysis.
PD-1/PD-L1免疫疗法是晚期非小细胞肺癌（NSCLC）患者的主要治疗方法；然而，个体对该疗法的反应率各不相同。这项双中心研究旨在整合瘤周影像组学和多实例深度学习，以预测免疫疗法的持久临床获益。
我们回顾性收集了来自两个医疗中心的590例接受PD-1/PD-L1抑制剂免疫治疗的NSCLC患者。乔治梅森大学（GMU）中心的患者被分为训练队列（n = 375）和内部验证队列（n = 161），用于瘤周分析和多实例深度学习模型开发。浙江大学医学院附属第一医院（YJ）中心的患者组成外部测试队列（n = 54）用于模型验证。我们采用基于DenseNet121的架构，从三平面（轴位/冠状位/矢状位）肿瘤序列中提取影像组学特征，构建一个2.5D深度学习数据集。然后，我们通过多实例学习融合2.5D特征。此外，我们使用K均值聚类将肿瘤感兴趣区（VOI）划分为三个子区域，以提取放射学特征来构建瘤周模型。最后，我们使用极端随机树分类器构建多实例学习（MIL）、瘤周和联合模型，联合模型将年龄因素纳入分析。主要终点是持久临床获益。最后，使用一个单独的PD-L1表达数据集来比较影像模型相对于PD-L1状态（阳性/阴性）和表达水平（高/低）的预测性能，以确定预测免疫治疗临床获益的最佳模型。
结合瘤周、多实例学习和患者年龄的联合模型在训练、验证和测试队列中分别显示出强大的持久临床获益（DCB）预测能力，曲线下面积（AUC）分别为0.906（95%置信区间：0.874 - 0.936）、0.889（95%置信区间：0.826 - 0.948）和0.831（95%置信区间：0.710 - 0.927）。比较分析显示，在预测治疗反应方面，所有影像模型均优于PD-L1表达状态（阳性/阴性）和水平（高/低），瘤周分析显示出比单独的多实例学习更好的性能。值得注意的是，瘤周结构特征是治疗疗效的重要预测指标。
这个非侵入性预测框架为免疫治疗分层提供了临床可操作的见解，可能克服当前生物标志物检测的局限性，同时突出肿瘤空间异质性分析的预后价值。
