PO.BCS02.04 · 生物信息与计算
基于多区域CT的影像组学融合预测与肺腺癌相关的病理污染物指数
Multi-regional CT-based radiomics fusion predicts pathological pollutant index associated with lung adenocarcinoma
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
引言：肺腺癌（LUAD）是最常见的非小细胞肺癌，尤其在从不吸烟者中。环境污染，特别是空气颗粒物（PM2.5/PM5），是驱动肺癌发生的关键因素[1]。然而，可靠的个体水平污染暴露量化具有挑战性。我们近期引入了肺污染物指数（LPI），这是一种AI衍生的指标，从病理图像中量化组织驻留的污染物负荷。然而，基于病理的LPI是有创的，不适合大规模应用。我们提出一个机器学习框架，从胸部CT预测基于CT的LPI（CT-LPI），使接受胸部影像检查的个体（包括高危吸烟者和有偶发结节的从不吸烟者）能够无创地量化污染物负荷。
方法：我们回顾性研究了153例在MD Anderson癌症中心接受术前肺部CT（IRB 2023-0114）并有手术病理的LUAD患者。从数字化H&E图像计算的LPI[2]将队列分为LPI高（n=61）和LPI低（n=92）。从5-mm瘤周环、正常肺和全肺中提取区域性影像组学特征（每个区域793个），包括一阶、纹理、形状、高斯拉普拉斯、小波和生境特征。我们纳入了COPD相关的影像组学标志物以增强生物学可解释性。我们构建了一个多区域集成框架，使用互信息和弹性网（Elastic-Net）进行特征选择。训练了区域特异性分类器（Ridge逻辑回归、梯度提升、CatBoost），最终预测通过加权平均集成得出[3]。
结果：在5折交叉验证中，多区域集成实现了AUC 0.719和ACC 0.687，较最佳单区域模型AUC提升0.048，并优于简单平均（0.710）、LogisticNet（0.664）和ElasticNet（0.661）。纳入COPD相关标志物将AUC提高至0.724。
结论：我们开发了CT-LPI，利用互补的多区域特征从常规CT预测组织驻留的污染物负荷。该框架无创地量化个体对肺癌发生相关环境致癌物的暴露。通过实现对污染驱动的生物学改变的可扩展监测，CT-LPI可能支持环境暴露评估和个体化风险分层。下一步包括外部验证、应用于筛查数据集以及与其他生物标志物整合。[1] Hill W, 等. Nature. 2023. [2] Pan 等, Nature Cancer, 审稿中. [3] Shaheen A, 等. Front Neurosci. 2022.
查看英文原文 English abstract
Introduction: Lung adenocarcinoma (LUAD) is the most common non-small cell lung cancer, especially in never-smokers. Environmental pollution, particularly airborne particulates (PM2.5/PM5), is a critical factor driving lung cancer initiation [1]. However, reliable individual-level pollution exposure quantification is challenging. We recently introduced the lung pollutant index (LPI), an AI-derived metric quantifying tissue-resident pollutant burden from pathology images. However, pathology-based LPI is invasive and unsuitable for large-scale application. We propose a machine-learning framework to predict CT-based LPI (CT-LPI) from chest CT, enabling non-invasive pollutant burden quantification for individuals undergoing chest imaging, including high-risk smokers and never-smokers with incidental nodules.
Methods: We retrospectively investigated 153 LUAD patients who received preoperative lung CT at MD Anderson Cancer Center (IRB 2023-0114) with surgical pathology. LPI computed from digitalized H&E images [2] categorized cohorts into LPI-high (n=61) and LPI-low (n=92). Region-wise radiomics features (793 per region) were extracted from 5-mm peritumoral ring, normal lung, and whole lung, including first-order, texture, shape, Laplacian-of-Gaussian, wavelet, and habitat features. We incorporated COPD-associated radiomic markers to enhance biological interpretability. We built a multi-regional ensemble framework with features selected using mutual information and Elastic-Net. Region-specific classifiers (Ridge Logistic, Gradient Boosting, CatBoost) were trained, with final predictions via weighted-average ensemble [3].
Results: In 5-fold cross-validation, the multi-regional ensemble achieved AUC 0.719 and ACC 0.687, improving AUC by 0.048 over the best single-regional model and outperforming simple averaging (0.710), LogisticNet (0.664), and ElasticNet (0.661). Incorporating COPD-associated markers improved AUC to 0.724.
Conclusion: We developed CT-LPI, predicting tissue-resident pollutant burden from routine CT using complementary multi-regional features. This framework non-invasively quantifies individual exposure to environmental carcinogens implicated in lung cancer initiation. By enabling scalable monitoring of pollution-driven biological alterations, CT-LPI may support environmental exposure assessment and personalized risk stratification. Next steps include external validation, application to screening datasets, and integration with other biomarkers. [1] Hill W, et al. Nature. 2023. [2] Pan et al., Nature Cancer, under review. [3] Shaheen A, et al. Front Neurosci. 2022.
利益披露 Disclosure
Y. Li, None..
X. Pan, None..
A. Balachandra, None..
C. Young, None..
M. Salvatierra, None..
C. Behrens, None..
L. Solis Soto, None..
Y. Yuan, None..
C. Wu, None.