基于18F-FDG PET/CT的深度学习-影像组学-SUVmax整合预测鼻咽癌同步远处转移

文献信息

中文摘要

目的： 本研究旨在开发并评估基于氟-18氟代脱氧葡萄糖正电子发射计算机断层显像（18F-FDG PET/CT）的原发肿瘤（T）和颈部转移淋巴结（CMLNs）深度学习（DL）模型，用于预测鼻咽癌（NPC）患者的同步远处转移（SDM），并整合影像组学特征、原发肿瘤最大标准化摄取值（SUVmax-T）和临床特征。
方法： 分析了两个中心的218例患者（105例SDM，113例非SDM）的回顾性队列。在仅CT、仅PET和融合CT+PET图像上训练了三种DL架构（ResNet18、DenseNet121、EfficientNet-B0）。使用多层感知机（MLP）和随机森林（RF）分类器，建立了结合DL特征、T+CMLNs或仅T的影像组学特征、临床数据和SUVmax-T的九种模型。基于单独的T/N分期、临床数据、SUVmax-T和深度特征构建了多个MLP基准模型以进行比较分析。通过准确率、精确率、召回率、F1分数和ROC-AUC评估性能。排列特征重要性分析确定了最佳RF模型的核心预测因子，最佳混合模型进行了外部多中心验证。
结果： 双模态PET/CT网络优于单模态模型，ResNet18的内部ROC-AUC最高，为0.804，优于DenseNet121（0.791）和EfficientNet-B0（0.779）。整合影像组学特征（T）、临床参数和SUVmax-T持续提高了模型区分度，MLP混合模型达到内部ROC-AUC峰值0.839（召回率=0.747），优于RF模型（ROC-AUC=0.787，召回率=0.777）。仅基于T/N分期构建的模型内部AUC为0.476，外部AUC为0.513，而整合深度特征将其预测AUC提升至0.658（内部）和0.688（外部）。MLP混合模型的外部验证显示ROC-AUC为0.701，PR-AUC为0.571。SUVmax-T被确定为RF混合模型中最重要的预测特征。
结论： 在MLP框架中整合ResNet18（CT+PET）特征与影像组学特征（T）、SUVmax-T和临床数据获得了最高性能，SUVmax-T被确定为SDM预测因子。比较基准分析验证了该多模态混合模型比仅依赖传统T和N分期的模型具有更好的区分性能。

英文摘要

OBJECTIVES: This study aimed to develop and evaluate deep learning (DL) models of primary tumor (T) and cervical metastatic lymph nodes (CMLNs) using fluorine-18 fluorodeoxyglucose positron emission computed tomography (18F-FDG positron emission tomography/computed tomography (PET/CT)) imaging for predicting synchronous distant metastasis (SDM) in nasopharyngeal carcinoma (NPC) patients, integrating radiomic features, primary tumor maximum standardized uptake value (SUVmax-T) and clinical features.
METHODS: A two-center retrospective cohort of 218 patients (105 SDM, 113 non-SDM) was analyzed. Three DL architectures (ResNet18, DenseNet121, EfficientNet-B0) were trained on CT-only, PET-only, and fused CT+PET images. Nine models combining DL features, radiomic features of T + CMLNs or T-only, clinical data, and SUVmax-T using Multilayer Perceptron (MLP) and Random Forest (RF) classifiers were established. Multiple MLP benchmark models were built based on separate T/N staging, clinical data, SUVmax-T and deep features for comparative analysis. Performance was assessed via accuracy, precision, recall, F1-score, and ROC-AUC. Permutation feature importance analysis identified core predictors of the optimal RF model, and the optimal hybrid model underwent external multicenter validation.
RESULTS: Dual-modal PET/CT networks surpassed single-modality models, with ResNet18 yielding the highest internal ROC-AUC of 0.804, superior to DenseNet121 (0.791) and EfficientNet-B0 (0.779). Integrating radiomic features (T), clinical parameters and SUVmax-T continuously elevated model discrimination, and the MLP hybrid model reached the peak internal ROC-AUC of 0.839 (recall = 0.747), outperforming the RF model (ROC-AUC = 0.787, recall = 0.777). Models built only on T/N staging reached an internal AUC of 0.476 and an external AUC of 0.513, while integrating deep features boosted their predictive AUC to 0.658 (internal) and 0.688 (external). External validation of the MLP hybrid model showed an ROC-AUC of 0.701 and a PR-AUC of 0.571. SUVmax-T was identified as the most important predictive feature in the RF hybrid model.
CONCLUSION: Integrating ResNet18 (CT+PET) features with radiomic features (T), SUVmax-T and clinical data in an MLP framework yielded the highest performance, with SUVmax-T identified as an SDM predictor. Comparative benchmark analysis verified that this multimodal hybrid model achieved better discriminative performance than models relying solely on conventional T and N staging.