基于功能磁共振成像特征和深度学习影像组学的堆叠多模态模型用于预测鼻咽癌放疗早期反应

A Stacked Multimodality Model Based on Functional MRI Features and Deep Learning Radiomics for Predicting the Early Response to Radiotherapy in Nasopharyngeal Carcinoma.

作者信息

Wang Xiaowen, Song Jian, Qiu Qingtao, Su Ya, Wang Lizhen, Cao Xiujuan

机构信息

Shandong University Cancer Center, Jinan, Shandong, China (X.W.); Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China (X.W., X.C.).

Medical Imageology, Shandong Medical College, Jinan, China (J.S.).

出版信息

Acad Radiol. 2025 Mar;32(3):1631-1644. doi: 10.1016/j.acra.2024.10.011. Epub 2024 Nov 3.

DOI:10.1016/j.acra.2024.10.011

PMID:39496536

Abstract

BACKGROUND

This study aimed to construct and assess a comprehensive model that integrates MRI-derived deep learning radiomics, functional imaging (fMRI), and clinical indicators to predict early efficacy of radiotherapy in nasopharyngeal carcinoma (NPC).

METHODS

This retrospective study recruited NPC patients with radiotherapy from two Chinese hospitals between October 2018 and July 2022, divided into a training set (hospital I, 194 cases), an internal validation set (hospital I, 82 cases), and an external validation set (hospital II, 40 cases). We extracted 3404 radiomic features and 2048 deep learning features from multi-sequence MRI includes T1WI, CE-T1WI, T2WI and T2WI/FS. Additionally, both the Apparent diffusion coefficient (ADC), its maximum (ADCmax) and Tumor blood flow (TBF), its maximum (TBFmax) were obtained by Diffusion-weighted imaging (DWI) and Arterial spin labeling (ASL) respectively. We used four classifiers (LR, XGBoost, SVM and KNN) and stacked algorithm as model construction methods. The area under the receiver operating characteristic curve (AUC) and decision curve analysis was used to assess models.

RESULTS

The manual radiomics model based on XGBoost and the deep learning model based on KNN (the AUCs in the training set: 0.909, 0.823, respectively) showed better predictive efficacy than other machine learning algorithms. The stacked model that integrated MRI-based deep learning radiomics, fMRI, and hematological indicators, has the strongest efficacy prediction ability of AUC in the training set [0.984 (95%CI: 0.972-0.996)], the internal validation set [0.936 (95%CI: 0.885-0.987)], and the external validation set [0.959 (95%CI: 0.901-1.000)].

CONCLUSION

Our research has developed a clinical-radiomics integrated model based on MRI which can predict early radiotherapy response in NPC and provide guidance for personalized treatment.

摘要

背景

本研究旨在构建并评估一个综合模型，该模型整合了磁共振成像（MRI）衍生的深度学习放射组学、功能成像（fMRI）和临床指标，以预测鼻咽癌（NPC）放疗的早期疗效。

方法

这项回顾性研究纳入了2018年10月至2022年7月期间在两家中国医院接受放疗的NPC患者，分为训练集（医院I，194例）、内部验证集（医院I，82例）和外部验证集（医院II，40例）。我们从包括T1WI、增强T1WI、T2WI和T2WI/FS的多序列MRI中提取了3404个放射组学特征和2048个深度学习特征。此外，表观扩散系数（ADC）及其最大值（ADCmax）以及肿瘤血流量（TBF）及其最大值（TBFmax）分别通过扩散加权成像（DWI）和动脉自旋标记（ASL）获得。我们使用四种分类器（逻辑回归（LR）、极端梯度提升（XGBoost）、支持向量机（SVM）和K近邻（KNN））以及堆叠算法作为模型构建方法。采用受试者操作特征曲线（AUC）下面积和决策曲线分析来评估模型。

结果

基于XGBoost的手工放射组学模型和基于KNN的深度学习模型（训练集中的AUC分别为0.909、0.823）显示出比其他机器学习算法更好的预测疗效。整合基于MRI的深度学习放射组学、fMRI和血液学指标的堆叠模型在训练集[AUC为0.984（95%CI：0.972 - 0.996）]、内部验证集[AUC为0.936（95%CI：0.885 - 0.987）]和外部验证集[AUC为0.959（95%CI：0.901 - 1.000）]中具有最强的疗效预测能力。