基于 habitat 影像组学、3D 深度学习与临床变量整合模型在非增强胸部 CT 上检测早期食管鳞状细胞癌的多中心研究
Integrating habitat-based radiomics, 3D deep learning, and clinical variables for detection of early-stage esophageal squamous cell carcinoma on noncontrast chest CT: A multicenter study.
作者
作者单位
- The First School of Medicine, School of Information and Engineering, Wenzhou Medical University, Wenzhou 325000, China.
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China. Electronic address: caoguoquan@wmu.edu.cn.
摘要
中文
本研究旨在开发并验证一种整合 habitat 亚区影像组学、3D 深度学习（DL）特征与临床变量的联合模型（Combined model），用于在非增强胸部 CT 上检测早期食管鳞状细胞癌（ESCC）。在这项回顾性多中心研究中，通过无监督聚类将分割的食管感兴趣区划分为 habitat 亚区，从这些亚区提取影像组学特征，并与基于 3D ResNet-101 提取的深度特征融合，构建深度学习–影像组学融合模型（DLR）。进一步将筛选的临床变量与 DLR 签名整合形成 Combined 模型。通过曲线下面积（AUC）、校准曲线和决策曲线分析（DCA）评估模型性能。利用 SHAP 分析评估模型可解释性，并通过探索性阅片者对比研究评估 AI 辅助对放射科医生表现的影响。共纳入 469 例受试者。DLR 模型在各队列中均优于 habitat 影像组学模型和独立 DL 模型。Combined 模型表现最佳，内部验证 AUC 为 0.895，外部测试 AUC 为 0.847，校准和 DCA 良好。AI 辅助提高了所有四位放射科医生对早期 ESCC 的敏感性并增加了阅片者间一致性。在这项回顾性病例对照研究中，Combined 模型在早期 ESCC 检测中展现出良好的区分度和校准度，并具有初步的跨中心表现。这些发现支持对该模型进行前瞻性评估，作为已有非增强胸部 CT 检查的机会性第二阅片者与分诊工具。
English
To develop and validate a Combined model integrating habitat-based sub-regional radiomics, 3D deep learning (DL) features, and clinical variables for the detection of early-stage esophageal squamous cell carcinoma (ESCC) on noncontrast chest CT. In this retrospective multicenter study, the segmented esophageal region of interest was partitioned into habitat sub-regions via unsupervised clustering, and radiomic features extracted from these sub-regions were fused with deep features derived from a 3D ResNet-101 to construct a deep learning-radiomics fusion model (DLR). Selected clinical variables were further integrated with the DLR signature to form the Combined model. Performance was evaluated by the area under the curve (AUC), calibration curves, and decision curve analysis (DCA). Model interpretability was assessed using SHAP analysis, and an exploratory reader-comparison study evaluated the effect of AI assistance on radiologist performance. A total of 469 subjects were included. The DLR model outperformed both the habitat-based radiomic model and the standalone DL model across cohorts. The Combined model achieved the highest AUC of 0.895 (internal validation) and 0.847 (external test), with favorable calibration and DCA. AI assistance improved the sensitivity of all four radiologists for early-stage ESCC and increased inter-reader agreement. In this retrospective case-control study, the Combined model demonstrated promising discrimination and calibration for early-stage ESCC, with preliminary cross-center performance. These findings support prospective evaluation of the model as an opportunistic second-reader and triage tool for already-acquired noncontrast chest CT examinations.
分类与指标
- 研究类型
- AI/ML
- 病种
- 食管癌
- JCR 分区
- Q1
- 影响因子
- 3.9
- 新锐分区
- 2区