基于RegGAN的无对比剂CT增强食管癌评估:自动肿瘤分割与T分期的多中心验证
该回顾性多中心研究纳入1092例食管癌患者,利用配准引导生成对抗网络(RegGAN)从平扫CT合成增强CT,并用CSSNet分割肿瘤、双路径深度学习模型进行T分期。合成图像质量与真实增强CT相当,分割Dice=0.89,T分期AUC=0.7893-0.8360,辅助临床医生后诊断准确率AUC提升约0.1(p<0.01)。
要点
- RegGAN可从平扫CT合成质量接近真实增强CT的图像(NMAE=0.1903,SSIM=0.7723,视觉评分p≥0.12)。
- CSSNet肿瘤分割在外部测试中Dice=0.89,95%HD=2.27。
- 深度学习T分期模型AUC=0.7893-0.8360,辅助后临床医生AUC提升约0.1(p<0.01)。
核心结论
- 基于RegGAN的框架无需对比剂即可维持食管癌分割(Dice>0.88)和T分期(AUC>0.78)的诊断准确性,为碘过敏或肾功能损害患者提供安全、经济的替代方案,并提升不同经验水平医生间的诊断一致性。
研究设计与样本
- 回顾性多中心分析纳入1092例食管癌患者(2013-2024年),分为训练组(N=313)、内部测试组(N=117)和外部测试组(N=116及N=546);采用RegGAN合成增强CT,CSSNet分割肿瘤,双路径深度学习模型结合影像组学特征与Vision Transformer深度特征进行T分期。
诊断标准与关键数值
- RegGAN合成增强CT质量:NMAE=0.1903,SSIM=0.7723,视觉评分与真实增强CT比较p≥0.12。
- CSSNet肿瘤分割外部测试:Dice=0.89,95%HD=2.27。
- 深度学习T分期模型AUC=0.7893-0.8360,优于机器学习模型(AUC≤0.8323)。
- 深度学习模型AUC超过早期职业临床医生(AUC=0.641-0.757),与专家相当(AUC=0.840)。
- 合成增强CT辅助临床医生后诊断准确率AUC提升约0.1(p<0.01),决策曲线分析显示在>35%风险阈值具有临床效用。
临床应用与阅片要点
- 合成增强CT辅助可使临床医生诊断准确率AUC提升约0.1(p<0.01),并缩小不同经验水平医生间的诊断差异。
- 决策曲线分析确认合成增强CT在>35%风险阈值具有临床效用。
- 作者认为该框架为碘过敏或肾功能损害患者提供安全、经济的替代方案。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: This study aimed to develop a deep learning (DL) framework using registration-guided generative adversarial networks (RegGAN) to synthesize contrast-enhanced CT (Syn-CECT) from non-contrast CT (NCCT), enabling iodine-free esophageal cancer (EC) T-staging.
METHODS: A retrospective multicenter analysis included 1,092 EC patients (2013-2024) divided into training (N = 313), internal (N = 117), and external test cohorts (N = 116 and N = 546). RegGAN synthesized Syn-CECT by integrating registration and adversarial training to address NCCT-CECT misalignment. Tumor segmentation used CSSNet with hierarchical feature fusion, while T-staging employed a dual-path DL model combining radiomic features (from NCCT/Syn-CECT) and Vision Transformer-derived deep features. Performance was validated via quantitative metrics (NMAE, PSNR, SSIM), Dice scores, AUC, and reader studies comparing six clinicians with/without model assistance.
RESULTS: RegGAN achieved Syn-CECT quality comparable to real CECT (NMAE = 0.1903, SSIM = 0.7723; visual scores: p ≥ 0.12). CSSNet produced accurate tumor segmentation (Dice = 0.89, 95% HD = 2.27 in external tests). The DL staging model outperformed machine learning (AUC = 0.7893-0.8360 vs. ≤ 0.8323), surpassing early-career clinicians (AUC = 0.641-0.757) and matching experts (AUC = 0.840). Syn-CECT-assisted clinicians improved diagnostic accuracy (AUC increase: ~ 0.1, p < 0.01), with decision curve analysis confirming clinical utility at > 35% risk threshold.
CONCLUSIONS: The RegGAN-based framework eliminates contrast agents while maintaining diagnostic accuracy for EC segmentation (Dice > 0.88) and T-staging (AUC > 0.78). It offers a safe, cost-effective alternative for patients with iodine allergies or renal impairment and enhances diagnostic consistency across clinician experience levels. This approach addresses limitations of invasive staging and repeated contrast exposure, demonstrating transformative potential for resource-limited settings.
引用
- Huang X, Li W, Wang Y, et al. RegGAN-based contrast-free CT enhances esophageal cancer assessment: multicenter validation of automated tumor segmentation and T-staging. Radiol Med. 2025. PMID: 40892332. doi:10.1007/s11547-025-02083-y
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。