RegGAN-based contrast-free CT enhances esophageal cancer assessment: multicenter validation of automated tumor segmentation and T-staging.

IF 4.8 1区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiologia Medica Pub Date : 2025-09-02 DOI:10.1007/s11547-025-02083-y

Xiaoyu Huang, Weihang Li, Yaru Wang, Qibing Wu, Ping Li, Kai Xu, Yong Huang

{"title":"RegGAN-based contrast-free CT enhances esophageal cancer assessment: multicenter validation of automated tumor segmentation and T-staging.","authors":"Xiaoyu Huang, Weihang Li, Yaru Wang, Qibing Wu, Ping Li, Kai Xu, Yong Huang","doi":"10.1007/s11547-025-02083-y","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":20817,"journal":{"name":"Radiologia Medica","volume":" ","pages":""},"PeriodicalIF":4.8000,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiologia Medica","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s11547-025-02083-y","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

基于reggan的无对比CT增强食管癌评估：自动肿瘤分割和t分期的多中心验证。

目的：本研究旨在开发一个使用注册引导生成对抗网络（RegGAN）的深度学习（DL）框架，从非对比CT （NCCT）合成对比增强CT (Syn-CECT)，从而实现无碘食管癌（EC） t分期。方法：回顾性多中心分析纳入1092例EC患者（2013-2024），分为训练组（N = 313）、内部组（N = 117）和外部组（N = 116和N = 546）。RegGAN通过结合配准和对抗性训练来合成Syn-CECT，解决NCCT-CECT的错位问题。肿瘤分割采用分层特征融合的CSSNet，而t分期采用结合放射学特征（来自NCCT/Syn-CECT）和Vision transformer衍生深度特征的双路径深度学习模型。通过定量指标（NMAE、PSNR、SSIM）、Dice评分、AUC和比较6名有/没有模型辅助的临床医生的读者研究来验证其表现。结果：RegGAN达到了与真实CECT相当的Syn-CECT质量（NMAE = 0.1903, SSIM = 0.7723；视觉评分：p≥0.12）。CSSNet对肿瘤进行了准确的分割（外测Dice = 0.89, 95% HD = 2.27）。深度学习分期模型优于机器学习（AUC = 0.7893-0.8360 vs.≤0.8323），超过早期职业临床医生（AUC = 0.641-0.757）和匹配专家（AUC = 0.840）。syn - cect辅助临床医生提高了诊断准确性（AUC提高~ 0.1，风险阈值p 35%）。结论：基于reggan的框架消除了造影剂，同时保持了EC分割（Dice > 0.88）和t分期（AUC > 0.78）的诊断准确性。它为碘过敏或肾损害患者提供了一种安全、具有成本效益的替代方案，并提高了临床医生经验水平的诊断一致性。这种方法解决了侵袭性分期和重复造影剂暴露的局限性，展示了在资源有限的情况下的变革潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Radiologia Medica 医学-核医学

CiteScore

14.10

自引率

7.90%

发文量

133

审稿时长

4-8 weeks

期刊介绍： Felice Perussia founded La radiologia medica in 1914. It is a peer-reviewed journal and serves as the official journal of the Italian Society of Medical and Interventional Radiology (SIRM). The primary purpose of the journal is to disseminate information related to Radiology, especially advancements in diagnostic imaging and related disciplines. La radiologia medica welcomes original research on both fundamental and clinical aspects of modern radiology, with a particular focus on diagnostic and interventional imaging techniques. It also covers topics such as radiotherapy, nuclear medicine, radiobiology, health physics, and artificial intelligence in the context of clinical implications. The journal includes various types of contributions such as original articles, review articles, editorials, short reports, and letters to the editor. With an esteemed Editorial Board and a selection of insightful reports, the journal is an indispensable resource for radiologists and professionals in related fields. Ultimately, La radiologia medica aims to serve as a platform for international collaboration and knowledge sharing within the radiological community.