文献速递头颈技术与安全CTMRPET

口咽鳞癌AI影像组学的转化差距:TRIPOD+AI范围综述

The Translational Gap in AI for Oropharyngeal Squamous Cell Carcinoma: A TRIPOD+AI Scoping Review of Methodological Barriers to Treatment Deintensification.
PubMed 文献 · Acad Radiol · 2026-09-05

结果显示HPV模型AUC为0.65–0.95,但外部验证仅36.1%,TRIPOD+AI报告质量评估发现校准、缺失数据处理、风险分层等方面存在严重报告缺口,尚不能安全指导临床治疗降级。

要点

  • HPV预测模型AUC达0.65–0.95,但外部验证不足且性能常下降
  • 绝大多数研究仅分析原发肿瘤,淋巴结病变纳入率仅18.0%
  • 校准信息91.8%缺失,无法评估模型预测概率的可靠性

核心结论

  • CT、MRI、FDG-PET/CT的AI/影像组学模型在口咽鳞癌HPV相关目标中显示出有前景的区分能力,但校准、透明度及风险分层报告缺口持续存在,加上外部验证有限及淋巴结覆盖不足,尚不能安全用于临床治疗降级指导。

研究设计与样本

  • 纳入61项组织学确诊口咽鳞癌中应用AI/影像组学于CT、MRI、FDG-PET/CT的研究,聚焦HPV预测和治疗降级。
  • 采用TRIPOD+AI工具(27个条目,0–2评分制)评价报告质量。
  • 61项研究中34项针对HPV预测,29项针对生存或预后,3项针对治疗反应,部分研究涉及多个目标。

关键影像表现/征象

  • CT为最常用影像模态(49.2%),其次为MRI(29.5%)和FDG-PET/CT(21.3%,均为18F-FDG)。
  • 手动分割(85.2%)和手工特征影像组学结合机器学习(57.4%)为最常见的技术路径。
  • 大多数研究(78.7%)仅分析原发肿瘤,仅11/61(18.0%)纳入淋巴结病变,2/61(3.3%)以淋巴结为唯一分析目标。

诊断标准与关键数值

  • HPV预测模型报告的AUC范围为0.65–0.95,外部验证比例为22/61(36.1%),且验证时性能常出现下降。
  • TRIPOD+AI报告质量关键缺口:缺失数据处理完全报告仅3.3%,缺失达54.1%。
  • 校准信息完全报告仅6.6%,缺失高达91.8%;可解释风险分组完全报告27.9%,缺失68.9%。
  • 数据可获取性报告比例为19.7%,代码可获取性报告比例为11.5%。

临床应用与阅片要点

  • 日常阅片中应关注模型是否同时纳入原发肿瘤和淋巴结信息,单纯原发灶模型在颈淋巴结评估中可能存在盲区。
  • 报告AI预测结果时注意模型校准信息普遍缺失,预测概率的绝对数值不宜直接用于治疗降级决策。
  • 外部验证性能下降提示在不同设备或人群间直接套用已发表模型存在风险,临床引用前需确认验证条件。

局限性

  • 外部验证比例仅为36.1%,多数模型缺乏跨中心验证。
  • 校准信息在91.8%的研究中缺失,无法评估模型预测概率的可靠性。
  • 数据可获取性(19.7%)和代码可获取性(11.5%)报告率低,结果可重复性受限。

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

RATIONALE AND OBJECTIVES: To map artificial intelligence (AI) and radiomics applications in computed tomography (CT), magnetic resonance imaging (MRI), and fluorodeoxyglucose positron emission tomography/CT (FDG-PET/CT) for oropharyngeal squamous cell carcinoma (OPSCC) in the context of human papillomavirus (HPV) status and treatment deintensification, evaluate reporting quality using TRIPOD+AI (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis + Artificial Intelligence), and identify barriers to clinical translation.

MATERIALS AND METHODS: Following PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews), we searched PubMed/MEDLINE and Scopus (January 2015-December 2025) for studies applying AI/radiomics to CT, MRI, and FDG-PET/CT in histologically confirmed OPSCC, focusing on HPV prediction and treatment deintensification. TRIPOD+AI (27 items, 0-2 scoring) assessed reporting quality.

RESULTS: Sixty-one studies were included; 34 addressed HPV prediction, 29 survival or prognosis, and 3 treatment response, with several studies addressing more than one objective. CT was the most frequent modality (49.2%), followed by MRI (29.5%) and FDG-PET/CT (21.3%, all 18F-FDG), with manual segmentation (85.2%) and handcrafted radiomics with machine learning (57.4%) being the most common. HPV models reported areas under the curve (AUCs) of 0.65-0.95, but external validation remained limited (22/61, 36.1%), often with performance decline. TRIPOD+AI revealed critical gaps: missing data handling (fully reported 3.3%, absent 54.1%), calibration (6.6% fully, 91.8% absent), interpretable risk groups (27.9% fully, 68.9% absent), data availability (19.7%), and code availability (11.5%). Most studies (78.7%) restricted analysis to the primary tumor; nodal disease was incorporated in 11/61 (18.0%) and was the sole target in 2/61 (3.3%).

CONCLUSION: CT-, MRI-, and FDG-PET/CT-based AI/radiomics models for OPSCC show promising discrimination, but persistent reporting gaps in calibration, transparency, and risk stratification, plus limited external validation and insufficient nodal coverage, preclude safe clinical implementation. Findings apply specifically to HPV-oriented objectives across CT, MRI, and FDG-PET/CT. Standardized protocols, rigorous validation, and structured reporting are needed before these tools can guide treatment deintensification.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Salvaggio, Gargano, Cutaia, et al. The Translational Gap in AI for Oropharyngeal Squamous Cell Carcinoma: A TRIPOD+AI Scoping Review of Methodological Barriers to Treatment Deintensification. Acad Radiol. 2026. PMID: 42701048. doi:10.1016/j.acra.2026.08.075

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。