胸部CT黏液栓检测:放射科医师与AI性能比较
回顾性分析278例COPDGene参与者,比较AI自动黏液栓检测与放射科医师评估。AI患者层面敏感度低于医师R1但特异度相近,AI辅助提高了医师的栓子层面敏感度和观察者一致性。AI检出的非参考阳性病灶与更严重的气流受限和临床严重程度独立相关。
要点
- AI黏液栓检测特异度高,可作为初筛工具但需医师复核以避免漏诊
- AI辅助阅片可提高放射科医师黏液栓检出敏感度及一致性
- AI检出的支气管壁增厚或部分阻塞性黏液也提示气道疾病严重程度,应关注
核心结论
- AI对胸部CT黏液栓检测的敏感度低于放射科医师,但患者层面特异度与医师相近
- AI辅助提高了医师的栓子层面敏感度和观察者间一致性
- AI额外检出的非参考阳性气道异常与更差的气流受限、肺气肿、Pi10及临床严重程度独立相关
研究设计与样本
- 回顾性分析COPDGene队列278例,涵盖从不吸烟者、保留比值肺功能受损者及GOLD 0–4级
- AI工具生成候选黏液栓,两名胸部放射科医师分别独立在无AI和有AI辅助下识别黏液栓
- 第三名胸部放射科医师对所有候选病灶进行裁定作为参考标准
关键影像表现/征象
- 参考标准黏液栓见于114/278例(41%)参与者
- AI检出的非参考阳性病灶多为明显的支气管壁增厚或部分阻塞性黏液
诊断标准与关键数值
- 患者层面AI敏感度为68.4%,低于R1的86.8%(p<0.001),与R2的79.8%差异无统计学意义(p=0.141)
- 患者层面AI特异度为95.7%,与医师的98.8%–100.0%相近
- 栓子层面AI敏感度为34.8%,低于R1的58.9%和R2的55.6%(均p<0.001)
- AI辅助使医师栓子层面敏感度提高至63.6%–68.6%(p≤0.004)
- AI与医师一致性良好(κ=0.62–0.69),AI辅助后观察者间一致性从κ=0.70提高至0.78(p<0.001)
临床应用与阅片要点
- AI可辅助放射科医师提高黏液栓检出敏感度,适合作为标准化筛查和辅助阅片工具
- AI检出的支气管壁增厚或部分阻塞性黏液不应简单归为假阳性,需结合肺功能与临床严重程度评估
- 日常报告时应关注AI标注的额外气道异常,尤其在与气流受限程度不符时
局限性
- 该研究为回顾性分析,样本来自COPDGene队列,参考标准由第三名医师裁定而非病理或随访
- AI检测的非参考阳性病灶缺乏独立验证,其临床意义需前瞻性研究确认
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
OBJECTIVES: To compare automated mucus plug detection with radiologist evaluation, assess AI-assisted detection, and examine associations of algorithm-derived airway obstruction burden with COPD severity.
MATERIALS AND METHODS: This retrospective analysis included 278 COPDGene participants selected across never-smokers, smokers with preserved ratio-impaired spirometry, and GOLD stages 0-4. An AI tool generated candidate plugs. Two thoracic radiologists independently identified plugs in unaided and AI-assisted sessions. A third thoracic radiologist adjudicated all candidates as the reference. Patient- and plug-level performance, observer agreement, false-positive detection, and rank-transformed associations with pulmonary function, CT parameters, and clinical severity were evaluated.
RESULTS: Reference mucus plugs were present in 114/278 participants (41%). Patient-level AI sensitivity was lower than R1 (68.4% vs 86.8%; p < 0.001) but not different from R2 (68.4% vs 79.8%; p = 0.141), whereas specificity was similar across approaches (95.7% vs 98.8%-100.0%). Plug-level AI sensitivity was lower than both readers (34.8% vs 58.9% for R1 and 55.6% for R2; both p < 0.001). AI assistance improved readers' plug-level sensitivity (63.6-68.6%; p ≤ 0.004). AI-reader agreement was good (κ, 0.62-0.69), and inter-reader agreement improved with AI (κ, 0.70 vs 0.78; p < 0.001). These non-reference-positive AI detections (0.396/scan) were mostly marked bronchial wall thickening or partially occlusive mucus. They were independently associated with worse airflow limitation, CT emphysema, Pi10, and clinical severity after accounting for true-positive burden, improving model fit (ΔR², 0.03-0.05).
CONCLUSION: AI was less sensitive than radiologists but had similar specificity for mucus plug detection. AI assistance improved reader sensitivity and agreement. Additional algorithm-detected airway abnormalities remained associated with airway disease severity.
KEY POINTS: QuestionAutomated mucus plug detection on chest CT may enable standardized COPD assessment, but independent validation against radiologist assessments remains limited. FindingsArtificial intelligence showed lower sensitivity than radiologists but similar patient-level specificity on chest CT, and assistance improved sensitivity and inter-reader agreement. Clinical relevanceAutomated mucus plug analysis may support standardized airway obstruction burden assessment in COPD research and clinical trials while retaining radiologist oversight.
引用
- Yoon, Kligerman, Friedlander, et al. Radiologist and AI performance in detecting mucus plugs on chest CT. Eur Radiol. 2026. PMID: 42814120. doi:10.1007/s00330-026-12868-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。