堆叠模型AI辅助诊断疑似垂体微腺瘤:非增强T1COR MRI多中心阅片研究
本研究基于非增强T1COR MRI构建整合临床、影像组学和深度学习特征的堆叠模型,并在三个中心636例患者中验证。联合模型在外部验证队列AUC达0.818和0.899,在315个病灶、5名放射科医生的阅片研究中,AI辅助显著提高各经验水平医生的诊断准确率并改善阅片者间一致性。
要点
- 联合模型在外部验证队列中AUC为0.818和0.899,EVC2敏感度0.929、特异度0.833。
- AI辅助使高年资医生在最具挑战性外部队列准确率最高达85.4%,较无辅助绝对提升约30%。
- 联合模型辅助可系统性改善微腺瘤与非微腺瘤组的阅片者间一致性总分。
核心结论
- 整合临床、影像组学和深度学习特征的堆叠模型有潜力辅助放射科医生诊断疑似垂体微腺瘤,为未来临床转化提供基础。
研究设计与样本
- 回顾性多中心研究,纳入三个中心636例患者,分为训练集321例、内部验证集138例和两个外部验证集136例与41例。
- 基于非增强T1COR MRI构建手工影像组学、深度迁移学习、深度学习影像组学和临床四种基模型,以逻辑回归为元分类器进行堆叠集成。
- 阅片研究纳入315个病灶和5名放射科医生(3名初级、2名高级),分三轮评估无辅助、DTL辅助和联合模型辅助。
诊断标准与关键数值
- 联合模型在外部验证队列EVC1的AUC为0.818,在EVC2的AUC为0.899。
- 联合模型在EVC2的敏感度为0.929、特异度为0.833。
- 联合模型辅助下,高级医生在内部验证队列准确率为75.4-79.0%(P-adj < 0.05),在最具挑战性外部队列最高达85.4%(P-adj < 0.05),较无辅助绝对提升约30%。
临床应用与阅片要点
- 在非增强T1COR MRI上可借助联合模型辅助识别疑似垂体微腺瘤,尤其对经验不足医生有增益。
- 联合模型辅助有助于提高微腺瘤诊断的阅片者间一致性,可减少双向判读误差。
局限性
- 本研究为回顾性设计,结论需前瞻性验证。
- 外部验证队列样本量较小(EVC2仅41例),泛化性需进一步评估。
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
OBJECTIVE: This study sought to quantify, through a multi-reader study, whether AI assistance improves diagnostic accuracy across experience levels, reduces bidirectional errors, and enhances inter-reader consensus in suspected pituitary microadenoma diagnosis. To this end, we developed and validated a stacking model integrating clinical, radiomics, and deep learning features on non-contrast T1COR MRI.
MATERIALS AND METHODS: This retrospective multicenter study enrolled 636 patients from three centers, divided into training (n = 321), internal validation (n = 138), and two external validation cohorts (n = 136, n = 41). We developed four base models-handcrafted radiomics, deep transfer learning (DTL), deep learning radiomics (DLR), and clinical-and integrated them via a stacking ensemble with logistic regression as the meta-classifier. To evaluate real-world clinical impact, a three-round reader study was conducted with 315 lesions and five radiologists (three juniors, two seniors). Readers assessed non-contrast T1COR MRI unaided, with DTL assistance, and with combined model assistance. Performance metrics included AUC, accuracy, sensitivity, specificity, and inter-reader consensus.
RESULTS: The combined model outperformed all single-modality approaches across validation cohorts, achieving AUCs of 0.818 (EVC1) and 0.899 (EVC2) with balanced sensitivity and specificity (EVC2: 0.929 and 0.833, respectively). In the reader study with 315 lesions and five radiologists, AI assistance significantly improved diagnostic accuracy across all experience levels. With combined model assistance, gains were more pronounced: seniors achieved 75.4-79.0% accuracy in the internal validation cohort (P-adj < 0.05), and up to 85.4% in the most challenging external cohort (P-adj < 0.05)- an absolute improvement of approximately 30% over unaided performance. The combined model also enhanced diagnostic consensus, with total scores from five radiologists showing systematic improvement for both microadenoma and non-microadenoma groups.
CONCLUSIONS: The findings of this study suggest that our combined model holds promise as an effective tool to assist radiologists in the diagnosis of suspected pituitary microadenoma, providing a foundation for future clinical translation.
引用
- Kang S, Wang K, Yu Y, et al. A stacking model for AI-assisted diagnosis of suspected pituitary microadenomas on non-contrast T1COR MRI: a multicenter reader study on bridging the experience gap. Neuroradiology. 2026. PMID: 42622847. doi:10.1007/s00234-026-04135-0
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。