基于MRI的深度学习算法与放射科医师对结直肠癌淋巴结转移的诊断比较:系统综述与Meta分析
该系统综述与Meta分析比较基于MRI的深度学习算法与放射科医师诊断结直肠癌淋巴结转移的性能,共纳入10项研究。内部验证队列(9项研究,n=1850)汇总敏感度0.89、特异度0.85、AUC 0.93;放射科医师汇总敏感度0.65、特异度0.74、AUC 0.76。深度学习算法在内部验证队列中各项指标均优于初级放射科医师,敏感度和AUC高于高级放射科医师(均P<0.05)。
要点
- 内部验证队列中,深度学习算法汇总敏感度0.89、特异度0.85、AUC 0.93。
- 放射科医师汇总敏感度0.65、特异度0.74、AUC 0.76。
- 深度学习算法各项指标优于初级放射科医师,敏感度和AUC高于高级放射科医师。
核心结论
- 基于MRI的深度学习算法在检测结直肠癌淋巴结转移方面显示出有前景的诊断性能,在内部验证队列中总体高于放射科医师的报告性能,尤其是经验较少的阅片者。
研究设计与样本
- 系统综述与Meta分析,检索PubMed、Embase和Web of Science截至2025年6月30日,纳入以组织病理学为参考标准、评估基于MRI的深度学习算法诊断淋巴结转移的研究,共纳入10项研究。
诊断标准与关键数值
- 内部验证队列(9项研究,n=1850)深度学习算法汇总敏感度0.89(95%CI:0.80-0.94)、特异度0.85(95%CI:0.77-0.91)、AUC 0.93(95%CI:0.91-0.95)。
- 放射科医师汇总敏感度0.65(95%CI:0.60-0.71)、特异度0.74(95%CI:0.71-0.77)、AUC 0.76(95%CI:0.73-0.80)。
- 深度学习算法在内部验证队列中各项指标均优于初级放射科医师,敏感度和AUC高于高级放射科医师(均P<0.05)。
临床应用与阅片要点
- 作者认为基于MRI的深度学习算法在内部验证队列中诊断性能总体高于放射科医师报告的性能,尤其对经验较少的阅片者。
- 作者建议需要前瞻性、多中心研究在不同人群中验证这些发现。
局限性
- 大多数纳入研究为回顾性研究。
- 大多数纳入研究来自中国,限制了结果的普遍性。
- 需要前瞻性、多中心研究在不同人群中验证这些发现。
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 systematic review and meta-analysis aimed to compare the diagnostic performance of MRI-based deep learning (DL) algorithms versus radiologists in detecting lymph node metastasis (LNM) in colorectal cancer (CRC).
METHODS: A comprehensive literature search was conducted in PubMed, Embase, and Web of Science up to June 30, 2025 for studies evaluating MRI-based DL algorithms for LNM diagnosis, using histopathology as the reference standard. Pooled sensitivity, specificity, and area under the curve (AUC) were calculated using a bivariate random-effects model. Risk of bias and applicability were assessed using the PROBAST+AI tool. Certainty of evidence was rated with the GRADE approach.
RESULTS: A total of 10 studies met inclusion criteria. Internal validation cohorts (9 studies, n=1850) showed pooled sensitivity of 0.89 (95% CI: 0.80-0.94), specificity of 0.85 (95% CI: 0.77-0.91), and AUC of 0.93 (95% CI: 0.91-0.95). Radiologists achieved lower pooled sensitivity of 0.65 (95% CI: 0.60-0.71) and specificity of 0.74 (95% CI: 0.71-0.77), with an AUC of 0.76 (95% CI: 0.73-0.80). DL algorithms in internal validation cohorts consistently outperformed junior radiologists in all metrics, and demonstrated higher sensitivity and AUC than senior radiologists(all P<0.05).
CONCLUSION: MRI-based DL algorithms show promising diagnostic performance in detecting LNM in CRC, with performance generally higher than those reported for radiologists in internal validation cohorts, particularly junior-experienced readers. However, most included studies were retrospective and originated from China, limiting generalizability. Prospective, multicenter studies are warranted to validate these findings across diverse populations.
引用
- Wang F, Deng W, Zhong Z, et al. MRI-Based Deep Learning Algorithms vs. Radiologists for Lymph Node Metastasis in Colorectal Cancer: A Systematic Review and Meta-analysis. Acad Radiol. 2025. PMID: 41107125. doi:10.1016/j.acra.2025.09.048
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。