计算机辅助诊断食管癌及肿瘤内镜图像的系统综述与诊断准确性荟萃分析
该系统综述与诊断准确性荟萃分析评估了基于内镜图像的计算机辅助诊断(CAD)算法对食管癌或肿瘤的诊断性能。共纳入21项研究进行系统综述,19项纳入荟萃分析。CAD算法诊断食管癌或肿瘤的汇总AUC为0.97,灵敏度0.94,特异度0.88;诊断浸润深度的汇总AUC为0.96,灵敏度0.90,特异度0.88。结论认为CAD算法准确性高,但需克服外部验证和临床应用的局限。
要点
- CAD算法诊断食管癌或肿瘤的汇总AUC达0.97,灵敏度0.94,特异度0.88。
- CAD算法诊断浸润深度的汇总AUC为0.96,灵敏度0.90,特异度0.88。
- 研究提示CAD算法准确性高,但外部验证和临床应用不足。
核心结论
- CAD算法在内镜自动诊断食管癌及肿瘤方面显示出高准确性。
研究设计与样本
- 系统综述与诊断准确性荟萃分析,检索核心数据库,纳入基于内镜成像的CAD算法诊断研究。
- 系统综述纳入21项研究,诊断准确性荟萃分析纳入19项研究。
主要发现
- 图像分析中CAD诊断食管癌或肿瘤的汇总AUC为0.97(95%CI 0.95-0.99),灵敏度0.94(95%CI 0.89-0.96),特异度0.88(95%CI 0.76-0.94),诊断比值比108(95%CI 43-273)。
- CAD诊断食管癌浸润深度的汇总AUC为0.96(95%CI 0.86-0.99),灵敏度0.90(95%CI 0.88-0.92),特异度0.88(95%CI 0.83-0.91),诊断比值比138(95%CI 12-1569)。
- Meta回归显示无 heterogeneity,未检测到发表偏倚。
关键数值与推荐
- CAD诊断食管癌或肿瘤的汇总AUC 0.97,灵敏度0.94,特异度0.88。
- CAD诊断浸润深度的汇总AUC 0.96,灵敏度0.90,特异度0.88。
临床怎么用
- CAD算法有望辅助内镜医师提高食管癌及肿瘤的诊断准确性,但需进一步外部验证和临床落地。
局限性
- 缺乏外部验证和临床应用性能数据。
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)。
原文
BACKGROUND AND AIMS: Diagnosis of esophageal cancer or precursor lesions by endoscopic imaging depends on endoscopist expertise and is inevitably subject to interobserver variability. Studies on computer-aided diagnosis (CAD) using deep learning or machine learning are on the increase. However, studies with small sample sizes are limited by inadequate statistical strength. Here, we used a meta-analysis to evaluate the diagnostic test accuracy (DTA) of CAD algorithms of esophageal cancers or neoplasms using endoscopic images. METHODS: Core databases were searched for studies based on endoscopic imaging using CAD algorithms for the diagnosis of esophageal cancer or neoplasms and presenting data on diagnostic performance, and a systematic review and DTA meta-analysis were performed. RESULTS: Overall, 21 and 19 studies were included in the systematic review and DTA meta-analysis, respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD algorithms for the diagnosis of esophageal cancer or neoplasms in the image-based analysis were 0.97 (95% confidence interval [CI], 0.95-0.99), 0.94 (95% CI, 0.89-0.96), 0.88 (95% CI, 0.76-0.94), and 108 (95% CI, 43-273), respectively. Meta-regression showed no heterogeneity, and no publication bias was detected. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD algorithms for the diagnosis of esophageal cancer invasion depth were 0.96 (95% CI, 0.86-0.99), 0.90 (95% CI, 0.88-0.92), 0.88 (95% CI, 0.83-0.91), and 138 (95% CI, 12-1569), respectively. CONCLUSIONS: CAD algorithms showed high accuracy for the automatic endoscopic diagnosis of esophageal cancer and neoplasms. The limitation of a lack in performance in external validation and clinical applications should be overcome.
引用
- Bang CS, Lee JJ, Baik GH, et al. Computer-aided diagnosis of esophageal cancer and neoplasms in endoscopic images: a systematic review and meta-analysis of diagnostic test accuracy. Gastrointest Endosc. 2020. PMID: 33290771. doi:10.1016/j.gie.2020.11.025
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。