Department of Internal Medicine, Hallym University College of Medicine, Chuncheon, Korea; Institute for Liver and Digestive Diseases, Hallym University, Chuncheon, Korea; Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon, Korea; Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon, Korea.
Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon, Korea; Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon, Korea; Department of Anesthesiology and Pain Medicine, Hallym University College of Medicine, Chuncheon, Korea.
Gastrointest Endosc. 2021 May;93(5):1006-1015.e13. doi: 10.1016/j.gie.2020.11.025. Epub 2020 Dec 5.
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.
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.
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.
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.
通过内镜成像诊断食管癌或癌前病变取决于内镜医师的专业知识，且不可避免地受到观察者间变异性的影响。基于深度学习或机器学习的计算机辅助诊断（CAD）研究越来越多。然而，小样本量的研究受到统计效力不足的限制。在此，我们使用荟萃分析评估了基于内镜图像的 CAD 算法诊断食管癌或肿瘤的诊断测试准确性（DTA）。
根据基于 CAD 算法的内镜图像诊断食管癌或肿瘤的研究，检索核心数据库，并提供诊断性能数据，进行系统评价和 DTA 荟萃分析。
系统评价和 DTA 荟萃分析分别纳入了 21 项和 19 项研究。CAD 算法对基于图像的食管癌或肿瘤诊断的汇总曲线下面积、敏感度、特异度和诊断比值比分别为 0.97（95%可信区间[CI]，0.95-0.99）、0.94（95% CI，0.89-0.96）、0.88（95% CI，0.76-0.94）和 108（95% CI，43-273）。Meta 回归显示无异质性，未检测到发表偏倚。CAD 算法对食管癌浸润深度诊断的汇总曲线下面积、敏感度、特异度和诊断比值比分别为 0.96（95% CI，0.86-0.99）、0.90（95% CI，0.88-0.92）、0.88（95% CI，0.83-0.91）和 138（95% CI，12-1569）。
CAD 算法对自动内镜诊断食管癌和肿瘤具有较高的准确性。应克服外部验证和临床应用性能不足的局限性。
