卷积神经网络在无线胶囊内镜图像中计算机辅助诊断消化道溃疡和/或出血的汇总性能高:系统评价与Meta分析
该系统评价与Meta分析检索多个数据库至2019年11月,纳入9项研究评估基于卷积神经网络(CNN)的计算机辅助诊断(CAD)在无线胶囊内镜(WCE)图像中诊断消化道溃疡和/或出血的性能。汇总准确率95.4%、灵敏度95.5%、特异度95.8%、阳性预测值95.8%、阴性预测值96.8%,除阳性预测值外异质性可忽略;作者认为CNN-CAD具有高水平的诊断性能,证据质量稳健,有潜力成为优化WCE图像/视频阅片的首选机器学习方法。
要点
- 基于CNN的CAD在WCE图像中诊断消化道溃疡和/或出血的汇总准确率为95.4%、灵敏度为95.5%、特异度为95.8%。
- 汇总阳性预测值为95.8%、阴性预测值为96.8%,除阳性预测值外异质性可忽略。
- 作者认为CNN-CAD有潜力成为优化WCE图像/视频阅片的首选机器学习方法。
核心结论
- 基于该Meta分析,CNN-CAD在WCE图像中诊断消化道溃疡和/或出血达到高水平性能,证据质量稳健,有潜力成为优化WCE图像/视频阅片的首选机器学习方法。
研究设计与样本
- 系统评价与Meta分析,检索多个数据库(从建库至2019年11月),纳入9项报告CNN在WCE图像中诊断消化道溃疡和/或出血性能的研究。
- 采用随机效应模型计算汇总率;当提供多个不同阈值的2×2列联表时,假设各数据表相互独立;采用I²%和95%预测区间评估异质性。
主要发现
- 汇总准确率为95.4%(95%CI 94.3-96.3),灵敏度为95.5%(95%CI 94-96.5),特异度为95.8%(95%CI 94.7-96.6)。
- 汇总阳性预测值为95.8%(95%CI 90.5-98.2),阴性预测值为96.8%(95%CI 94.9-98.1)。
- 除汇总阳性预测值外,I²%异质性可忽略。
局限性
- 原文未报告局限性。
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 GI ulcers and/or hemorrhage by wireless capsule endoscopy (WCE) is limited by the physician-dependent, tedious, time-consuming process of image and/ or video classification. Computer-aided diagnosis (CAD) by convolutional neural network (CNN)-based machine learning may help reduce this burden. Our aim was to conduct a meta-analysis and appraise the reported data. METHODS: Multiple databases were searched (from inception to November 2019), and studies that reported on the performance of CNN in the diagnosis of GI ulcerations and/or hemorrhage on WCE were selected. A random-effects model was used to calculate the pooled rates. In cases where multiple 2 × 2 contingency tables were provided for different thresholds, we assumed the data tables were independent from each other. Heterogeneity was assessed by I2% and 95% prediction intervals. RESULTS: Nine studies were included in our final analysis that evaluated the performance of CNN-based CAD of GI ulcers and/or hemorrhage by WCE. The pooled accuracy was 95.4% (95% confidence interval [CI], 94.3-96.3), sensitivity was 95.5% (95% CI, 94-96.5), specificity was 95.8% (95% CI, 94.7-96.6), positive predictive value was 95.8% (95% CI, 90.5-98.2), and negative predictive value was 96.8% (95% CI, 94.9-98.1). I2% heterogeneity was negligible except for the pooled positive predictive value. CONCLUSIONS: Based on our meta-analysis, CNN-based CAD of GI ulcerations and/or hemorrhage on WCE achieves a high-level performance. The quality of the evidence is robust, and therefore CNN-based CAD has the potential to become the first choice of machine learning to optimize WCE image/video reading.
引用
- Mohan BP, Khan SR, Kassab LL, et al. High pooled performance of convolutional neural networks in computer-aided diagnosis of GI ulcers and/or hemorrhage on wireless capsule endoscopy images: a systematic review and meta-analysis. Gastrointest Endosc. 2020. PMID: 32721487. doi:10.1016/j.gie.2020.07.038
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。