Department of Thoracic Surgery, Chongqing General Hospital, No.118, Xingguang Avenue, Liangjiang New Area, Chongqing, China.
Department of Radiology, Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing Key Laboratory of Pediatrics, Chongqing, China.
Saudi J Gastroenterol. 2022 Sep-Oct;28(5):332-340. doi: 10.4103/sjg.sjg_178_22.
Early screening and treatment of esophageal cancer (EC) is particularly important for the survival and prognosis of patients. However, early EC is difficult to diagnose by a routine endoscopic examination. Therefore, convolutional neural network (CNN)-based artificial intelligence (AI) has become a very promising method in the diagnosis of early EC using endoscopic images. The aim of this study was to evaluate the diagnostic performance of CNN-based AI for detecting early EC based on endoscopic images.
A comprehensive search was performed to identify relevant English articles concerning CNN-based AI in the diagnosis of early EC based on endoscopic images (from the date of database establishment to April 2022). The pooled sensitivity (SEN), pooled specificity (SPE), positive likelihood ratio (LR+), negative likelihood ratio (LR-), diagnostic odds ratio (DOR) with 95% confidence interval (CI), summary receiver operating characteristic (SROC) curve, and area under the curve (AUC) for the accuracy of CNN-based AI in the diagnosis of early EC based on endoscopic images were calculated. We used the I test to assess heterogeneity and investigated the source of heterogeneity by performing meta-regression analysis. Publication bias was assessed using Deeks' funnel plot asymmetry test.
Seven studies met the eligibility criteria. The SEN and SPE were 0.90 (95% confidence interval [CI]: 0.82-0.94) and 0.91 (95% CI: 0.79-0.96), respectively. The LR+ of the malignant ultrasonic features was 9.8 (95% CI: 3.8-24.8) and the LR- was 0.11 (95% CI: 0.06-0.21), revealing that CNN-based AI exhibited an excellent ability to confirm or exclude early EC on endoscopic images. Additionally, SROC curves showed that the AUC of the CNN-based AI in the diagnosis of early EC based on endoscopic images was 0.95 (95% CI: 0.93-0.97), demonstrating that CNN-based AI has good diagnostic value for early EC based on endoscopic images.
Based on our meta-analysis, CNN-based AI is an excellent diagnostic tool with high sensitivity, specificity, and AUC in the diagnosis of early EC based on endoscopic images.
早期筛查和治疗食管癌（EC）对患者的生存和预后尤为重要。然而，常规内镜检查对早期 EC 诊断困难。因此，基于卷积神经网络（CNN）的人工智能（AI）已成为内镜图像诊断早期 EC 的一种很有前途的方法。本研究旨在评估基于内镜图像的 CNN 人工智能诊断早期 EC 的诊断性能。
从数据库建立日期到 2022 年 4 月，全面检索有关基于内镜图像的 CNN 人工智能诊断早期 EC 的英文文献。计算基于内镜图像的 CNN 人工智能诊断早期 EC 的汇总敏感度（SEN）、汇总特异度（SPE）、阳性似然比（LR+）、阴性似然比（LR-）、诊断比值比（DOR）及其 95%置信区间（CI）、汇总受试者工作特征（SROC）曲线和曲线下面积（AUC）。采用 I 检验评估异质性，并通过进行 meta 回归分析来探究异质性来源。采用 Deeks 漏斗图不对称检验评估发表偏倚。
符合纳入标准的研究有 7 项。SEN 和 SPE 分别为 0.90（95%CI：0.82-0.94）和 0.91（95%CI：0.79-0.96）。恶性超声特征的 LR+为 9.8（95%CI：3.8-24.8），LR-为 0.11（95%CI：0.06-0.21），提示基于 CNN 的 AI 在内镜图像上对早期 EC 的确认或排除具有出色的能力。此外，SROC 曲线显示，基于内镜图像的 CNN 人工智能在早期 EC 诊断中的 AUC 为 0.95（95%CI：0.93-0.97），表明基于 CNN 的 AI 对早期 EC 具有良好的诊断价值。
基于我们的荟萃分析，基于 CNN 的 AI 是一种出色的诊断工具，在基于内镜图像的早期 EC 诊断中具有较高的敏感度、特异度和 AUC。
