Convolution neural network for the diagnosis of wireless capsule endoscopy: a systematic review and meta-analysis.
Convolution neural network for the diagnosis of wireless capsule endoscopy: a systematic review and meta-analysis.
复制标题
用于无线胶囊内窥镜诊断的卷积神经网络：系统评价和荟萃分析
DOI：
10.1007/s00464-021-08689-3
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Li Q
中科院分区：
文献类型：
--
作者：
Qin K;Li J;Fang Y;Xu Y;Wu J;Zhang H;Li H;Liu S;Li Q
背景无线胶囊内窥镜（WCE）被认为是诊断肠道疾病的有力仪器。卷积神经网络 (CNN) 是一种人工智能，有潜力辅助 WCE 图像的检测。我们的目的是对当前 CNN 在 WCE 中应用的研究进展进行系统回顾。方法通过在 PubMed、SinoMed 和 Web of Science 中进行检索，收集所有有关 CNN 在 WCE 中实现的原始出版物。偏倚风险的评估是通过诊断准确性研究质量评估-2风险列表进行的。通过双变量混合效应回归模型的精确二项式计算来计算汇总敏感性和特异性。I2用于评估异质性。结果纳入了23项独立研究的16篇文章。 CNN在WCE中的应用分为糜烂/溃疡、胃肠道出血（GI出血）和息肉/癌症的检测。 CNN 对糜烂/溃疡的汇总敏感性为 0.96 [95% CI 0.91, 0.98]，对胃肠道出血的敏感性为 0.97 (95% CI 0.93–0.99)，对息肉/癌症的敏感性为 0.97 (95% CI 0.82–0.99)。 CNN 对糜烂/溃疡的相应特异性为 0.97 (95% CI 0.93–0.99)，对胃肠道出血的相应特异性为 1.00 (95% CI 0.99–1.00)，对息肉/癌症的相应特异性为 0.98 (95% CI 0.92–0.99)。息肉/癌症由于其高敏感性和特异性而达到了高水平的性能。因此，从未来的角度来看，CNN有潜力成为WCE诊断的重要助手。
BackgroundWireless capsule endoscopy (WCE) is considered to be a powerful instrument for the diagnosis of intestine diseases. Convolution neural network (CNN) is a type of artificial intelligence that has the potential to assist the detection of WCE images. We aimed to perform a systematic review of the current research progress to the CNN application in WCE.MethodsA search in PubMed, SinoMed, and Web of Science was conducted to collect all original publications about CNN implementation in WCE. Assessment of the risk of bias was performed by Quality Assessment of Diagnostic Accuracy Studies-2 risk list. Pooled sensitivity and specificity were calculated by an exact binominal rendition of the bivariate mixed-effects regression model.I2was used for the evaluation of heterogeneity.Results16 articles with 23 independent studies were included. CNN application to WCE was divided into detection on erosion/ulcer, gastrointestinal bleeding (GI bleeding), and polyps/cancer. The pooled sensitivity of CNN for erosion/ulcer is 0.96 [95% CI 0.91, 0.98], for GI bleeding is 0.97 (95% CI 0.93–0.99), and for polyps/cancer is 0.97 (95% CI 0.82–0.99). The corresponding specificity of CNN for erosion/ulcer is 0.97 (95% CI 0.93–0.99), for GI bleeding is 1.00 (95% CI 0.99–1.00), and for polyps/cancer is 0.98 (95% CI 0.92–0.99).ConclusionBased on our meta-analysis, CNN-dependent diagnosis of erosion/ulcer, GI bleeding, and polyps/cancer approached a high-level performance because of its high sensitivity and specificity. Therefore, future perspective, CNN has the potential to become an important assistant for the diagnosis of WCE.
登录
查看更多内容
影响因子：
29.4
作者：
Enns, Robert A.;Hookey, Lawrence;Sadowski, Daniel
通讯作者：
Sadowski, Daniel
影响因子：
7.7
作者：
Aoki, Tomonori;Yamada, Atsuo;Tada, Tomohiro
通讯作者：
Tada, Tomohiro
影响因子：
4.1
作者：
Aoki, Tomonori;Yamada, Atsuo;Tada, Tomohiro
通讯作者：
Tada, Tomohiro
影响因子：
64.8
作者：
Iddan, G;Meron, G;Swain, P
通讯作者：
Swain, P
DOI：
10.1016/j.compmedimag.2020.101852
发表时间：
2021-01-23
影响因子：
5.7
作者：
Caroppo, Andrea;Leone, Alessandro;Siciliano, Pietro
通讯作者：
Siciliano, Pietro