Performance of artificial intelligence for colonoscopy regarding adenoma and polyp detection: a meta-analysis.,Gastrointestinal Endoscopy

当前位置： X-MOL 学术 › Gastrointest. Endosc. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Performance of artificial intelligence for colonoscopy regarding adenoma and polyp detection: a meta-analysis.
Gastrointestinal Endoscopy ( IF 6.7 ) Pub Date : 2020-06-26 , DOI: 10.1016/j.gie.2020.06.059
Cesare Hassan ₁ , Marco Spadaccini ₂ , Andrea Iannone ₃ , Roberta Maselli ₄ , Manol Jovani ₅ , Viveksandeep Thoguluva Chandrasekar ₆ , Giulio Antonelli ₁ , Honggang Yu ₇ , Miguel Areia ₈ , Mario Dinis-Ribeiro ₉ , Pradeep Bhandari ₁₀ , Prateek Sharma ₆ , Douglas K Rex ₁₁ , Thomas Rösch ₁₂ , Michael Wallace ₁₃ , Alessandro Repici ₂

Affiliation

Digestive Endoscopy Unit, Nuovo Regina Margherita Hospital, Rome, Italy.
Endoscopy Unit, Humanitas Clinical and Research Center-IRCCS, Rozzano, Italy; Department of Biomedical Sciences, Humanitas University, Rozzano, Italy.
Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of Bari, Bari, Italy.
Endoscopy Unit, Humanitas Clinical and Research Center-IRCCS, Rozzano, Italy.
Division of Gastroenterology and Hepatology, Johns Hopkins Hospital, Baltimore, Maryland, USA; Division of Gastroenterology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Gastroenterology and Hepatology, Kansas City VA Medical Center, Kansas City, Missouri, USA.
Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China.
Department of Gastroenterology, Portuguese Oncology Institute of Coimbra, Coimbra, Portugal.
MEDCIDS-Department of Community Medicine, Information and Decision in Health, Faculty of Porto, University of Medicine, Porto, Portugal.
Department of Gastroenterology, Queen Alexandra Hospital, Portsmouth, UK.
Division of Gastroenterology/Hepatology, Indiana University School of Medicine, Indianapolis, Indiana, USA.
Department of Interdisciplinary Endoscopy, University Hospital Hamburg-Eppendorf, Hamburg, Germany.
Department of Gastroenterology, Mayo Clinic, Jacksonville, Florida, USA.

Background and Aims

One-fourth of colorectal neoplasia are missed at screening colonoscopy, representing the main cause of interval colorectal cancer. Deep learning systems with real-time computer-aided polyp detection (CADe) showed high accuracy in artificial settings, and preliminary randomized controlled trials (RCTs) reported favorable outcomes in the clinical setting. The aim of this meta-analysis was to summarize available RCTs on the performance of CADe systems in colorectal neoplasia detection.

Methods

We searched MEDLINE, EMBASE, and Cochrane Central databases until March 2020 for RCTs reporting diagnostic accuracy of CADe systems in the detection of colorectal neoplasia. The primary outcome was pooled adenoma detection rate (ADR), and secondary outcomes were adenoma per colonoscopy (APC) according to size, morphology, and location; advanced APC; polyp detection rate; polyps per colonoscopy; and sessile serrated lesions per colonoscopy. We calculated risk ratios (RRs), performed subgroup and sensitivity analyses, and assessed heterogeneity and publication bias.

Results

Overall, 5 randomized controlled trials (4354 patients) were included in the final analysis. Pooled ADR was significantly higher in the CADe group than in the control group (791/2163 [36.6%] vs 558/2191 [25.2%]; RR, 1.44; 95% confidence interval [CI], 1.27-1.62; P < .01; I² = 42%). APC was also higher in the CADe group compared with control (1249/2163 [.58] vs 779/2191 [.36]; RR, 1.70; 95% CI, 1.53-1.89; P < .01; I² = 33%). APC was higher for ≤5-mm (RR, 1.69; 95% CI, 1.48-1.84), 6- to 9-mm (RR, 1.44; 95% CI, 1.19-1.75), and ≥10-mm adenomas (RR, 1.46; 95% CI, 1.04-2.06) and for proximal (RR, 1.59; 95% CI, 1.34-1.88), distal (RR, 1.68; 95% CI, 1.50-1.88), flat (RR, 1.78; 95% CI, 1.47-2.15), and polypoid morphology (RR, 1.54; 95% CI, 1.40-1.68). Regarding histology, CADe resulted in a higher sessile serrated lesion per colonoscopy (RR, 1.52; 95% CI, 1.14-2.02), whereas a nonsignificant trend for advanced ADR was found (RR, 1.35; 95% CI, .74-2.47; P = .33; I² = 69%). Level of evidence for RCTs was graded as moderate.

Conclusions

According to available evidence, the incorporation of artificial intelligence as aid for detection of colorectal neoplasia results in a significant increase in the detection of colorectal neoplasia, and such effect is independent from main adenoma characteristics.

中文翻译：

结肠镜检查中有关腺瘤和息肉检测的人工智能性能：一项荟萃分析。

背景和目标

结肠镜筛查漏检了四分之一的大肠肿瘤，这代表间隔性大肠癌的主要原因。具有实时计算机辅助息肉检测（CADe）的深度学习系统在人工环境中显示出很高的准确性，而初步的随机对照试验（RCT）报告了在临床环境中的良好结果。这项荟萃分析的目的是总结有关CADe系统在结直肠肿瘤形成检测中的性能的可用RCT。

方法

我们搜索了MEDLINE，EMBASE和Cochrane Central数据库，直到2020年3月为止，这些RCT报告了CADe系统在检测结直肠肿瘤中的诊断准确性。主要结局是合并的腺瘤检出率（ADR），次要结局是根据大小，形态和位置，每个结肠镜检查腺瘤（APC）。先进的APC; 息肉检出率；结肠镜检查息肉; 结肠镜检查检查无创锯齿状病变。我们计算了风险比（RRs），进行了亚组和敏感性分析，并评估了异质性和发表偏倚。

结果

总体而言，最终分析包括5项随机对照试验（4354例患者）。CADe组的合并ADR显着高于对照组（791/2163 [36.6％]与558/2191 [25.2％]； RR，1.44； 95％置信区间[CI]，1.27-1.62；P <。 01；我² = 42％）。CADe组的APC也高于对照组（1249/2163 [.58] vs 779/2191 [.36]; RR，1.70; 95％CI，1.53-1.89; P <.01; I ² = 33％）。≤5-mm（RR，1.69; 95％CI，1.48-1.84），6至9mm（RR，1.44; 95％CI，1.19-1.75）和≥10mm腺瘤（RR）的APC更高，1.46; 95％CI，1.04-2.06）和近端（RR，1.59; 95％CI，1.34-1.88），远端（RR，1.68; 95％CI，1.50-1.88），扁平（RR，1.78; 95 ％CI，1.47-2.15）和息肉状形态（RR，1.54； 95％CI，1.40-1.68）。就组织学而言，CADe每次结肠镜检查可导致更高的无柄锯齿状病变（RR，1.52； 95％CI，1.14-2.02），而晚期ADR的趋势则无统计学意义（RR，1.35； 95％CI，.74-2.47；P = 0.33； I ² = 69％）。RCT的证据等级为中等。