神经网络模型诊断胃肠道早癌价值的Meta分析-东南大学学报医学版

神经网络模型诊断胃肠道早癌价值的Meta分析

单位：南京中医药大学附属医院消化内镜中心, 江苏南京 210029

分类号：R735

出版年·卷·期（页码）：2020·39·第六期（721-729）

摘要：

目的：系统评价神经网络模型诊断胃肠道早癌的价值。方法：计算机检索PubMed、EMbase、Web of Science、the Cochrane Library以及知网、万方、维普等数据库，搜集神经网络模型诊断胃肠道早癌的诊断性研究，检索时限为2010年1月至2019年10月。2名研究者按纳入与排除标准独立筛选文献、提取资料、运用QUADAS-2工具评价纳入研究的偏倚风险后，采用META-DISC 1.4和STATA 15.0软件进行Meta分析，计算合并敏感度、特异度、阳性似然比、阴性似然比、诊断比值比，绘制总受试者工作特征曲线并计算曲线下面积。结果：最终纳入了21篇文献的25个研究，包括13 711张图像。Meta分析结果显示，神经网络模型诊断胃肠道早癌的合并敏感度为0.95（95%CI为0.94~0.95），合并特异度为0.90（95%CI为0.89~0.90），合并阳性似然比为7.00（95%CI为2.98~16.42），合并阴性似然比为0.09（95%CI为0.05~0.17），合并诊断比值比为78.23（95%CI为33.71~181.52）。总受试者工作特征曲线下面积为0.97。结论：神经网络模型对胃肠道早癌的诊断具有明确价值，值得进一步研究及推广。

Objective: To systematically evaluate the performance of neural network models in the diagnosis of early gastrointestinal cancer. Methods: Studies on the diagnosis of early gastrointestinal cancer using neural network models published between January 2010 and October 2019 were acquired from databases such as PubMed, EMbase, Web of Science, the Cochrane Library, CNKI, WanFang Data and VIP. Two researchers independently screened the studies, extracted data, and assessed the risk of bias for incorporating each study using the QUADAS-2 tool. Meta-analysis was then performed with META-DISC 1.4 and STATA 15.0. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and the diagnostic odds ratio were calculated, and the summary receiver operating characteristic curve was plotted and the area under the curve was calculated. Results: A total of 25 studies from 21 articles were selected, featuring 13,711 images. The results of Meta-analysis showed that, the pooled sensitivity was 0.95(95%CI:0.94-0.95), the pooled specificity was 0.90(95%CI:0.89-0.90), the pooled positive likelihood ratio was 7.00(95%CI:2.98-16.42), the pooled negative likelihood ratio was 0.09(95%CI:0.05-0.17), the pooled diagnosis odds ratio was 78.23(95%CI:33.71-181.52), and the area under the summary receiver operating characteristic curve was 0.97. Conclusion: Neural network models have significant value in the diagnosis of early gastrointestinal cancer and are worth further studying and popularizing.

参考文献：

[1] BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018:Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].CA Cancer J Clin, 2018, 68(6):394-424.
[2] KATAI H, ISHIKAWA T, AKAZAWA K, et al. Five-year survival analysis of surgically resected gastric cancer cases in Japan:a retrospective analysis of more than 100,000 patients from the nationwide registry of the Japanese Gastric Cancer Association(2001-2007)[J].Gastric Cancer, 2018, 21(1):144-154.
[3] SUMIYAMA K. Past and current trends in endoscopic diagnosis for early stage gastric cancer in Japan[J].Gastric Cancer, 2017, 20(1):20-27.
[4] MIN J K, KWAK M S, CHA J M. Overview of deep learning in gastrointestinal endoscopy[J].Gut Liver, 2019, 13(4):388-393.
[5] 王智杰, 高杰, 孟茜茜,等.基于深度学习的人工智能技术在早期胃癌诊断中的应用[J].中华消化内镜杂志, 2018, 35(8):551-556.
[6] HIRASAWA T, AOYAMA K, TANIMOTO T, et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images[J].Gastric Cancer, 2018, 21(4):653-660.
[7] CHO B J, SEOK B C, WOO P S, et al. Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network[J]. Endoscopy, 2019, 51(12):1121-1129.
[8] WU L, ZHOU W, WAN X, et al. A deep neural network improves endoscopic detection of early gastric cancer without blind spots[J].Endoscopy, 2019, 51(6):522-531.
[9] SAKAI Y, TAKIMOTO S, HORI K, et al. Automatic detection of early gastric cancer in endoscopic images using a transferring convolutional neural network[J].Annu Int Conf IEEE Eng Med Biol Soc, 2018(2018):4138-4141.
[10] HORIUCHI Y, AOYAMA K, TOKAI Y, et al. Convolutional neural network for differentiating gastric cancer from gastritis using magnified endoscopy with narrow band imaging[J]. Dig Dis Sci, 2019(65):1355-1363.
[11] LI L,CHEN Y, SHEN Z, et al. Convolutional neural network for the diagnosis of early gastric cancer based on magnifying narrow band imaging[J].Gastric Cancer, 2019, 23(1):126-132.
[12] YOON H J, KIM S H, KIM J K, et al. A lesion-based convolutional neural network improves endoscopic detection and depth prediction of early gastric cancer[J]. J Clin Med, 2019, 8(9):1310.
[13] 蔡世伦, 阿依木克地斯·亚力孔, 李染,等.基于深度学习的人工智能辅助诊断在食管早癌中的应用[J].中华消化内镜杂志, 2019, 36(4):246-250.
[14] HORIE Y,YOSHIO T, AOYAMA K, et al. The diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks[J].Gastrointestinal Endoscopy, 2018(89):25-32.
[15] KUMAGAI Y, TAKUBO K, KAWADA K, et al. Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus[J].Esophagus, 2019, 16(2):180-187.
[16] GHATWARY N, ZOLGHARNI M, YE X J. Early esophageal adenocarcinoma detection using deep learning methods[J]. Int J Comput Assist Radiol Surg, 2019, 14(4):611-621.
[17] CAI S L,LI B, TAN W M, et al. Using deep learning system in endoscopy for screening of early esophageal squamous cell carcinoma(with video)[J].Gastrointestinal Endoscopy, 2019, 90(5):745-753.e2.
[18] OHMORI M, ISHIHARA R, AOYAMA K, et al. Endoscopic detection and differentiation of esophageal lesions using a deep neural network[J].Gastrointestinal Endoscopy, 2019, 91(2):301-309.e1.
[19] GUO L, XIAO X, WU C, et al. Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos)[J].Gastrointestinal Endoscopy, 2020, 91(1):41-51.
[20] SWAGER A F, VAN DER SOMMEN F, KLOMP S R, et al. Computer-aided detection of early Barrett's neoplasia using volumetric laser endomicroscopy[J].Gastrointestinal Endoscopy, 2017, 86(5):839-846.
[21] CHEN P J, LIN M C, LAI M J, et al. Accurate classification of diminutive colorectal polyps using computer-aided analysis[J].Gastroenterology, 2018, 154(3):568-575.
[22] KUDO S E, MASASHI M, YUICHI M, et al. Artificial intelligence-assisted system improves endoscopic identification of colorectal neoplasms[J].Clin Gastroenterol Hepatol, 2019, 18(8):1874-1881.e2.
[23] BYRNE M F, NICOLAS C, FLORIAN S, et al. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model[J].Gut, 2017, 68(1):94-100.
[24] KOMEDA Y, HISASHI H, TOMOHIRO W, et al. Computer-aided diagnosis based on convolutional neural network system for colorectal polyp classification:preliminary experience[J].Oncology, 2017, 93(Suppl 1):30-34.
[25] RENNER J, PHLIPSEN H, HALLER B, et al. Optical classification of neoplastic colorectal polyps-a computer-assisted approach(the COACH study)[J].Scand J Gastroenterol, 2018, 53(9):1100-1106.
[26] TING D S W, CHEUNG C Y, LIM G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes[J].JAMA, 2017, 318(22):2211-2223.
[27] ALAGAPPAN M, BROWN J R G, MORI Y, et al. Artificial intelligence in gastrointestinal endoscopy:the future is almost here[J].World J Gastrointest Endosc, 2018, 10(10):239-249.
[28] PABLO M, PIZARRO D, ABERGEL A, et al. Computer-aided classification of gastrointestinal lesions in regular colonoscopy[J].IEEE Trans Med Imaging, 2016, 35(9):2051-2063.
[29] FONS VAN DER S, BISSCHOPS R, CURVERS W L, et al. Computer-aided detection of early neoplastic lesions in Barrett's esophagus[J].Endoscopy, 2016, 48(7):617-624.
[30] TAKASHI K, LEE T C, UEDO N, et al. Computer-aided diagnosis for identifying and delineating early gastric cancers in magnifying narrow-band imaging[J].Gastrointestinal Endoscopy, 2018, 87(5):1339-1344.
[31] YOUNGHAK S,BALASINGHAM I. Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification[J].Annu Int Conf IEEE Eng Med Biol Soc, 2017(2017):3277-3280.
[32] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J].Med Image Anal, 2017(42):60-88.
[33] GUYATT G H, OXMAN A D, MONTORI V,等.GRADE指南:Ⅴ.证据质量评价——发表偏倚[J].中国循证医学杂志, 2011, 11(12):1430-1434.
[34] TRACMANN R, SCHUETZ G, HAMM B, et al. Quality of the reporting of diagnostic accuracy studies:STARD(Standards for the Reporting of Diagnostic accuracy studies)[J].RoFo,2010, 182(8):655-659.
[35] 王智杰, 高杰, 孟茜茜,等.基于深度学习的人工智能技术在早期胃癌诊断中的应用[J].中华消化内镜杂志, 2018, 35(8):551-556.
[36] 赵胜兵, 钱维, 柏愚,等.人工智能在消化内镜诊疗领域的应用研究进展[J].中华消化内镜杂志, 2019, 36(4):293-296.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录