[1]侯军军,张喜梅,陈松,等.基于深度学习的视网膜毛细血管无灌注区智能识别定量分析系统在CRVO缺血分型诊断中的应用[J].眼科新进展,2022,42(6):465-468.[doi:10.13389/j.cnki.rao.2022.0095]
　HOU Junjun,ZHANG Ximei,CHEN Song,et al.Application of intelligent recognition and quantitative analysis system based on deep learning for retinal capillary non-perfusion area in ischemic typing of central retinal vein occlusion[J].Recent Advances in Ophthalmology,2022,42(6):465-468.[doi:10.13389/j.cnki.rao.2022.0095]
点击复制

基于深度学习的视网膜毛细血管无灌注区智能识别定量分析系统在CRVO缺血分型诊断中的应用/HTML
分享到：

《眼科新进展》[ISSN:1003-5141/CN:41-1105/R]

卷:
42卷
期数:
2022年6期
页码:
465-468
栏目:
应用研究
出版日期:
2022-06-05

文章信息/Info

Title:
Application of intelligent recognition and quantitative analysis system based on deep learning for retinal capillary non-perfusion area in ischemic typing of central retinal vein occlusion
作者:
侯军军; 张喜梅; 陈松; 孙斌; 张光华; 谢娟; 马非; 刘汉
300020　天津市，天津医科大学眼科临床学院，天津市眼科医院，天津市眼科研究所(侯军军，陈松)；030002　山西省太原市，山西省眼科医院（侯军军，张喜梅，孙斌，谢娟）；030000　山西省太原市，山西智能大数据产业技术创新研究院（张光华，马非，刘汉）；030000 山西省太原市，太原学院智能与自动化系（张光华）
Author(s):
HOU Junjun1; 2; ZHANG Ximei2; CHEN Song1; SUN Bin2; ZHANG Guanghua3; 4; XIE Juan2; MA Fei3; LIU Han3
1.Clinical College of Ophthalmology of Tianjin Medical University,Tianjin Eye Hospital,Tianjin Institute of Ophthalmology,Tianjin 300020,China
2.Shanxi Eye Hospital,Taiyuan 030002,Shanxi Province,China
3.Shanxi Intelligence Institute of Big Dat
关键词:
视网膜静脉阻塞; 荧光素血管造影术; 智能辅助诊断技术
Keywords:
retinal vein occlusion;  fundus fluorescein angiography;  intelligent computer-aided diagnosis
分类号:
R774
DOI:
10.13389/j.cnki.rao.2022.0095
文献标志码:
A
摘要:
目的　探讨一种基于深度学习的视网膜毛细血管无灌注区（NPA）智能识别定量分析系统在视网膜中央静脉阻塞（CRVO）缺血分型诊断中的应用价值。方法　回顾性病例系列研究。选取2017年1月至2018年12月经山西省眼科医院门诊确诊为CRVO并行荧光素眼底血管造影（FFA）检查的343例343眼患者纳入本研究。随访并记录患者自发病起1年内是否发生新生血管并发症。应用人工智能诊断系统计算CRVO患者后极部55°视野范围NPA面积，受试者工作特征曲线（ROC）分析该NPA面积对CRVO发生新生血管并发症的诊断价值。结果　343例CRVO患眼中有26眼发生了新生血管并发症，发病率7.58%。依据NPA面积判断CRVO患者是否发生新生血管并发症的曲线下面积为0.889（95%CI：0.799~0.978，P<0.001）。最佳截断值为20.997视盘面积（DA），灵敏度为0.808，26眼新生血管并发症患者中有21眼NPA值大于该值；特异度为0.946，317眼无并发症患者中有300眼NPA值小于该值。结论　基于深度学习的NPA智能识别定量分析系统可为CRVO分型诊断提供决策依据。55°视野范围后极部NPA>20 DA可作为CRVO缺血分型的阈值标准。
Abstract:
Objective　To explore the application value of an intelligent recognition and quantitative analysis system based on deep learning for the retinal capillary non-perfusion area (NPA) in ischemic typing of central retinal vein occlusion (CRVO). Methods　A total of 343 patients (343 eyes) who were diagnosed with CRVO and underwent fundus fluorescein angiography (FFA) in the outpatient department of Shanxi Eye Hospital from January 2017 to December 2018 were included in this retrospective case series study. All these patients were followed up for neovascularization complications within one year from the onset of the disease. The artificial intelligence-based diagnostic system was used to calculate the NPA area at 55° in the posterior pole of CRVO patients. The receiver operating characteristic (ROC) curve was used to evaluate the diagnostic value of the NPA area on the neovascularization complications in CRVO patients. Results　Neovascularization complications occurred in 26 eyes (7.58%) of 343 CRVO patients. The area under the curve for determining whether CRVO patients developed neovascularization complications based on the NPA area was 0.889 (95%CI: 0.799-0.978, P<0.001). The best cutoff value was 20.997 disk area (DA), the sensitivity was 0.808, and 21 of 26 eyes with neovascularization complications had the NPA area greater than this value. The specificity was 0.946, and 300 of 317 eyes without neovascularization complications had the NPA area less than this value. Conclusion　The NPA intelligent recognition and quantitative analysis system based on deep learning can provide a decision-making basis for CRVO typing diagnosis. NPA>20 DA at 55° in the posterior pole can be used as the threshold for CRVO ischemia typing.

参考文献/References:

［1］　EHLERS J P,FEKRAT S.Retinal vein occlusion:beyond the acute event［J］.Surv Ophthalmol,2011,56(4):281-299.
［2］　LI C,WANG R,LIU G,GE Z,JIN D,MA Y,et al.Efficacy of panretinal laser in ischemic central retinal vein occlusion:a systematic review［J］.Exp Ther Med,2019,17(1):901-910.
［3］　TANG Z,ZHANG X,YANG G,ZHANG G,GONG Y,ZHAO K,et al.Automated segmentation of retinal nonperfusion area in fluorescein angiography in retinal vein occlusion using convolutional neural networks［J］.Medical Physics,2021,48(2):648-658.
［4］　侯军军.基于眼底荧光血管造影的视网膜静脉阻塞人工智能分型诊断系统及其应用［D］.天津：天津医科大学,2020.
HOU J J.Artificial intelligence system of typing retinal vein occlusion based on fundus fluorescein angiography and its application［D］.Tianjin:Tianjin Medical University,2020.
［5］　The Central Vein Occlusion Study Group.A randomized clinical trial of early panretinal photocoagulation for ischemic central vein occlusion.The Central Vein Occlusion Study Group N report［J］.Ophthalmology,1995,102(10):1434-1444.
［6］　HAYREH S S,KLUGMAN M R,BERI M,KIMURA A E,PODHAJSKY P.Differentiation of ischemic from non-ischemic central retinal vein occlusion during the early acute phase［J］.Graefes Arch Clin Exp Ophthalmol,1990,228(3):201-217.
［7］　MAGARGAL L E,BROWN G C,AUGSBURGER J J,DONOSO L A.Efficacy of panretinal photocoagulation in preventing neovascular glaucoma following ischemic central retinal vein obstruction［J］.Ophthalmology,1982,89(7):780-784.
［8］　SCHMIDT-ERFURTH U,GARCIA-ARUMI J,GERENDAS B S,MIDENA E,SIVAPRASAD S,TADAYONI R,et al.Guidelines for the management of retinal vein occlusion by the European Society of Retina Specialists (EURETINA) ［J］.Ophthalmologica,2019,242(3):123-162.
［9］　FLAXEL C J,ADELMAN R A,BAILEY S T,FAWZI A,LIM J I,VEMULAKONDA G A,et al.Retinal vein occlusions preferred practice pattern［J］.Ophthalmology,2020,127(2):P288-P320.
［10］　DECROOS F C,TODORICH B,ALSHAREEF R,KHUTHAILA M,FEKRAT S,HO A C,et al.Neovascular events in eyes with central retinal vein occlusion undergoing serial bevacizumab or ranibizumab intravitreal injections:a retrospective review［J］.J Ophthalmic Vis Res,2014,9(4):461-468.
［11］　BROWN D M,WYKOFF C C,WONG T P,MARIANI A F,CROFT D E,SCHUETZLE K L.Ranibizumab in preproliferative (ischemic) central retinal vein occlusion:the rubeosis anti-VEGF (RAVE) trial［J］.Retina,2014,34(9):1728-1735.
［12］　BRADSHAW S E,GALA S,NANAVATY M,SHAH A,MWAMBURI M,KEFALAS P.Systematic literature review of treatments for management of complications of ischemic central retinal vein occlusion［J］.BMC Ophthalmol,2016,16:104.
［13］　HAYREH S S,ROJAS P,PODHAJSKY P,WOOLSON R F.Ocular neovascularization with retinal vascular occlusion-III.Incidence of ocular neovascularization with retinal vein occlusion［J］.Ophthalmology,1983,90(5):488-506.
［14］　NICHOLSON L,VAZQUEZ-ALFAGEME C,PATRAO N V,TRIANTAFYLLOPOLOU I,BAINBRIDGE J W,KYKIN P G,et al.Retinal nonperfusion in the posterior pole is associated with increased risk of neovascularization in central retinal vein occlusion［J］.Am J Ophthalmol,2017,182:118-125.
［15］　KHAYAT M,WILLIAMS M,LOIS N.Ischemic retinal vein occlusion:characterizing the more severe spectrum of retinal vein occlusion［J］.Surv Ophthalmol,2018,63(6):816-850.
［16］　BIROL G,WANG S,BUDZYNSKI E,WANGSA-WIRAWAN N D,LINSENMEIER R A.Oxygen distribution and consumption in the macaque retina［J］.Am J Physiol Heart Circ Physiol,2007,293(3):H1696-H1704.
［17］　FAWZI A A,PAPPURU R R,SARRAF D,LE P P,MCCANNEL C A,SOBRIN L,et al.Acute macular neuroretinopathy:long-term insights revealed by multimodal imaging［J］.Retina,2012,32(8):1500-1513.
［18］　MUQIT M M,SANGHVI C,MCLAUCHLAN R,DELGADO C,YOUNG L B,CHARLES S J,et al.Study of clinical applications and safety for Pascal? laser photocoagulation in retinal vascular disorders［J］.Acta Ophthalmol,2012,90(2):155-161.
［19］　TULTSEVA S N,ASTAKHOW Y S,NOVIKOV S A,NECHIPORENKO P A,LISOCHKINA A B,OVNANYAN A Y,et al.Alternative ways to optimize treatment for retinal vein occlusion with peripheral capillary non-perfusion:a pilot study［J］.Arq Bras Oftalmol,2017,80(4):224-228.

相似文献/References:

[1]王刚.曲安奈德联合氪激光治疗视网膜静脉阻塞的临床疗效观察[J].眼科新进展,2013,33(7):000.
[2]马宇 刘意 郭娟 周利晓.金纳多联合血栓通对视网膜静脉阻塞患者同型半胱氨酸水平的影响[J].眼科新进展,2013,33(9):000.
[3]袁子茗 王帅 宋蓓雯 胡健艳 吴强.维速达尔光动力疗法诱导兔视网膜静脉阻塞的实验研究[J].眼科新进展,2012,32(9):000.
[4]李娟娟 李燕.先天性及获得性视盘血管袢的临床观察[J].眼科新进展,2013,33(11):000.
[5]陆秉文 吴星伟.视网膜静脉阻塞黄斑水肿患者玻璃体内注射ranibi-zumab后视野变化[J].眼科新进展,2013,33(12):000.
[6]金昱,石安娜,刘淼. 玻璃体内注射雷珠单抗（Ranibizumab）治疗视网膜静脉阻塞继发黄斑水肿[J].眼科新进展,2014,34(9):855.[doi:10.13389/j.cnki.rao.2014.0236]
[7]周洁,王宏彬,王文亭.雷珠单抗治疗视网膜静脉阻塞的临床研究[J].眼科新进展,2016,36(1):070.[doi:10.13389/j.cnki.rao.2016.0020]
　ZHOU Jie,WANG Hong-Bin,WANG Wen-Ting.Efficacy of intravitreal injection of ranibizumab for retinal vein occlusion[J].Recent Advances in Ophthalmology,2016,36(6):070.[doi:10.13389/j.cnki.rao.2016.0020]
[8]袁牧之,林颖,刘泉.视网膜静脉阻塞患者血浆和泪液中血管内皮生长因子表达的研究[J].眼科新进展,2016,36(5):468.[doi:10.13389/j.cnki.rao.2016.0125]
　YUAN Mu-Zhi,LIN Ying,LIU Quan.Expression of VEGF in plasma and tears of patients with RVO[J].Recent Advances in Ophthalmology,2016,36(6):468.[doi:10.13389/j.cnki.rao.2016.0125]
[9]王琛,李东豪,闻毅颐.玻璃体内注射康柏西普联合周边视网膜选择性光凝治疗视网膜静脉阻塞继发黄斑水肿的疗效及安全性[J].眼科新进展,2016,36(5):471.[doi:10.13389/j.cnki.rao.2016.0126]
　WANG Chen,LI Dong-Hao,WEN Yi-Yi.Intravitreal injection of conbercept combined with selective peripheral retinal photocoagulation for macular edema secondary to retinal vein occlusion[J].Recent Advances in Ophthalmology,2016,36(6):471.[doi:10.13389/j.cnki.rao.2016.0126]
[10]王琴,周杰,颜学梅,等.急性视网膜色素上皮炎眼底荧光血管造影与频域光相干断层扫描特征观察[J].眼科新进展,2016,36(9):857.[doi:10.13389/j.cnki.rao.2016.0229]
　WANG Qin,ZHOU Jie,YAN Xue-Mei,et al.Characteristics of fluorescein fundus angiograph and spectral- domain optical coherence tomography in acute retinal pigment epithelitis[J].Recent Advances in Ophthalmology,2016,36(6):857.[doi:10.13389/j.cnki.rao.2016.0229]

备注/Memo

备注/Memo:
山西省卫健委科研项目（编号：2018090） ；山西省重点研发项目（编号：201903D311009）； 山西省卫健委“四个一批”工程眼科学山西省重点实验室培育项目（编号：2020SYS12）
更新日期/Last Update: 2022-06-05