[1]朱娟,常花蕾,李进.特发性黄斑裂孔的人工智能诊断研究[J].眼科新进展,2019,39(11):1040-1043.[doi:10.13389/j.cnki.rao.2019.0238]
　ZHU Juan,CHANG Hua-Lei,LI Jin.Artificial intelligence diagnosis of idiopathic macular hole[J].Recent Advances in Ophthalmology,2019,39(11):1040-1043.[doi:10.13389/j.cnki.rao.2019.0238]
点击复制

特发性黄斑裂孔的人工智能诊断研究/HTML
分享到：

《眼科新进展》[ISSN:1003-5141/CN:41-1105/R]

卷:
39卷
期数:
2019年11期
页码:
1040-1043
栏目:
应用研究
出版日期:
2019-11-05

文章信息/Info

Title:
Artificial intelligence diagnosis of idiopathic macular hole
作者:
朱娟; 常花蕾; 李进
710004　陕西省西安市，陕西省眼科中心、西安市第四医院眼科、西安交通大学医学院附属广仁医院眼科（朱娟，常花蕾）；710071　陕西省西安市，西安电子科技大学 综合业务网理论及关键技术国家重点实验室（李进）
Author(s):
ZHU Juan; CHANG Hua-Lei; LI Jin
Shaanxi Ophthalmic Center，Department of Ophthalmology，Xi’an Fourth Hospital，Affiliated Guangren Hospital，School of Medicine，Xi’an Jiaotong University（ZHU Juan，CHANG Hua-Lei），Xi’an 710004，Shaanxi Province，China；State Key Laboratory of Integrate Service Networks，Xi’an Dianzi University （LI Jin），Xi’an 710071，Shaanxi Province，China
关键词:
特发性黄斑裂孔; 光学相干断层扫描; 人工智能诊断; 特征参数
Keywords:
idiopathic macular hole; optical coherence tomography; artificial intelligence diagnosis; feature parameter
分类号:
R774.5
DOI:
10.13389/j.cnki.rao.2019.0238
文献标志码:
A
摘要:
目的　利用计算机图像特征识别和特征参数提取算法实现特发性黄斑裂孔的人工智能诊断。方法　收集2018年5月至8月在西安市第四医院眼科诊断为特发性黄斑裂孔患者48例（48眼）和同期健康志愿者48人（48眼）眼底光学相干断层扫描 （optical coherence tomography，OCT）图像。通过对收集的OCT图像进行人工智能学习，利用图像处理和特征识别判断技术，提取能够区别正常人眼和特发性黄斑裂孔患眼的特征参数，在此基础上得到诊断的初始阈值。对2018年9-12月于西安市第四医院眼科诊断为特发性黄斑裂孔的患者73例（73眼）和正常51人（51眼）的OCT图像进行1~124随机编号后，使用计算机程序逐一进行处理，对处理后图像进行特征参数提取，然后将特征参数和阈值进行比较。结果　经计算得到训练样本中正常人OCT图像特征参数为9，特发性黄斑裂孔患者OCT图像特征参数为23，初始阈值为16。经过计算机智能诊断，124例随机图像中73例OCT特征参数最小值为16.8，最大值为27.5，平均值为23.4，特征参数均大于阈值；51人随机图像OCT特征参数最小值为2.8，最大值为14.7，平均值为8.3，特征参数均小于阈值。经过比对，特征参数大于阈值的73例OCT图像均为特发性黄斑裂孔，特征参数小于阈值的51例OCT图像均为正常人。计算机判断结果与眼科医师判断结果差异无统计学意义（P=0.551）。结论　一种基于特征参数提取和智能门限选取的特发性黄斑裂孔自动诊断算法可达到特发性黄斑裂孔智能诊断的目的，能够很好地应用于临床诊断。
Abstract:
Objective　To diagnosis the idiopathic macular hole though the artificial intelligence (AI) using computer image feature recognition and feature parameter extraction algorithm.Methods　We retrospectively reviewed 48 patients(48 eyes) fundus optical coherence tomography (OCT) images of patients with idiopathic macular hole and 48 images of healthy individuals in Xi’an Fourth Hospital from May 2018 to August 2018.AI learning was performed for the collected OCT images,and image processing and feature recognition technology was applied to extract the feature parameters which could differentiate OCT image of patients with idiopathic macular hole from healthy individuals.On this basis,the initial threshold for diagnosis of was idiopathic macular hole obtained.After randomly numbered fundus OCT images of 73 patients (73 eyes) with idiopathic macular hole and 51 healthy individuals (51 eyes) in Xi’an Fourth Hospital from 1 to 124，and the images was processed by the computer program,and then feature parameters were extracted from the processed images.Finally,we compared the feature parameters with the threshold.Results　The feature parameter of OCT image of the normal individuals in the training samples was 9 and 23 for the patients with idiopathic macular hole,and the initial threshold was 16.After computer intelligent diagnosing,it was shown that the minimum value of the OCT feature parameters of 73 patients in 124 random images was 16.8,the maximum value was 27.5,and the average value was 23.4.All the feature parameters were larger than the threshold.The minimum value of OCT feature parameters of the 51 random images was 2.8,with the maximum value of 14.7,the average value of 8.3,and all the feature parameters were less than the threshold.73 OCT images of feature parameter larger than the threshold were all patients with idiopathic macular hole and 51 OCT images feature parameter smaller than the threshold were all healthy individuals.There was no statistical difference between the computer diagnosis and the ophthalmologist diagnosis (P=0.551).Conclusion　The intelligent diagnosis algorithm based on feature parameter extraction and intelligent threshold selection can help diagnose idiopathic macular hole and can be well applied to clinical diagnosis.

参考文献/References:

［1］　ZHAO J L.The development of ophthalmology in artificial intelligence era［J］.Chin J Ophthalmol，2018，54（9）：645-648.
赵家良.关注人工智能时代的眼科学发展［J］.中华眼科杂志，2018，54（9）：645-648.
［2］　QIN T Y，GAO S S，WANG W Z.Comparison of peripheral retinal degeneration in macular hole caused by high myopia and trauma［J］.Rec Adv Ophthalmol，2017，37（9）：853-855.
秦廷玉，高莎莎，王文战.不同类型黄斑裂孔周边视网膜变性的比较［J］.眼科新进展，2017，37（9）：853-855.
［3］　FU W，FAN F，JIA Z Y.Progress in diagnosis and treatment of idiopathic macular hole［J］.Rec Adv Ophthalmol，2018，38（10）：995-1000.
付维，樊芳，贾志旸.特发性黄斑裂孔诊治进展［J］.眼科新进展，2018，38（10）：995-1000.
［4］　XING Y，GENG H Q，WU J H.Area and volume ratios for prediction of visual outcome in idiopathic macular hole［J］.Int J Ophthalmol，2017，10（8）：1255-1260.
［5］　HUANG S W，ZHANG A，TIAN X L，SUN Y K.Dynamic adaptive weight multi-scale and multi-structure morphological edge detection in anterior chamber OCT images［J］.Key Eng Mater，2012，40（3）：70-75.
［6］　LIU Y Y，ISHI KAWA H，CHEN M，WOLLSTEIN G，DUKER J S.Computerized macular pathology diagnosis in spectral domain optical coherence tomography scans based on multiscale texture and shape features［J］.Invest Ophthalmol Vis Sci，2011，52（11）：8316-8322.
［7］　NIU L J，JIA B Q，ZHANG M S，WU B，LI L，ZHANG N.Automatic recognition of corneal morphologyfrom optical coherence tomography of the rabbit eyes based on morphological denoising［J］.Beijing Bio Med Eng，2017，36（5）：459-464.
牛璐洁，贾博奇，张梦诗，武博，李林，张楠.基于形态学去噪的兔眼相干光断层成像中角膜形态自动识别［J］.北京生物医学工程，2017，36（5）：459-464.
［8］　SHPAK A A，SHKVORCHENKO D O，SHARAFETDINOV I K，YUKHANOVA O A.Predicting anatomical results of surgical treatment of idiopathic macular hole［J］.Int J Ophthalmol，2016，9（2）：253-257.
［9］　CHEN Y，LIU X L，SONG Z X，CHEN L X，LIN J J，WANG J J.Correlation of OCT image with postoperative early visual outcomes among patients with idiopathic macular holes［J］.Rec Adv Ophthalmol，2017，37（3）：275-278.
陈勇，刘向玲，宋子宣，陈立新，蔺静静，王娇娇.特发性黄斑裂孔OCT影像与术后早期视力恢复的相关性研究［J］.眼科新进展，2017，37（3）：275-278.
［10］　ZHANG F，PENG Z W，MENG S J.Improved Canny edge detection method based on self-adoptivethreshold［J］.J Comput Appl，2012，32（8）：2296-2298.
张帆，彭中伟，蒙水金.基于自适应阈值的改进Canny 边缘检测方法［J］.计算机应用，2012，32（8）：2296-2298.
［11］　WANG X J，LIU X M，GUAN Y.Image edge detection algorithm based on improved Canny operator［J］.Comput Eng，2012，38（14）：196-202.
王小俊，刘旭敏，关永.基于改进Canny 算子的图像边缘检测算法［J］.计算机工程，2012，38（14）：196-202.
［12］　REN M H.Comparison and prospect of image edge detection algorithms［J］.Chin Sci Tech Info，2007，19（10）：119-120.
任民宏.图像边缘检测算法的比较与展望［J］.中国科技信息，2007，19（10）：119-120.

相似文献/References:

[1]陈晓 李舒茵 牛超 李建新 陈慷.先天性视网膜劈裂症的影像学观察[J].眼科新进展,2012,32(11):000.
[2]闵红波 刘小红 花雷 韩文龙 储明慧 邵娟英.近视对OCT测量视网膜神经纤维层厚度的影响[J].眼科新进展,2012,32(12):000.
[3]张译心 巩琰 戴艳丽 黄厚斌 魏世辉.特发性脱髓鞘性视神经炎视网膜神经纤维层厚度和黄斑厚度的变化特点[J].眼科新进展,2013,33(2):000.
[4]马兰茗 金喜浓 金丽.光学相干断层扫描测量下方泪河高度诊断2型糖尿病患者眼干燥症的可行性[J].眼科新进展,2013,33(2):000.
[5]李朝晖 崔治华 胡晓英 孟丽珠 张敬维.糖尿病视网膜病变激光面积与疗效的分析[J].眼科新进展,2013,33(2):000.
[6]陈月芹 黄振平 薛春燕 葛轶睿.有晶状体眼虹膜固定型人工晶状体植入术后房角宽度的改变[J].眼科新进展,2013,33(6):000.
[7]杨世琳 杜改萍 郝玉华.频域OCT观察Vogt-小柳-原田病患者病程中黄斑中心凹的图像特点[J].眼科新进展,2013,33(6):000.
[8]辛晨 汪军 刘广峰 孟忻.增强成像技术光学相干断层扫描在在体脉络膜结构研究中的应用[J].眼科新进展,2013,33(6):000.
[9]马英慧 张铁民 齐建平.原发性开角型青光眼与慢性原发性闭角型青光眼视网膜神经纤维层厚度与视野缺损的关系[J].眼科新进展,2013,33(7):000.
[10]张海涛 杨玉新 毛永 丁晓丽 秦海霞 梁长华 郭英昌.青光眼与非炎症性缺血型视神经病变的傅立叶OCT扫描视神经形态学对比[J].眼科新进展,2013,33(8):000.
[11]高丰玫. 特发性黄斑裂孔玻璃体切割术后视力恢复及黄斑解剖愈合的相关因素分析[J].眼科新进展,2015,35(5):460.[doi:10.13389/j.cnki.rao.2015.0125]
　GAO Feng-Mei. Correlation analysis of postoperative visual acuity and macular anatomical outcomes after vitrectomy for idiopathic macular hole[J].Recent Advances in Ophthalmology,2015,35(11):460.[doi:10.13389/j.cnki.rao.2015.0125]
[12]朱欣悦,朱小敏,刘亚军,等.特发性黄斑裂孔手术治疗后裂孔愈合和视力恢复的相关因素[J].眼科新进展,2017,37(1):065.[doi:10.13389/j.cnki.rao.2017.0018]
　ZHU Xin-Yue,ZHU Xiao-Min,LIU Ya-Jun,et al.Associated factors analysis for predicting anatomical outcomes and postoperative visual acuity after vitrectomy for idiopathic macular hole[J].Recent Advances in Ophthalmology,2017,37(11):065.[doi:10.13389/j.cnki.rao.2017.0018]
[13]陈勇,刘向玲,宋子宣,等.特发性黄斑裂孔OCT影像与术后早期视力恢复的相关性研究[J].眼科新进展,2017,37(3):275.[doi:10.13389/j.cnki.rao.2017.0069]
　CHEN Yong,LIU Xiang-Ling,SONG Zi-Xuan,et al.Correlation of OCT image with postoperative early visual outcomes among patients with idiopathic macular holes[J].Recent Advances in Ophthalmology,2017,37(11):275.[doi:10.13389/j.cnki.rao.2017.0069]
[14]唐吉森,黄雄高,刘伟仙,等.黄斑部视网膜浅层毛细血管密度对特发性黄斑裂孔患者术后裂孔愈合的影响[J].眼科新进展,2020,40(12):1147.[doi:10.13389/j.cnki.rao.2020.0255]
　TANG Jisen,HUANG Xionggao,LIU Weixian,et al.Effects of retina superficial capillary plexus densities on the type of hole healing in patients with idiopathic macular hole[J].Recent Advances in Ophthalmology,2020,40(11):1147.[doi:10.13389/j.cnki.rao.2020.0255]
[15]王一博,孟旭霞,余川,等.特发性黄斑裂孔患者术后黄斑区视网膜微结构修复与视功能恢复关系研究[J].眼科新进展,2021,41(3):244.[doi:10.13389/j.cnki.rao.2021.0051]
　WANG Yibo,MENG Xuxia,YU Chuan,et al.Relationship between postoperative macular microstructure repair and visual function recovery in patients with idiopathic macular fissure[J].Recent Advances in Ophthalmology,2021,41(11):244.[doi:10.13389/j.cnki.rao.2021.0051]

备注/Memo

备注/Memo:
国家自然科学基金项目（编号：61801363）
更新日期/Last Update: 2019-11-18