综述

人工智能在眼病筛查和诊断中的研究进展

Research progress of artificial intelligence in screening and diagnosis of eye diseases

:208-213
 
近年来随着人口老龄化的发展、人群用眼方式的改变,现有的眼科医疗资源正越来越难以满足日渐增长的医疗需求,亟需新型的诊疗模式予以补足。眼科人工智能作为眼科领域的新兴元素,在眼病的筛查诊断中发展迅速,主要表现为“眼部图像数据+人工智能”的模式。近年来,随着该模式在白内障、青光眼、糖尿病性视网膜病变(diabetic retinopathy,DR)等常见病中研究的深入,相关技术日渐成熟,表现出了较大的应用优势与应用前景,部分技术甚至成功转化并被逐渐应用于临床。眼科诊疗向智慧医学模式的过渡,有望缓解日益增长的医疗需求与紧缺的医疗资源之间的矛盾,从而提高整体的医疗服务水平。
The development of population aging and changes in the way people use their eyes over the recent years have increasingly challenged the existing ophthalmic medical resources to meet the growing medical needs, thus urgently calling for a novel diagnostic and treatment mode. Despite its status as an emerging sector in ophthalmology, ophthalmic artificial intelligence has developed rapidly in the screening and diagnosis of eye diseases, as can be seen in practices adopting the “eye imaging data + AI” mode. In recent years, with the intensified research on this mode with respect to common diseases such as cataract, glaucoma and diabetic retinopathy, relevant technologies have grown increasingly mature, presenting undeniable application superiority and prospects. Some of the relevant technical achievements have also been successfully transformed for practical usage, and are gradually being applied to clinical practices. Ophthalmic diagnosis and treatment are transitioning toward the era of intelligent medical services, which are expected to reduce the contradictions between the growing medical needs and the shortage of medical resources, as well as ultimately improve the overall experience of medical services.
论著

兰州市中小学生屈光状态筛查

Screening on the refractive status of primary and secondary school students in Lanzhou City

:9-16
 
目的:对兰州市中小学生的屈光状态进行调查分析,了解兰州市中小学生筛查性屈光不正的流行病学特征。方法:采用横断面研究方法,用随机分层抽样法抽取2021年4至12月在甘肃省兰州市47所学校的中小学生作为调查对象。以学校为单位,采用国际标准视力表检查视力,采用非睫状肌麻痹的电脑自动验光仪进行屈光检查。裸眼视力<0.8为视力低下,具体分为:近视为等效球镜度≥–0.75 DS;远视为等效球镜度≥+2.00 DS;散光为柱镜度≥1.00 DC;屈光参差为双眼屈光度数差值(等效球镜度)≥1.00 DS。比较不同年级不同屈光状态人数所占的百分比。结果:共纳入40 302人,其中男21 328人,女18 974人;汉族37 938人,少数民族2364人。小学、初中、高中各26 122、9346和4834人。视力低下的总检出率为59.1%(23 832/40 302),小学、初中和高中年级视力低下的检出率分别为48.8%(12 748/26 122),76.9%(7 189/9 346)和87.9%(4 250/4 834)。近视的总检出率为63.3%(25 521/40 302),其中,小学、初中和高中筛查性近视的检出率分别为51.4%(13 438/26 122),84.4%(7 888/9 346)和86.8%(4 195/4 834)。筛查性视力低下、远视、近视、散光及屈光参差的检出率在低中高年级间比较差异均有统计学意义(均P<0.001)。结论:兰州市中小学生视力低下和近视人群的检出率高于国家平均水平,且随着年级的增加检出率逐渐升高。
Objective: To investigate and analyze the refractive status of primary and secondary school students in Lanzhou City, and to understand the epidemiological characteristics of screening refractive errors among primary and secondary school students in Lanzhou City. Methods: Using the cross-sectional research method, primary and secondary school students from 47 schools in Lanzhou City, Gansu Province from April to December 2021 were selected as survey subjects by random stratified sampling method. Taking school as a unit, international standard visual acuity chart was used to check the eyesight and non-cycloplegia computerized autorefractor was used for refractive examination. Visual acuity ≥5.0 is considered normal; whereas visual acuity <4.8 is considered as poor vision. Poor vision is further divided into: short-sightedness with myopic spherical equivalent ≥0.75 DS; long-sightedness with telephoto spherical equivalent ≥+2.00 DS; astigmatism with cylinder mirror equivalent ≥1.00 DC; anisometropia with the difference of diopters between the two eyes (spherical equivalent) ≥1.00 DS. The percentage of the survey subjects with different refractive status in different grades were compared. Results: total of 40 302 subjects were enrolled, including 21 328 males and 18 974 females. There were 37 938 Han and 2 364 ethnic minorities; 26 122 elementary, 9 346 middle and 4 834 high schools. The total detection rate of low visual acuity was 59.1% (23 832/40 302), and 48.8% (12 748/26 122) in primary school, junior middle school and senior high school, 76.9% (7 189/9 346) and 87.9% (4 250/4 834), respectively. The total detection rate of myopia was 63.3% (25 521/40 302), among which, the detection rate of screening myopia in primary school, middle school and high school was 51.4% (13 438/26 122), 84.4% (7 888/9 346) and 86.8% (4 195/4 834), respectively. The detection rates of screening low visual acuity, hyperopia, myopia, astigmatism and anisometropia were statistically significant in low, middle and high grades (all P<0.001). Conclusion: The detection rate of low vision and myopia among primary and secondary school students in Lanzhou is higher than the national average, and the detection rate increases gradually with the increase of grades.
论著

人工智能诊断系统在基层眼底视网膜疾病筛查领域的应用实践

Application practice of artificial intelligence diagnosis system in the field of primary fundus retinal disease screening

:405-413
 
目的:借助于人工智能(artificial intelligence,AI)眼底筛查远程接转诊系统,探索“患者-社区-医院”远程筛查模式,推进眼科分级诊疗和双向转诊实施,为地市级医疗机构开展眼底疾病人工智能筛查工作提供一定的经验借鉴。方法:通过AI辅助远程筛查基层医疗机构的4886例患者,完成眼科检查并经AI初判、人工复核形成眼底诊断结论。通过医联体和专科联盟模式,对基层医疗机构的4886例患者的AI诊断系统结果和上级医师审核结果进行对照分析,分析AI诊断系统在眼科常见病种筛查中的推广应用的可信度和可行性。结果:AI检出DR的灵敏度为94.70%,特异度96.06%;DME的灵敏度96.43%,特异度96.55%;AMD的灵敏度77.55%,特异度95.74%;同时,其在病理性近视、白内障、青光眼等常见病种眼底筛查中也有一定作用。结论:AI辅助远程筛查系统对于绝大多数眼底疾病有较高的敏感性和特异性,适用于眼底疾病的筛查工作,利于基层医院或社区医院对于眼底疾病的初步诊断,落实眼科分级诊疗,有借鉴推广意义。
Objective: With the help of artificial intelligence (AI) based fundus screening remote referral telemedicine system,it enables us to explore the remote screening mode of patient-community-hospital, and promote the two-way referral and ophthalmic graded diagnosis. This investigation provides certain practice experiences for prefecture-level medical institutions to carry out AI screening for fundus diseases. Methods: Ophthalmologic examination was performed on 4,886 patients in primary medical institutions through AI-aided remote screening, and the final fundus diagnosis conclusion was formed after AI preliminary judgment and manual review. Through the Medical Consortium and specialty alliance model, the results of the AI diagnosis system and the audit results of superior physicians for 4 886 patients in primary care institutions were compared and analyzed, and the credibility and feasibility of the AI diagnosis system application in the screening of common ophthalmic diseases were discussed. Results: The sensitivity and specificity of AI detection of diabetic retinopathy were 94.70% and 96.06%, respectively. In the diabetic macular edema classification, the sensitivity and specificity were 96.43% and 96.55%, respectively. In the age-related macular degeneration classification, the sensitivity and specificity were 77.55% and 95.74%, respectively. Meanwhile, it also plays a role in screening common fundus diseases such as pathological myopia, cataract and glaucoma. Conclusion: The AI-aided remote screening system has high sensitivity and specificity for most of fundus diseases, indicating it is promising for fundus diseases screening in primary medical institutions. It is conducive for primary hospitals or community hospitals to carry out the initial diagnosis of fundus diseases, as well as the implementation of graded diagnosis and treatment of ophthalmology, which has reference and promotion significance.
论著

温州地区足月新生儿眼部筛查结果分析

Analysis of eye screening results for term neonates in Wenzhou area

:400-404
 
目的:足月新生儿行眼部筛查,对眼部疾病的发生情况与特征进行分析。方法:回顾性分析从2021年1月至2022年6月间就诊于温州医科大学附属第二医院&育英儿童医院的足月新生儿共4 594例,记录眼部筛查结果并分析。结果:新生儿眼部筛查总异常率约10.54%,眼底异常率约6.38%。眼前段常见病为新生儿泪囊炎、结膜炎、血管瘤、睑内翻、白内障等;眼底常见病为视网膜白色病灶、视网膜出血、家族性渗出性视网膜病变等。结论:广角婴幼儿眼底筛查仪可早期发现新生儿隐匿性的眼病,部分致盲性眼病需要早期给予治疗,今后需要建立和完善新生儿眼病筛查及随访机制。
Objective: To screen the eyes of term neonates and analyze the occurrence and characteristics of eye diseases. Methods: The eye screening results of 4 594 term neonates admitted to the Second Affiliated Hospital & Yuying Children's Hospital of Wenzhou Medical University from January 2021 to June 2022 were recorded and retrospectively analyzed. Results: The  total abnormal rate of neonatal eye screening was about 10.54%, among which the abnormal rate of fundus was about 6.38%. Common diseases of the anterior segment included neonatal dacryocystitis, conjunctivitis, hemangioma, entropion, cataract, et al. Common diseases of the posterior segment included retinal leukoplakia, retinal hemorrhage, familial exudative retinopathy, et al. Conclusions: The wide-angle infant fundus screening instrument could detect neonatal occult ophthalmopathy early. And some blinding ophthalmopathies might need early treatment. In the future, it is necessary to establish and improve the screeningand the follow-up mechanism system for the neonatal ophthalmopathy.
论著

白内障人工智能辅助诊断系统在社区筛查中的应用效果

Application of artificial intelligence-assisted diagnostic system for community-based cataract screening

:4-9
 
目的:评估白内障人工智能辅助诊断系统在社区筛查中的应用效果。方法:采用前瞻性观察性研究方法对白内障人工辅助诊断系统的应用效果进行分析,结合远程医疗的模式,由社区卫生人员对居民进行病史采集、视力检查和裂隙灯眼前节检查等,将数据上传至云平台,由白内障人工智能辅助诊断系统和人类医生依次进行白内障评估。结果:受检人群中男性所占比例为35.7%,年龄中位数为66岁,裂隙灯眼前节照片有98.7%的图像质量合格。该白内障人工智能辅助诊断系统在外部验证集中检出重度白内障的曲线下面积为0.915。在人类医生建议转诊的病例中,有80.3%也由人工智能系统给出了相同的建议。结论:该白内障人工智能辅助诊断系统在白内障社区筛查的应用中具有较好的可行性和准确性,为开展社区筛查疾病提供了参考依据。

Objective: To evaluate the effectiveness of an artificial intelligence-assisted diagnostic system for cataract screening in community. Methods: A prospective observational study was carried out based on a telemedicine platform. Patient history, medical records and anterior ocular segment images were collected and transmitted from community healthcare centers to Zhongshan Ophthalmic Center for evaluation by both ophthalmologists and artificial intelligence-assisted cataract diagnostic system. Results: Of all enumerated subjects, 35.7% were male and the median age was 66 years old. Of all enumerated slit-lamp images, 98.7% met the requirement of acceptable quality. This artificial intelligence-assisted diagnostic system achieved an AUC of 0.915 for detection of severe cataracts in the external validation dataset. For subjects who were advised to be referred to tertiary hospitals by doctors, 80.3% of them received the same suggestion from this artificial intelligence-assisted diagnostic system.Conclusion: This artificial intelligence-assisted cataract diagnostic system showed high applicability and accuracy in community-based cataract screening and could be a potential model of care in community-based disease screening.
论著

儿童双目视力筛查仪在筛查先天性白内障中的应用

Application of binocular vision screening instrument for children in screening congenital cataract

:8-14
 
目的: 探讨儿童双目视力筛查仪在先天性白内障中的应用。 方法: 本文为回顾性分析,选择 2017 年 7 月 至 2018 年 5 月在厦门市儿童医院眼科的 3 个月至 2 岁婴幼儿 336 例(672眼),均由2个固定的医生分别采用小瞳孔红光反射及儿童双目视力筛查仪检查,同时详细记录病史资料。所有患儿均给予裂隙灯检查、复方托品卡胺散瞳后行眼底检查,对眼底无法窥入的者必要时给予眼部B超检查或眼部MRI检查,以排除眼底病变。结果:依据2009年出版的第5版《Harley’s小儿眼科学》的先天性白内障临床分类方法,本组病例中先天性白内障的类型依次为皮质(核)白内障2 7例(35眼),其中胚胎核2例( 4眼),板层2 3例(29眼),核性2例( 2眼);囊膜性白内障1 9例(28眼),缝合性白内障2例( 4眼),极性白内障3例( 6眼),全白内障2例( 3眼)。儿童双目视力筛查仪筛查出先天性白内障的灵敏度为81.58%,特异度为79.87%,诊断符合率为80.06%;红光反射筛查的先天性白内障的灵敏度为51.32%,特异度为69.97%,诊断符合率为67.86%;两组结果比较均有统计学意义。儿童双目视力筛查仪对皮质(核)性白内障筛查率为97.14%,而红光反射的筛查率为37.14%,结果比较具有统计学意义。结论:儿童双目视力筛查仪在先天性白内障筛查中,具有低漏诊率和误诊率,较高的诊断一致性的优势,尤其对皮质(核)性白内障有高的检出率,将有利于在日常儿童眼保健的辅助筛查工作中,及早发现先天性白内障患儿。
Objective: To explore the application of children’s binocular vision screening instrument in screening congenital cataract. Methods: This was a retrospective analysis of 336 infants aged 3 months to 2 years (672 eyes) who were admitted to the Ophthalmology Department of Xiamen Children's Hospital from July 2017 to May 2018. They were examined by two fixed doctors with the pupil red light reflex and binocular vision screening instrument, and the medical history was recorded in details. All the children received slit lamp examination, compound tropicamide mydriasis and fundus examination. If necessary, the children who could not see fundus were given with B-ultrasonic examination or MRI examination. Results: According to the clinical classification of congenital cataracts published in the 5th edition of Harley’s pediatric ophthalmology in 2009, In this group, there were 27 cases (35 eyes) of congenital cataract, including 2 cases (4 eyes) of embryonic nucleus, 23 cases (29 eyes) of lamellar layer, 2 cases (2 eyes) of nuclear cataract, 19 cases (28 eyes) of capsular cataract, 2 cases (4 eyes) of suture cataract, 3 cases (6 eyes) of polar cataract and 2 cases (3 eyes) of total cataract. The sensitivity of children’s binocular vision screening instrument screening congenital cataract was 81.58%, the specificity was 79.87%, and the diagnostic coincidence rate was 80.06%; the sensitivity of red reflection screening congenital cataract was 51.32%, the specificity was 69.97%, and the diagnostic coincidence rate was 67.86%; the results of the two groups were statistically significant. The screening rate of children's binocular vision screening instrument for cortical (nuclear) cataract was 97.14%, while that of red reflex was 37.14%. The results were statistically significant. Conclusion: In the screening of congenital cataract, the binocular vision screening instrument for children has the advantages of low missed diagnosis rate, high misdiagnosis rate and high diagnostic consistency, especially for cortical (nuclear) cataract. It is helpful to find the congenital cataract early in the auxiliary screening of children’cares eye health
其他期刊
  • 眼科学报

    主管:中华人民共和国教育部
    主办:中山大学
    承办:中山大学中山眼科中心
    主编:林浩添
    主管:中华人民共和国教育部
    主办:中山大学
    浏览
  • Eye Science

    主管:中华人民共和国教育部
    主办:中山大学
    承办:中山大学中山眼科中心
    主编:林浩添
    主管:中华人民共和国教育部
    主办:中山大学
    浏览
推荐阅读
出版者信息