Background: Patients with retinal diseases may exhibit serious complications that cause severe visual impairment owing to a lack of awareness of retinal diseases and limited medical resources. Understanding how artificial intelligence (AI) is used to make predictions and perform relevant analyses is a very active area of research on retinal diseases. In this study, the relevant Science Citation Index (SCI) literature on the AI of retinal diseases published from 2012 to 2021 was integrated and analyzed.
Objective: The aim of this study was to gain insights into the overall application of AI technology to the research of retinal diseases from set time and space dimensions.
Methods: Citation data downloaded from the Web of Science Core Collection database for AI in retinal disease publications from January 1, 2012, to December 31, 2021, were considered for this analysis. Information retrieval was analyzed using the online analysis platforms of literature metrology: Bibliometrc, CiteSpace V, and VOSviewer.
Results: A total of 197 institutions from 86 countries contributed to relevant publications; China had the largest number and researchers from University College London had the highest H-index. The reference clusters of SCI papers were clustered into 12 categories. “Deep learning” was the cluster with the widest range of cocited references. The burst keywords represented the research frontiers in 2018-2021, which were “eye disease” and “enhancement.”
Conclusions: This study provides a systematic analysis method on the literature regarding AI in retinal diseases. Bibliometric analysis enabled obtaining results that were objective and comprehensive. In the future, high-quality retinal image–forming AI technology with strong stability and clinical applicability will continue to be encouraged.
Retinal diseases are the main afflictions affecting human vision. Diabetic retinopathy (DR) is an eye vascular disease caused by diabetes . Following DR, retinal vein occlusion is the most frequent retinal vascular disorder [ ]. Drusen, long-spaced collagen, and phospholipid vesicles are all linked to age-related macular degeneration (AMD). These structures exist between the retinal pigment epithelium’s basement membrane and the rest of the Bruch membrane [ ]. Glaucoma is a disease that leads to the death of retinal ganglion cells as well as the loss of axons that make up the optic nerve [ ]. Early detection of the disease is challenging; however, the condition may be improved with appropriate treatment [ ]. These lesions are the major cause of vision loss or impairment in working-age and elderly adults worldwide [ , ]. The identification of retinopathy and maculopathy retinopathy may be time-intensive and requires expert training.
Artificial intelligence (AI), in which training data are used to develop a system, has become increasingly popular regarding clinical image analysis and disease diagnosis [- ]. The US Food and Drug Administration has approved a device based on AI to diagnose DR, despite the fact that the application and development of AI in medicine are still in an infancy stage [ ]. To address the current limitations of auxiliary examination processes, computer algorithms determine the optimal decision boundary in a multidimensional feature space [ ]. At present, such systems are still being improved by researchers.
The aim of this study was to gain insights into the overall application of AI technology in the research of retinal diseases from specific time and space dimensions. We used bibliometric methods to analyze papers in the Science Citation Index (SCI) reporting studies performed from January 1, 2012, to December 31, 2021, on AI in retinal disease research. The citations of countries, regions, institutions, periodicals, study categories, keywords, and references were included in the data. In addition, we established a visual and unbiased approach to explore hotspot knowledge frontiers in a research area. This study thus provides a useful reference for algorithm researchers, ophthalmologists, and experts in the field of medical engineering.
On February 15, 2022, all citation data published between January 1, 2012, and December 31, 2021, were retrieved from the Web of Science Core Collection (WoSCC). The data were independently verified by two authors (YL and JZ). The detailed search string is listed in. The document type was article. From each publication, we gathered the following basic data: title, abstract, authors, institution, country or region, journal, keywords, and references. The detailed search and analysis processes are depicted in .
Unpublished and document types other than articles were excluded. The citation data were downloaded on February 15, 2022, and some 2021 documents included by WoSCC were not published and were thus not included in this study. Some data were excluded because their document types were not articles, such as procedures, papers, review articles, meeting abstracts, early access, editorial materials, book chapters, letters, corrections, data papers, books, and retracted publications.
Collaborative networks of countries, institutions, journals, keywords, and research categories were analyzed and visualized using the bibliometrics online analysis platform Bibliometrc , CiteSpace V, and VOSviewer. We collected detailed citation features for analysis, including the number of annual publications, countries, institutes, journals, subject categories, cocited references, and keywords. The H-index represents an estimate of the importance and general impact of the research contributions [ ].
Distribution of Articles by Publication Year
We analyzed a total of 2275 papers published between 2012 and 2021. The numbers of published studies on the application of AI technology to retinal illnesses over time are summarized in. Since 2017, the number of studies on the use of AI in the treatment of retinal illnesses has skyrocketed.
Countries or Regions and Institutes
These citations mentioned a total of 86 nations or territories. In, the publications from different countries or regions are represented by blocks of different colors. The size of the colored block area represents the number of citations and the size of the different colored coverage areas represents the intensity of the cooperation. In , a larger label area for a given country represents a greater contribution to the related literature. The purple node area indicates the strength of the centrality; the higher the centrality value, the more cooperative the relations it establishes in the country where the node is located. As per and , China and the United States have contributed the largest number of documents to this field. The United States, the United Kingdom, and Singapore cooperated more with other countries.
lists the top 10 countries cited. China had the largest number of publications, followed by the United States, India, and the United Kingdom. Britain had the strongest centrality, followed by the United States and Singapore.
A total of 197 institutions have published relevant papers, and the clustering of their cooperative relationships is shown in. The top 10 institutions regarding the frequency of cited institutions are listed in , including three Chinese institutions (Sun Yat Sen University, Chinese Academy of Sciences, and Shanghai Jiao Tong University), three US institutions (Johns Hopkins University, Oregon Health and Science University, and Stanford University), two Singapore institutions (Singapore National Eye Centre and National University Singapore), one Austrian institution (Medical University of Vienna), and one UK institution (University College London). Among them, the number of citations with authors from University College London ranked in 10th position; however, their H-index was the highest. In addition, Johns Hopkins University and University College London, which were the two highest-ranked institutions in the center, appeared in the same cluster.
|Country or region|
|1. People’s Republic of China||634||0.16||42|
|2. United States||620||0.57||56|
|5. South Korea||150||0.00||24|
|1. Sun Yat Sen University||62||0.05||16|
|2. Chinese Academy of Science||51||008||14|
|3. Johns Hopkins University||49||0.13||16|
|4. Oregon Health and Science University||48||0.01||16|
|5. Stanford University||47||0.03||18|
|6. Medical University of Vienna||42||0.06||19|
|7. Singapore National Eye Centre||39||0.11||18|
|8. National University of Singapore||38||0.07||20|
|9. Shanghai Jiao Tong University||38||0.00||10|
|10. University College London||37||0.12||21|
Citing journals represents the research frontier and cited journals represents the research foundation. The top 10 citing journals and cited journals are shown in. The most frequently cited journals in the included citations were Translational Vision Science Technology, Scientific Reports, and IEEE Access. The journals that appeared most frequently among the cited journals were Ophthalmology, British Journal of Ophthalmology, and IEEE Transactions on Medical Imaging. PLoS One appeared in both the top-ranked citing and cited journals lists. The dual map of the journals is shown in . Red represents the discipline field with the greatest influence. The research influence in the field of mathematics/systems/mathematical subject ranked first among the citing journals.
|1. Translational Vision Science Technology||100|
|2. Scientific Reports||86|
|3. IEEE Access||85|
|4. Biomedical Optics Express||67|
|5. PLoS One||53|
|6. IEEE Transactions on Medical Imaging||48|
|7. American Journal of Ophthalmology||41|
|8. Computer Methods and Programs in Biomedicine||40|
|9. British Journal of Ophthalmology||36|
|2. Investigative Ophthalmology & Visual Science||1083|
|3. IEEE Transactions on Medical Imaging||974|
|4. Lecture Notes in Computer Science||855|
|5. British Journal of Ophthalmology||778|
|6. PLoS One||775|
|7. Medical Image Analysis||714|
|8. JAMA (Journal of the American Medical Association)||681|
|9. American Journal of Ophthalmology||673|
|10. JAMA Ophthalmology||647|
and present the research areas of the citations. The most involved research areas were Ophthalmology and Engineering Electrical Electronic. The highest H-index score areas were Engineering Biomedical and Radiology Nuclear Medicine Medical Imaging. This indicates that research on AI in retinal diseases is primarily focused within the fields of computer engineering and medical imaging.
|2||Engineering Electrical Electronic||332||33|
|4||Computer Science Artificial Intelligence||265||34|
|5||Computer Science Interdisciplinary Applications||250||40|
|6||Radiology Nuclear Medicine Medical Imaging||246||42|
|7||Computer Science Information Systems||206||23|
|10||Mathematical Computational Biology||139||24|
Keywords were retrieved and examined from the relevant literature.lists the top 20 keywords used. Among them, the keywords cited over 200 times were “diabetic retinopathy,” “classification,” “validation,” and “imaging.” The keywords of the 2267 articles were analyzed and divided into four categories (deep learning, DR, optical coherence tomography, and classification), as shown in . The time trend was examined using the hotspot transfer method, which was applied to the first 15 keywords with the highest citation outbreak. As shown in , the key words with the greatest outburst intensity were “pattern” and “retinal ganglion cell.” The red grid indicates the emergence of keywords. “Information” and “neuron” were the keywords with the longest use (2012-2019), and “eye disease” and “enhancement” were the most popular keywords from 2018 to 2021.
|6||Optical coherence tomography||154|
A reference’s citation frequency represents its influence. We constructed a cocited literature network and analyzed the scientific relevance of the publications. The modularity of the network was measured using the modularity index; the higher the modularity Q score, the better the network’s clustering. Q>0.3 indicates that the network community structure obtained is noteworthy. The better the network’s homogeneity, the closer the Silhouette S value is to 1. The cited documents were grouped into 12 clusters, as shown in. The homogeneity of these clusters was characterized by modularity Q=0.838 and weighted mean Silhouette S=0.9474. Cluster markers were created using the index items taken from the literature. The modularity of the network was measured using the modularity index. “Deep learning“ was the cluster with the widest range.
There were 2275 SCI papers reviewed in this study of AI and retinal diseases, which were published from 2012 to 2021, with a major increase in these publications since 2017. This is due to one study  being cited 506 times in 2016, which provided an important scientific and technical reference for researchers in this field. China and the United States had the maximum number of publications. The United Kingdom had the most cooperative relations. In addition, the three outcome indicators of the institution indicated that the research conducted by University College London and Johns Hopkins University has had a major influence on this research field. The number of citations in this field published by citing journals and cited journals indicated that the application of AI in retinal diseases has mainly been in the fields of computer engineering and medical imaging based on digital technology. This same pattern also applied to the citation categories.
The important nodes in the clustering demonstrated this research field’s knowledge bases after clustering the cited references. They were labeled #0 deep learning, #1 artificial intelligence, #2 optical coherence tomography, #3 image segmentation, #4 vessel segmentation, #5 Kohonen neural network, #6 Brownian motion, #7 diabetic retinopathy, #8 retina imaging, #9 age-related macular degeneration, #10 image analysis, and #11 glaucoma. The top 10 cocited references in these clusters are listed in. These studies’ conclusions require a substantial amount of basic work to be performed by ophthalmologists. For example, from the top-ranking article, 54 ophthalmologists or ophthalmic trainees participated in the identification of 5-year image data of three eye hospital patients presenting for image-based DR screening. From the second-ranked article, 494,661 retinal photographs were used to assess the diagnosis performance of a deep-learning system for DR and related eye illnesses. Each retinal image was analyzed by two trained senior, certified nonmedical professional graders. To achieve progress in the application of AI in retinal diseases, more cooperative and collaborative relationships among ophthalmologists, imaging technicians, and computer technology researchers are required in the future.
|Rank||Reference||Title of cocited reference||Count||Interpretation of the findings|
|1||Gulshan et al ||Development and validation of a deep learning algorithm for the detection of DRa in retinal fundus photographs||506||For diagnosing referable DR, a deep machine learning method had good sensitivity and specificity|
|2||Ting et al ||Development and validation of a deep learning system for DR and related eye diseases using retinal images from multiethnic populations with diabetes||270||The deep learning system demonstrated high sensitivity and specificity for detecting DR and related eye disorders|
|3||Lam et al ||Automated Identification of DR using deep learning||214||A high-reliability data-driven AI-based grading technique for screening and identifying fundus pictures taken from patients with diabetes. For further assessment and therapy, these patients should be referred to an ophthalmologist|
|4||Ronneberger et al ||U-Net: convolutional networks for biomedical image segmentation||208||This research provides a network and training technique that heavily depends on data augmentation to make better use of existing annotated samples|
|5||He et al ||Deep residual learning for image recognition||173||This research proposes a residual learning paradigm for network training|
|6||Kermany et al ||Identifying medical diagnoses and treatable diseases by image-based deep learning||163||This paper describes the development of a diagnostic tool for screening patients with common treatable blinding retinal disorders based on a deep-learning architecture|
|7||LeCun et al ||Deep learning||162||AI will advance as a result of systems that combine representation learning and complicated reasoning|
|8||De Fauw et al ||Clinically applicable deep learning for diagnosis and referral in retinal disease||160||When using tissue segmentations from a different type of device, a unique deep learning architecture was used to a clinically diverse data set to retain referral accuracy|
|9||Abràmoff et al ||Improved automated detection of DR on a publicly available dataset through the integration of deep learning||159||Deep learning–enhanced algorithms have the potential to improve the effectiveness of DR screening, thereby preventing vision loss and blindness from this dreadful disease|
|10||Esteva et al ||Dermatologist-level classification of skin cancer with deep neural networks||145||This research shows how deep learning works in dermatology and how it can be applied to other fields, including ophthalmology, otolaryngology, radiography, and pathology|
aDR: diabetic retinopathy.
Research Hotspots and Frontiers
Keywords provide a quick summary of the most important aspects and points in a collection of articles . Current research hotspots and frontiers can be identified using burst keyword analysis. Following the capture of the burst keywords, two study fields were identified: eye disease (2018-2021) and enhancement (2018-2021).
The application of AI technology to eye diseases is comparable to the best clinical systems and has achieved competitive results in solving issues related to the diagnosis and monitoring of complex ophthalmic diseases. AMD is usually asymptomatic, and an intermediate stage may not be identified. Moreover, AMD affects several people worldwide and thus identifying it can be time-consuming and difficult without the assistance of experts. Fortunately, applying deep learning–based automated algorithms may solve this challenge. This could also address the expenses of screening or monitoring, health care access, and the evaluation of innovative treatments for AMD development or progression . DR also causes challenges for many people. It is the leading cause of vision loss and preventable blindness in adults aged 20-74 years in middle- and high-income countries [ ]. Using a combination of digital retinal image analysis and telemedicine assessment to help identify people at risk of cardiovascular disease and cognitive impairment may have benefits beyond sight-threatening diseases prevention [ , ]. Aamir et al [ ] built a hierarchical deep convolutional neural network (CNN) for glaucoma recognition and prevention using an advanced deep-learning technique. This project was then used to extract multilayer features from 1338 images to verify the performance of the algorithm, achieving nearly 100% specificity, sensitivity, accuracy, and precision. These studies highlight the current research findings based on the use of AI technology in clinical applications for the management of ophthalmic diseases.
In addition, AI technology has been applied to the screening, referral, diagnosis, health care, and follow-up visits of patients with a variety retinal illness. Wang et al  developed a two-step semiautomatic deep learning algorithm–assisted technique to identify fundus pictures and aid in the detection of DR with vision-threatening complications. Optical coherence tomographic (OCT) angiography is a noninvasive imaging technology that may generate angiograms at precise depths within the retina as well as visualize the microvasculature in real time [ ]. A British study published in 2021 assessed an AI decision support system with the use of OCT scanning of retinal pictures to identify the digital referral path, providing evidence of the contributing reasons and difficulties of adopting the digital path in real life, with the goal of helping to eliminate unnecessary referrals [ ]. To boost doctors’ faith in AI systems to make accurate diagnoses, some AI systems must be written as interpretable programs [ ]. According to a follow-up poll conducted in 2017, radiologists used certain touch-environment solutions forced by the clinical setting at the time, demonstrating that they are still opposed to the transfer from traditional to updated interfaces [ ].
Ophthalmologists are confused by the quality differences among fundus diagnostic images . Enhancing the analysis of retinal image structures requires the development of a computer-assisted algorithm to correct the low fundus image quality [ ]. Wan et al [ ] proposed a deep learning–based technique that overcomes the limitations of current imaging algorithms and improves the low retinal image quality. CNN models may be developed under strong and mostly correct assumptions regarding the nature of macular disease images [ ]. El-Hag et al [ ]established the importance of the proposed blurry image improvement phase. Additionally, using CNN as a classification technique with hazy logic augmentation was shown to improve the classification of normal and abnormal outcomes. In the testing phase, this resulted in a classification accuracy of 100% [ ]. The blood vessels in the neural network must be divided into arteries and veins to diagnose hypertensive retinopathy using retinal diagnostic images. According to this demand, Hussein and Faheem [ ] proposed the use of an AI method to improve vascular contrast. Zhou et al [ ] proposed the learning of discriminative CNN features and enhanced thin vessels in color fundus images to further improve the segmentation performance. This algorithm improves the contrast of the retinal vessels and was verified by three pediatric ophthalmologists [ ]. Goel et al [ ] showed that using a development learning model to transfer learning can improve the accuracy of correct classification of different aneurysms in the retina area caused by DR.
AI technology can improve diagnosis accuracy and can also save time for both doctors and patients by increasing the contrast between image structures, such as segmenting distinct blood arteries or calculating normal and pathological structures. The image quality of retinal disease examination needs to be unified with high precision. This is currently a research hotspot to provide more high-quality research images based on research and development in AI technology, improvements in image acquisition technology, and the standardization of acquisition steps.
This bibliometric analysis only included the literature data in WoSCC. Some other databases were not included, such as PubMed, Medline, and Cochrane. In addition, the citation data analyzed were only from the literature published from 2012 to 2021, rather than collecting all articles published in this research field to date. Some 2022 studies are still ongoing and have not yet been published. These criteria may result in publication bias.
This study provides a systematic literature analysis on the use of AI in retinal diseases. Bibliometric analysis enabled obtaining objective and comprehensive results. Judging by the volume of published papers and research subjects, this study area is still popular and a noteworthy topic with major interdisciplinary exploration space. Ophthalmologists, imaging experts, and computer algorithm researchers in developing and developed countries need to make full use of population advantages or core technologies in different regions to strengthen collaboration. This idea has become a research hotspot that uses the existing basic clinical research results and a more advanced algorithm mode to develop a high-quality ophthalmic examination image system and further verify its clinical applicability. At present, an algorithm program with 100% diagnostic accuracy for retinal disease has been developed . In the future, high-quality retinal image–forming AI technology with strong stability and clinical applicability will continue to be encouraged.
This research was funded by the Nanjing Enterprise Expert Team Project, Medical Science and Technology Development Project Fund of Nanjing (YKK21262), and Medical Big Data Clinical Research Project of Nanjing Medical University.
JZ, YL, and YQ acquired, analyzed, and discussed the data, and drafted the manuscript. YL drafted the manuscript. WY designed the research, acquired the clinical information, and revised the manuscript. All authors have contributed to the manuscript and approved the submitted version.
Conflicts of Interest
- Zhang P, Xue W, Huang X, Xu Y, Lu L, Zheng K, et al. Prevalence and risk factors of diabetic retinopathy in patients with type 2 diabetes in Shanghai. Int J Ophthalmol 2021;14(7):1066-1072 [FREE Full text] [CrossRef] [Medline]
- Song P, Xu Y, Zha M, Zhang Y, Rudan I. Global epidemiology of retinal vein occlusion: a systematic review and meta-analysis of prevalence, incidence, and risk factors. J Glob Health 2019 Jun;9(1):010427. [CrossRef] [Medline]
- Age-Related Eye Disease Study Research Group. The Age-Related Eye Disease Study system for classifying age-related macular degeneration from stereoscopic color fundus photographs: the Age-Related Eye Disease Study Report Number 6. Am J Ophthalmol 2001 Nov;132(5):668-681. [CrossRef] [Medline]
- Cesareo M, Ciuffoletti E, Ricci F, Missiroli F, Giuliano MA, Mancino R, et al. Visual disability and quality of life in glaucoma patients. Prog Brain Res 2015;221:359-374. [CrossRef] [Medline]
- Ireka OJ, Ogbonnaya CE, Arinze OC, Ogbu N, Chuka-Okosa CM. Comparing posture induced intraocular pressure variations in normal subjects and glaucoma patients. Int J Ophthalmol 2021;14(3):399-404 [FREE Full text] [CrossRef] [Medline]
- King H, Aubert RE, Herman WH. Global burden of diabetes, 1995-2025: prevalence, numerical estimates, and projections. Diabetes Care 1998 Sep;21(9):1414-1431. [CrossRef] [Medline]
- Nucci C, Russo R, Martucci A, Giannini C, Garaci F, Floris R, et al. New strategies for neuroprotection in glaucoma, a disease that affects the central nervous system. Eur J Pharmacol 2016 Sep 15;787:119-126. [CrossRef] [Medline]
- Chen Q, Yu W, Lin S, Liu B, Wang Y, Wei Q, et al. Artificial intelligence can assist with diagnosing retinal vein occlusion. Int J Ophthalmol 2021;14(12):1895-1902 [FREE Full text] [CrossRef] [Medline]
- Wan C, Li H, Cao G, Jiang Q, Yang W. An artificial intelligent risk classification method of high myopia based on fundus images. J Clin Med 2021 Sep 29;10(19):4488 [FREE Full text] [CrossRef] [Medline]
- Xu J, Shen J, Jiang Q, Wan C, Yan Z, Yang W. Research on the segmentation of biomarker for chronic central serous chorioretinopathy based on multimodal fundus image. Dis Markers 2021;2021:1040675. [CrossRef] [Medline]
- Wan C, Chen Y, Li H, Zheng B, Chen N, Yang W, et al. EAD-Net: a novel lesion segmentation method in diabetic retinopathy using neural networks. Dis Markers 2021;2021:6482665. [CrossRef] [Medline]
- Calisto FM, Santiago C, Nunes N, Nascimento JC. Introduction of human-centric AI assistant to aid radiologists for multimodal breast image classification. Int J Hum Comput Stud 2021 Jun;150:102607. [CrossRef]
- Calisto F, Nunes N, Nascimento J. BreastScreening. 2020 Sep Presented at: International Conference on Advanced Visual Interfaces; September 20-October 2, 2020; Salerno, Italy p. 1-5. [CrossRef]
- FDA permits marketing of artificial intelligence-based device to detect certain diabetes-related eye problems. US Food and Drug Administration. URL: https://www.fda.gov/news-events/press-announcements/fda-permits-marketing-artificial -intelligence-based-device-detect-certain-diabetes-related-eye [accessed 2018-04-11]
- Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal 2017 Dec;42:60-88. [CrossRef] [Medline]
- Bibliomtrc. URL: https://bibliometric.com/ [accessed 2022-04-25]
- Hirsch JE. An index to quantify an individual's scientific research output. Proc Natl Acad Sci U S A 2005 Nov 15;102(46):16569-16572 [FREE Full text] [CrossRef] [Medline]
- Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016 Dec 13;316(22):2402-2410. [CrossRef] [Medline]
- Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, 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. JAMA 2017 Dec 12;318(22):2211-2223 [FREE Full text] [CrossRef] [Medline]
- Lam C, Yi D, Guo M, Lindsey T. Automated detection of diabetic retinopathy using deep learning. AMIA Jt Summits Transl Sci Proc 2018;2017:147-155 [FREE Full text] [Medline]
- Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Lecture Notes in Computer Science. 2015 Jan 01 Presented at: 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI); October 5-9, 2015; Munich, Germany p. 234-241 URL: https://arxiv.org/pdf/1505.04597.pdf
- He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 Jan 01 Presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); June 27-30, 2016; Seattle, WA p. 770-778 URL: https://openaccess.thecvf.com/content_cvpr_2016/papers/He_Deep_Residual_Learning_CVPR_2016_paper.pdf
- Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 2018 Feb 22;172(5):1122-1131 [FREE Full text] [CrossRef] [Medline]
- LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015 May 28;521(7553):436-444. [CrossRef] [Medline]
- De Fauw J, Ledsam JR, Romera-Paredes B, Nikolov S, Tomasev N, Blackwell S, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med 2018 Sep;24(9):1342-1350. [CrossRef] [Medline]
- Abràmoff MD, Lou Y, Erginay A, Clarida W, Amelon R, Folk JC, et al. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophthalmol Vis Sci 2016 Oct 01;57(13):5200-5206. [CrossRef] [Medline]
- Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017 Feb 02;542(7639):115-118 [FREE Full text] [CrossRef] [Medline]
- Li H, An H, Wang Y, Huang J, Gao X. Evolutionary features of academic articles co-keyword network and keywords co-occurrence network: Based on two-mode affiliation network. Phys A Stat Mech Appl 2016 May;450:657-669. [CrossRef]
- Shen J, Wang L, Wang LL, Lyu CF, Liu S, Xie GT, et al. Image enhancement of color fundus photographs for age-related macular degeneration: the Shanghai Changfeng Study. Int J Ophthalmol 2022 Feb 18;15(2):268-275 [FREE Full text] [CrossRef] [Medline]
- Cheung N, Tikellis G, Wang JJ. Diabetic retinopathy. Ophthalmology 2007 Nov;114(11):2098-9; author reply 2099. [CrossRef] [Medline]
- Vujosevic S, Aldington SJ, Silva P, Hernández C, Scanlon P, Peto T, et al. Screening for diabetic retinopathy: new perspectives and challenges. Lancet Diabetes Endocrinol 2020 Apr;8(4):337-347. [CrossRef] [Medline]
- Aamir M, Irfan M, Ali T, Ali G, Shaf A, Al-Beshri A, et al. An adoptive threshold-based multi-level deep convolutional neural network for glaucoma eye disease detection and classification. Diagnostics 2020 Aug 18;10(8):602 [FREE Full text] [CrossRef] [Medline]
- Wang Y, Shi D, Tan Z, Niu Y, Jiang Y, Xiong R, et al. Screening referable diabetic retinopathy using a semi-automated deep learning algorithm assisted approach. Front Med 2021 Nov 25;8:740987. [CrossRef] [Medline]
- Jia Y, Tan O, Tokayer J, Potsaid B, Wang Y, Liu JJ, et al. Split-spectrum amplitude-decorrelation angiography with optical coherence tomography. Opt Express 2012 Feb 09;20(4):4710. [CrossRef]
- Han JED, Liu X, Bunce C, Douiri A, Vale L, Blandford A, et al. Teleophthalmology-enabled and artificial intelligence-ready referral pathway for community optometry referrals of retinal disease (HERMES): a Cluster Randomised Superiority Trial with a linked Diagnostic Accuracy Study-HERMES study report 1-study protocol. BMJ Open 2022 Feb 01;12(2):e055845 [FREE Full text] [CrossRef] [Medline]
- Ahuja AS, Halperin LS. Understanding the advent of artificial intelligence in ophthalmology. J Curr Ophthalmol 2019 Jun;31(2):115-117 [FREE Full text] [CrossRef] [Medline]
- Calisto F, Ferreira A, Nascimento J, Gonçalves D. Towards touch-based medical image diagnosis annotation. 2017 Jan 01 Presented at: 12th Association of Computing Machinery International Conference on Interactive Surfaces and Spaces (ACM ISS); October 17-20, 2017; Brighton, England p. 390-395.
- Philip S, Cowie LM, Olson JA. The impact of the Health Technology Board for Scotland's grading model on referrals to ophthalmology services. Br J Ophthalmol 2005 Jul;89(7):891-896 [FREE Full text] [CrossRef] [Medline]
- Wan C, Wu J, Li H, Yan Z, Wang C, Jiang Q, et al. Optimized-Unet: novel algorithm for parapapillary atrophy segmentation. Front Neurosci 2021;15:758887. [CrossRef] [Medline]
- Wan C, Zhou X, You Q, Sun J, Shen J, Zhu S, et al. Retinal image enhancement using cycle-constraint adversarial network. Front Med 2021;8:793726. [CrossRef] [Medline]
- Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM 2017 May 24;60(6):84-90. [CrossRef]
- El-Hag NA, Sedik A, El-Shafai W, El-Hoseny HM, Khalaf AAM, El-Fishawy AS, et al. Classification of retinal images based on convolutional neural network. Microsc Res Tech 2021 Mar;84(3):394-414. [CrossRef] [Medline]
- Hussain S, Faheem MR. Separation of veins and arteries for estimating hypertensive retinopathy in fundus images. Biomed Res Ther 2016 Jun 26;3(6):673-678. [CrossRef]
- Zhou L, Yu Q, Xu X, Gu Y, Yang J. Improving dense conditional random field for retinal vessel segmentation by discriminative feature learning and thin-vessel enhancement. Comput Methods Programs Biomed 2017 Sep;148:13-25. [CrossRef] [Medline]
- Intriago-Pazmino M, Ibarra-Fiallo J, Crespo J, Alonso-Calvo R. Enhancing vessel visibility in fundus images to aid the diagnosis of retinopathy of prematurity. Health Informatics J 2020 Dec;26(4):2722-2736 [FREE Full text] [CrossRef] [Medline]
- Goel S, Gupta S, Panwar A, Kumar S, Verma M, Bourouis S, et al. Deep learning approach for stages of severity classification in diabetic retinopathy using color fundus retinal images. Math Probl Eng 2021 Nov 24;2021:1-8. [CrossRef]
|AI: artificial intelligence|
|AMD: age-related macular degeneration|
|CNN: convolutional neural network|
|DR: diabetic retinopathy|
|OCT: optical coherence tomography|
|SCI: Science Citation Index|
|WoSCC: Web of Science Core Collection|
Edited by R Kukafka; submitted 24.02.22; peer-reviewed by FM Calisto, G Nneji, H Monday; comments to author 19.03.22; revised version received 25.03.22; accepted 04.04.22; published 14.06.22Copyright
©Junqiang Zhao, Yi Lu, Yong Qian, Yuxin Luo, Weihua Yang. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 14.06.2022.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.