1
|
Du K, Dong L, Zhang K, Guan M, Chen C, Xie L, Kong W, Li H, Zhang R, Zhou W, Wu H, Dong H, Wei W. Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images. Heliyon 2024; 10:e30881. [PMID: 38803983 PMCID: PMC11128864 DOI: 10.1016/j.heliyon.2024.e30881] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2023] [Revised: 05/03/2024] [Accepted: 05/07/2024] [Indexed: 05/29/2024] Open
Abstract
Background Ophthalmological screening for cytomegalovirus retinitis (CMVR) for HIV/AIDS patients is important to prevent lifelong blindness. Previous studies have shown good properties of automated CMVR screening using digital fundus images. However, the application of a deep learning (DL) system to CMVR with ultra-wide-field (UWF) fundus images has not been studied, and the feasibility and efficiency of this method are uncertain. Methods In this study, we developed, internally validated, externally validated, and prospectively validated a DL system to detect AIDS-related from UWF fundus images from different clinical datasets. We independently used the InceptionResnetV2 network to develop and internally validate a DL system for identifying active CMVR, inactive CMVR, and non-CMVR in 6960 UWF fundus images from 862 AIDS patients and validated the system in a prospective and an external validation data set using the area under the curve (AUC), accuracy, sensitivity, and specificity. A heat map identified the most important area (lesions) used by the DL system for differentiating CMVR. Results The DL system showed AUCs of 0.945 (95 % confidence interval [CI]: 0.929, 0.962), 0.964 (95 % CI: 0.870, 0.999) and 0.968 (95 % CI: 0.860, 1.000) for detecting active CMVR from non-CMVR and 0.923 (95 % CI: 0.908, 0.938), 0.902 (0.857, 0.948) and 0.884 (0.851, 0.917) for detecting active CMVR from non-CMVR in the internal cross-validation, external validation, and prospective validation, respectively. Deep learning performed promisingly in screening CMVR. It also showed the ability to differentiate active CMVR from non-CMVR and inactive CMVR as well as to identify active CMVR and inactive CMVR from non-CMVR (all AUCs in the three independent data sets >0.900). The heat maps successfully highlighted lesion locations. Conclusions Our UWF fundus image-based DL system showed reliable performance for screening AIDS-related CMVR showing its potential for screening CMVR in HIV/AIDS patients, especially in the absence of ophthalmic resources.
Collapse
Affiliation(s)
- Kuifang Du
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Li Dong
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Kai Zhang
- Chongqing Chang'an Industrial Group Co. Ltd, Chongqing, China
| | - Meilin Guan
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Chao Chen
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Lianyong Xie
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Wenjun Kong
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Heyan Li
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Ruiheng Zhang
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Wenda Zhou
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Haotian Wu
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Hongwei Dong
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Wenbin Wei
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| |
Collapse
|
2
|
Tang QQ, Yang XG, Wang HQ, Wu DW, Zhang MX. Applications of deep learning for detecting ophthalmic diseases with ultrawide-field fundus images. Int J Ophthalmol 2024; 17:188-200. [PMID: 38239939 PMCID: PMC10754665 DOI: 10.18240/ijo.2024.01.24] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2023] [Accepted: 11/07/2023] [Indexed: 01/22/2024] Open
Abstract
AIM To summarize the application of deep learning in detecting ophthalmic disease with ultrawide-field fundus images and analyze the advantages, limitations, and possible solutions common to all tasks. METHODS We searched three academic databases, including PubMed, Web of Science, and Ovid, with the date of August 2022. We matched and screened according to the target keywords and publication year and retrieved a total of 4358 research papers according to the keywords, of which 23 studies were retrieved on applying deep learning in diagnosing ophthalmic disease with ultrawide-field images. RESULTS Deep learning in ultrawide-field images can detect various ophthalmic diseases and achieve great performance, including diabetic retinopathy, glaucoma, age-related macular degeneration, retinal vein occlusions, retinal detachment, and other peripheral retinal diseases. Compared to fundus images, the ultrawide-field fundus scanning laser ophthalmoscopy enables the capture of the ocular fundus up to 200° in a single exposure, which can observe more areas of the retina. CONCLUSION The combination of ultrawide-field fundus images and artificial intelligence will achieve great performance in diagnosing multiple ophthalmic diseases in the future.
Collapse
Affiliation(s)
- Qing-Qing Tang
- Department of Ophthalmology and Research Laboratory of Macular Disease, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Xiang-Gang Yang
- Department of Ophthalmology and Research Laboratory of Macular Disease, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Hong-Qiu Wang
- Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, Guangdong Province, China
| | - Da-Wen Wu
- Department of Ophthalmology and Research Laboratory of Macular Disease, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Mei-Xia Zhang
- Department of Ophthalmology and Research Laboratory of Macular Disease, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| |
Collapse
|
3
|
Nguyen TD, Le DT, Bum J, Kim S, Song SJ, Choo H. Retinal Disease Diagnosis Using Deep Learning on Ultra-Wide-Field Fundus Images. Diagnostics (Basel) 2024; 14:105. [PMID: 38201414 PMCID: PMC10804390 DOI: 10.3390/diagnostics14010105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Revised: 12/20/2023] [Accepted: 12/26/2023] [Indexed: 01/12/2024] Open
Abstract
Ultra-wide-field fundus imaging (UFI) provides comprehensive visualization of crucial eye components, including the optic disk, fovea, and macula. This in-depth view facilitates doctors in accurately diagnosing diseases and recommending suitable treatments. This study investigated the application of various deep learning models for detecting eye diseases using UFI. We developed an automated system that processes and enhances a dataset of 4697 images. Our approach involves brightness and contrast enhancement, followed by applying feature extraction, data augmentation and image classification, integrated with convolutional neural networks. These networks utilize layer-wise feature extraction and transfer learning from pre-trained models to accurately represent and analyze medical images. Among the five evaluated models, including ResNet152, Vision Transformer, InceptionResNetV2, RegNet and ConVNext, ResNet152 is the most effective, achieving a testing area under the curve (AUC) score of 96.47% (with a 95% confidence interval (CI) of 0.931-0.974). Additionally, the paper presents visualizations of the model's predictions, including confidence scores and heatmaps that highlight the model's focal points-particularly where lesions due to damage are evident. By streamlining the diagnosis process and providing intricate prediction details without human intervention, our system serves as a pivotal tool for ophthalmologists. This research underscores the compatibility and potential of utilizing ultra-wide-field images in conjunction with deep learning.
Collapse
Affiliation(s)
- Toan Duc Nguyen
- Department of AI Systems Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
| | - Duc-Tai Le
- College of Computing and Informatics, Sungkyunkwan University, Suwon 16419, Republic of Korea
| | - Junghyun Bum
- Sungkyun AI Research Institute, Sungkyunkwan University, Suwon 16419, Republic of Korea
| | - Seongho Kim
- Department of Ophthalmology, Kangbuk Samsung Hospital, School of Medicine, Sungkyunkwan University, Suwon 16419, Republic of Korea;
| | - Su Jeong Song
- Department of Ophthalmology, Kangbuk Samsung Hospital, School of Medicine, Sungkyunkwan University, Suwon 16419, Republic of Korea;
- Biomedical Institute for Convergence, Sungkyunkwan University, Suwon 16419, Republic of Korea
| | - Hyunseung Choo
- Department of AI Systems Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
- College of Computing and Informatics, Sungkyunkwan University, Suwon 16419, Republic of Korea
- Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
| |
Collapse
|
4
|
Zhang J, Zou H. Insights into artificial intelligence in myopia management: from a data perspective. Graefes Arch Clin Exp Ophthalmol 2024; 262:3-17. [PMID: 37231280 PMCID: PMC10212230 DOI: 10.1007/s00417-023-06101-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2022] [Revised: 03/23/2023] [Accepted: 05/06/2023] [Indexed: 05/27/2023] Open
Abstract
Given the high incidence and prevalence of myopia, the current healthcare system is struggling to handle the task of myopia management, which is worsened by home quarantine during the ongoing COVID-19 pandemic. The utilization of artificial intelligence (AI) in ophthalmology is thriving, yet not enough in myopia. AI can serve as a solution for the myopia pandemic, with application potential in early identification, risk stratification, progression prediction, and timely intervention. The datasets used for developing AI models are the foundation and determine the upper limit of performance. Data generated from clinical practice in managing myopia can be categorized into clinical data and imaging data, and different AI methods can be used for analysis. In this review, we comprehensively review the current application status of AI in myopia with an emphasis on data modalities used for developing AI models. We propose that establishing large public datasets with high quality, enhancing the model's capability of handling multimodal input, and exploring novel data modalities could be of great significance for the further application of AI for myopia.
Collapse
Affiliation(s)
- Juzhao Zhang
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Haidong Zou
- Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Shanghai Eye Diseases Prevention & Treatment Center, Shanghai Eye Hospital, Shanghai, China.
- National Clinical Research Center for Eye Diseases, Shanghai, China.
- Shanghai Engineering Center for Precise Diagnosis and Treatment of Eye Diseases, Shanghai, China.
| |
Collapse
|
5
|
Li K, Zhu Q, Wu J, Ding J, Liu B, Zhu X, Lin S, Yan W, Li W. DCT-Net: An effective method to diagnose retinal tears from B-scan ultrasound images. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2024; 21:1110-1124. [PMID: 38303456 DOI: 10.3934/mbe.2024046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/03/2024]
Abstract
Retinal tears (RTs) are usually detected by B-scan ultrasound images, particularly for individuals with complex eye conditions. However, traditional manual techniques for reading ultrasound images have the potential to overlook or inaccurately diagnose conditions. Thus, the development of rapid and accurate approaches for the diagnosis of an RT is highly important and urgent. The present study introduces a novel hybrid deep-learning model called DCT-Net to enable the automatic and precise diagnosis of RTs. The implemented model utilizes a vision transformer as the backbone and feature extractor. Additionally, in order to accommodate the edge characteristics of the lesion areas, a novel module called the residual deformable convolution has been incorporated. Furthermore, normalization is employed to mitigate the issue of overfitting and, a Softmax layer has been included to achieve the final classification following the acquisition of the global and local representations. The study was conducted by using both our proprietary dataset and a publicly available dataset. In addition, interpretability of the trained model was assessed by generating attention maps using the attention rollout approach. On the private dataset, the model demonstrated a high level of performance, with an accuracy of 97.78%, precision of 97.34%, recall rate of 97.13%, and an F1 score of 0.9682. On the other hand, the model developed by using the public funds image dataset demonstrated an accuracy of 83.82%, a sensitivity of 82.69% and a specificity of 82.40%. The findings, therefore present a novel framework for the diagnosis of RTs that is characterized by a high degree of efficiency, accuracy and interpretability. Accordingly, the technology exhibits considerable promise and has the potential to serve as a reliable tool for ophthalmologists.
Collapse
Affiliation(s)
- Ke Li
- The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325035, China
| | - Qiaolin Zhu
- The Eye Hospital, School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325027, China
| | - Jianzhang Wu
- Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Wenzhou 325000, China
- The Eye Hospital, School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325027, China
| | - Juntao Ding
- The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325035, China
| | - Bo Liu
- The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325035, China
| | - Xixi Zhu
- The Eye Hospital, School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325027, China
| | - Shishi Lin
- The Eye Hospital, School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325027, China
| | - Wentao Yan
- The Eye Hospital, School of Ophthalmology & Optometry, Wenzhou Medical University, Wenzhou 325027, China
| | - Wulan Li
- The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325035, China
| |
Collapse
|
6
|
Yadav S, Murugan R, Goel T. H-Deep-Net: A deep hybrid network with stationary wavelet packet transforms for Retinal detachment classification through fundus images. Med Eng Phys 2023; 120:104048. [PMID: 37838406 DOI: 10.1016/j.medengphy.2023.104048] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Revised: 08/05/2023] [Accepted: 09/04/2023] [Indexed: 10/16/2023]
Abstract
Nowadays, automated disease diagnosis has become a vital role in the medical field due to the significant population expansion. An automated disease diagnostic approach assists clinicians in the diagnosis of disease by giving exact, consistent, and prompt results, along with minimizing the mortality rate. Retinal detachment has recently emerged as one of the most severe and acute ocular illnesses, spreading worldwide. Therefore, an automated and quickest diagnostic model should be implemented to diagnose retinal detachment at an early stage. This paper introduces a new hybrid approach of best basis stationary wavelet packet transform and modified VGG19-Bidirectional long short-term memory to detect retinal detachment using retinal fundus images automatically. In this paper, the best basis stationary wavelet packet transform is utilized for image analysis, modified VGG19-Bidirectional long short-term memory is employed as the deep feature extractors, and then obtained features are classified through the Adaptive boosting technique. The experimental outcomes demonstrate that our proposed method obtained 99.67% sensitivity, 95.95% specificity, 98.21% accuracy, 97.43% precision, 98.54% F1-score, and 0.9985 AUC. The model obtained the intended results on the presently accessible database, which may be enhanced further when additional RD images become accessible. The proposed approach aids ophthalmologists in identifying and easily treating RD patients.
Collapse
Affiliation(s)
- Sonal Yadav
- Bio-Medical Imaging Laboratory (BIOMIL), Department of Electronics and Communication Engineering, National Institute Of Technology Silchar, Assam-788010, India
| | - R Murugan
- Bio-Medical Imaging Laboratory (BIOMIL), Department of Electronics and Communication Engineering, National Institute Of Technology Silchar, Assam-788010, India.
| | - Tripti Goel
- Bio-Medical Imaging Laboratory (BIOMIL), Department of Electronics and Communication Engineering, National Institute Of Technology Silchar, Assam-788010, India
| |
Collapse
|
7
|
Freiberg J, Welikala RA, Rovelt J, Owen CG, Rudnicka AR, Kolko M, Barman SA. Automated analysis of vessel morphometry in retinal images from a Danish high street optician setting. PLoS One 2023; 18:e0290278. [PMID: 37616264 PMCID: PMC10449151 DOI: 10.1371/journal.pone.0290278] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 06/29/2023] [Indexed: 08/26/2023] Open
Abstract
PURPOSE To evaluate the test performance of the QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) software in detecting retinal features from retinal images captured by health care professionals in a Danish high street optician chain, compared with test performance from other large population studies (i.e., UK Biobank) where retinal images were captured by non-experts. METHOD The dataset FOREVERP (Finding Ophthalmic Risk and Evaluating the Value of Eye exams and their predictive Reliability, Pilot) contains retinal images obtained from a Danish high street optician chain. The QUARTZ algorithm utilizes both image processing and machine learning methods to determine retinal image quality, vessel segmentation, vessel width, vessel classification (arterioles or venules), and optic disc localization. Outcomes were evaluated by metrics including sensitivity, specificity, and accuracy and compared to human expert ground truths. RESULTS QUARTZ's performance was evaluated on a subset of 3,682 images from the FOREVERP database. 80.55% of the FOREVERP images were labelled as being of adequate quality compared to 71.53% of UK Biobank images, with a vessel segmentation sensitivity of 74.64% and specificity of 98.41% (FOREVERP) compared with a sensitivity of 69.12% and specificity of 98.88% (UK Biobank). The mean (± standard deviation) vessel width of the ground truth was 16.21 (4.73) pixels compared to that predicted by QUARTZ of 17.01 (4.49) pixels, resulting in a difference of -0.8 (1.96) pixels. The differences were stable across a range of vessels. The detection rate for optic disc localisation was similar for the two datasets. CONCLUSION QUARTZ showed high performance when evaluated on the FOREVERP dataset, and demonstrated robustness across datasets, providing validity to direct comparisons and pooling of retinal feature measures across data sources.
Collapse
Affiliation(s)
- Josefine Freiberg
- Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark
| | - Roshan A. Welikala
- School of Computer Science and Mathematics, Kingston University, Surrey, United Kingdom
| | - Jens Rovelt
- Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark
| | - Christopher G. Owen
- Population Health Research Institute, St. George’s, University of London, London, United Kingdom
| | - Alicja R. Rudnicka
- Population Health Research Institute, St. George’s, University of London, London, United Kingdom
| | - Miriam Kolko
- Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark
- Department of Ophthalmology, Copenhagen University Hospital, Rigshospitalet, Glostrup, Copenhagen, Denmark
| | - Sarah A. Barman
- School of Computer Science and Mathematics, Kingston University, Surrey, United Kingdom
| | | |
Collapse
|
8
|
Maltsev DS, Kulikov AN, Shaimova VA, Burnasheva MA, Vasiliev AS. Spotlight on Lattice Degeneration Imaging Techniques. Clin Ophthalmol 2023; 17:2383-2395. [PMID: 37605766 PMCID: PMC10440085 DOI: 10.2147/opth.s405200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Accepted: 08/10/2023] [Indexed: 08/23/2023] Open
Abstract
Lattice degeneration (LD), routinely diagnosed with indirect ophthalmoscopy, is one of the most common and clinically significant peripheral retinal findings. In this review, we have summarized the data on currently available imaging techniques which help to improve diagnosis and our understanding of LD pathogenesis. Ultra-wide field imaging provides reliable color fundus capturing for the primary diagnosis of LD and may also be used as a screening tool. Wide-field imaging can be used for targeted documentation of LD lesions using true colors and with minimal optical distortions. Information on the status of the vitreoretinal interface, including detection of retinal holes, detachments, and vitreous tractions, can be obtained with peripheral structural optical coherence tomography (OCT) or scanning laser ophthalmoscopy in retro-mode. These techniques clarify the associated risks of rhegmatogenous retinal detachment. Fundus autofluorescence can provide details on atrophic changes. However, the risk of retinal detachment by means of this technique requires further investigation. OCT angiography may be successfully performed for some lesions. Taken together, OCT and OCT angiography demonstrate thinning of the choroid, alteration of local choroidal microcirculation, and, in severe lesions, involvement of the sclera. OCT angiography confirms loss of retinal microcirculation within LD lesion, which was previously shown with fluorescein angiography. In conclusion, despite relatively simple primary diagnosis, imaging of LD lesions remains challenging due to their peripheral localization. However, several new strategies, including ultra-wide field imaging, peripheral OCT, and scanning laser ophthalmoscopy, make LD imaging possible on a routine basis, improving diagnosis and understanding of LD pathogenesis.
Collapse
Affiliation(s)
- Dmitrii S Maltsev
- Department of Ophthalmology, Military Medical Academy, St. Petersburg, Russia
| | - Alexei N Kulikov
- Department of Ophthalmology, Military Medical Academy, St. Petersburg, Russia
| | - Venera A Shaimova
- Academy of Postgraduate Education of the Federal Scientific and Clinical Center of Specialized Medical Care and Medical Technologies, Moscow, Russia
- “Center Zreniya”, Chelyabinsk, Russia
| | - Maria A Burnasheva
- Department of Ophthalmology, Military Medical Academy, St. Petersburg, Russia
| | | |
Collapse
|
9
|
Azzopardi M, Chong YJ, Ng B, Recchioni A, Logeswaran A, Ting DSJ. Diagnosis of Acanthamoeba Keratitis: Past, Present and Future. Diagnostics (Basel) 2023; 13:2655. [PMID: 37627913 PMCID: PMC10453105 DOI: 10.3390/diagnostics13162655] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 08/04/2023] [Accepted: 08/09/2023] [Indexed: 08/27/2023] Open
Abstract
Acanthamoeba keratitis (AK) is a painful and sight-threatening parasitic corneal infection. In recent years, the incidence of AK has increased. Timely and accurate diagnosis is crucial during the management of AK, as delayed diagnosis often results in poor clinical outcomes. Currently, AK diagnosis is primarily achieved through a combination of clinical suspicion, microbiological investigations and corneal imaging. Historically, corneal scraping for microbiological culture has been considered to be the gold standard. Despite its technical ease, accessibility and cost-effectiveness, the long diagnostic turnaround time and variably low sensitivity of microbiological culture limit its use as a sole diagnostic test for AK in clinical practice. In this review, we aim to provide a comprehensive overview of the diagnostic modalities that are currently used to diagnose AK, including microscopy with staining, culture, corneal biopsy, in vivo confocal microscopy, polymerase chain reaction and anterior segment optical coherence tomography. We also highlight emerging techniques, such as next-generation sequencing and artificial intelligence-assisted models, which have the potential to transform the diagnostic landscape of AK.
Collapse
Affiliation(s)
- Matthew Azzopardi
- Department of Ophthalmology, Royal London Hospital, London E1 1BB, UK;
| | - Yu Jeat Chong
- Birmingham and Midland Eye Centre, Birmingham B18 7QH, UK; (B.N.); (A.R.)
| | - Benjamin Ng
- Birmingham and Midland Eye Centre, Birmingham B18 7QH, UK; (B.N.); (A.R.)
| | - Alberto Recchioni
- Birmingham and Midland Eye Centre, Birmingham B18 7QH, UK; (B.N.); (A.R.)
- Academic Unit of Ophthalmology, Institute of Inflammation and Ageing, University of Birmingham, Birmingham B15 2TT, UK
| | | | - Darren S. J. Ting
- Birmingham and Midland Eye Centre, Birmingham B18 7QH, UK; (B.N.); (A.R.)
- Academic Unit of Ophthalmology, Institute of Inflammation and Ageing, University of Birmingham, Birmingham B15 2TT, UK
- Academic Ophthalmology, School of Medicine, University of Nottingham, Nottingham NG7 2RD, UK
| |
Collapse
|
10
|
Strzalkowski P, Schuster AK, Strzalkowska A, Steinberg JS, Dithmar S. Semi-automated quantification of vitreal hyperreflective foci in SD-OCT and their relevance in patients with peripheral retinal breaks. BMC Ophthalmol 2023; 23:324. [PMID: 37460946 DOI: 10.1186/s12886-023-03060-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2023] [Accepted: 06/25/2023] [Indexed: 07/20/2023] Open
Abstract
BACKGROUND Retinal breaks (RB) are emergencies that require treatment to prevent progression of rhegmatogenous retinal detachment. Vitreal hyperreflective foci (VHF) representing migration of RPE cell clusters or interphotoreceptor matrix from the RB are potential biomarkers. The aim of this study is to investigate VHF in RB-patients using SD-OCT. METHODS The retrospective cross-sectional study included RB patients from our Department of Ophthalmology, HSK Wiesbaden who underwent macular SD-OCT (SPECTRALIS®, Heidelberg Engineering, Germany) on both eyes. VHF, defined and quantified as foci that differ markedly in size and reflectivity from the background speckle pattern, were assessed for presence and frequency. The RB-affected eyes were the study group (G1), the partner eyes the control group (G2). RESULTS 160 consecutive patients with RB were included. Age was 60 ± 10.2 years (52% female). 89.4% of G1 and 87.5% of G2 were phakic (p = 0.73). 94.4% (n = 151) were symptomatic. Symptom duration was 8.0 ± 10.1 days in G1, 94.4% (n = 151) showed VHF versus 5.6% (p < 0.0001) in G2, of which 75% (n = 6) showed asymptomatic lattice degenerations. Detectable VHF showed a strong association of OR = 320 (95% CI, 110-788, p < 0.0001)) with respect to symptomatic RB. Sensitivity and specificity were 94.7% and 94.7%, respectively. CONCLUSIONS Most eyes with symptomatic RB show vitreal VHF in SD-OCT. Detected VHF are strongly associated with RB, and our semi-automated greyscale reflectivity analysis indicates that VHF likely originate from photoreceptor complexes torn out of the RB area that migrate into the vitreous cavity. The presence of VHF may indicate RB and should lead to a thorough fundus examination in both symptomatic and asymptomatic cases.
Collapse
Affiliation(s)
- P Strzalkowski
- Department of Ophthalmology, Helios HSK Wiesbaden, Wiesbaden, Germany.
- Department of Ophthalmology, Heinrich-Heine University Duesseldorf, Duesseldorf, Germany.
| | - A K Schuster
- Department of Ophthalmology, University Medical Center of the Johannes Gutenberg, University of Mainz, Mainz, Germany
| | - A Strzalkowska
- Department of Ophthalmology, Heinrich-Heine University Duesseldorf, Duesseldorf, Germany
- Department of Ophthalmology, University Medical Center of the Johannes Gutenberg, University of Mainz, Mainz, Germany
| | - J S Steinberg
- Department of Ophthalmology, Helios HSK Wiesbaden, Wiesbaden, Germany
| | - S Dithmar
- Department of Ophthalmology, Helios HSK Wiesbaden, Wiesbaden, Germany
| |
Collapse
|
11
|
Li Z, Wang L, Wu X, Jiang J, Qiang W, Xie H, Zhou H, Wu S, Shao Y, Chen W. Artificial intelligence in ophthalmology: The path to the real-world clinic. Cell Rep Med 2023:101095. [PMID: 37385253 PMCID: PMC10394169 DOI: 10.1016/j.xcrm.2023.101095] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Revised: 04/17/2023] [Accepted: 06/07/2023] [Indexed: 07/01/2023]
Abstract
Artificial intelligence (AI) has great potential to transform healthcare by enhancing the workflow and productivity of clinicians, enabling existing staff to serve more patients, improving patient outcomes, and reducing health disparities. In the field of ophthalmology, AI systems have shown performance comparable with or even better than experienced ophthalmologists in tasks such as diabetic retinopathy detection and grading. However, despite these quite good results, very few AI systems have been deployed in real-world clinical settings, challenging the true value of these systems. This review provides an overview of the current main AI applications in ophthalmology, describes the challenges that need to be overcome prior to clinical implementation of the AI systems, and discusses the strategies that may pave the way to the clinical translation of these systems.
Collapse
Affiliation(s)
- Zhongwen Li
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China; School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China.
| | - Lei Wang
- School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China
| | - Xuefang Wu
- Guizhou Provincial People's Hospital, Guizhou University, Guiyang 550002, China
| | - Jiewei Jiang
- School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
| | - Wei Qiang
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China
| | - He Xie
- School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China
| | - Hongjian Zhou
- Department of Computer Science, University of Oxford, Oxford, Oxfordshire OX1 2JD, UK
| | - Shanjun Wu
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China
| | - Yi Shao
- Department of Ophthalmology, the First Affiliated Hospital of Nanchang University, Nanchang 330006, China.
| | - Wei Chen
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China; School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China.
| |
Collapse
|
12
|
Zhang J, Sha D, Ma Y, Zhang D, Tan T, Xu X, Yi Q, Zhao Y. Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images. Front Cell Dev Biol 2023; 11:1181305. [PMID: 37215081 PMCID: PMC10196374 DOI: 10.3389/fcell.2023.1181305] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Accepted: 04/24/2023] [Indexed: 05/24/2023] Open
Abstract
Background: Ultra-Wide-Field (UWF) fundus imaging is an essential diagnostic tool for identifying ophthalmologic diseases, as it captures detailed retinal structures within a wider field of view (FOV). However, the presence of eyelashes along the edge of the eyelids can cast shadows and obscure the view of fundus imaging, which hinders reliable interpretation and subsequent screening of fundus diseases. Despite its limitations, there are currently no effective methods or datasets available for removing eyelash artifacts from UWF fundus images. This research aims to develop an effective approach for eyelash artifact removal and thus improve the visual quality of UWF fundus images for accurate analysis and diagnosis. Methods: To address this issue, we first constructed two UWF fundus datasets: the paired synthetic eyelashes (PSE) dataset and the unpaired real eyelashes (uPRE) dataset. Then we proposed a deep learning architecture called Joint Conditional Generative Adversarial Networks (JcGAN) to remove eyelash artifacts from UWF fundus images. JcGAN employs a shared generator with two discriminators for joint learning of both real and synthetic eyelash artifacts. Furthermore, we designed a background refinement module that refines background information and is trained with the generator in an end-to-end manner. Results: Experimental results on both PSE and uPRE datasets demonstrate the superiority of the proposed JcGAN over several state-of-the-art deep learning approaches. Compared with the best existing method, JcGAN improves PSNR and SSIM by 4.82% and 0.23%, respectively. In addition, we also verified that eyelash artifact removal via JcGAN could significantly improve vessel segmentation performance in UWF fundus images. Assessment via vessel segmentation illustrates that the sensitivity, Dice coefficient and area under curve (AUC) of ResU-Net have respectively increased by 3.64%, 1.54%, and 1.43% after eyelash artifact removal using JcGAN. Conclusion: The proposed JcGAN effectively removes eyelash artifacts in UWF images, resulting in improved visibility of retinal vessels. Our method can facilitate better processing and analysis of retinal vessels and has the potential to improve diagnostic outcomes.
Collapse
Affiliation(s)
- Jiong Zhang
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
- The Affiliated Ningbo Eye Hospital of Wenzhou Medical University, Ningbo, China
| | - Dengfeng Sha
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
- Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China
| | - Yuhui Ma
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
| | - Dan Zhang
- School of Cyber Science and Engineering, Ningbo University of Technology, Ningbo, China
| | - Tao Tan
- Faulty of Applied Sciences, Macao Polytechnic University, Macao, Macao SAR, China
| | - Xiayu Xu
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an, China
- Zhejiang Research Institute of Xi’an Jiaotong University, Hangzhou, China
| | - Quanyong Yi
- The Affiliated Ningbo Eye Hospital of Wenzhou Medical University, Ningbo, China
| | - Yitian Zhao
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
- The Affiliated Ningbo Eye Hospital of Wenzhou Medical University, Ningbo, China
| |
Collapse
|
13
|
Tang YW, Ji J, Lin JW, Wang J, Wang Y, Liu Z, Hu Z, Yang JF, Ng TK, Zhang M, Pang CP, Cen LP. Automatic Detection of Peripheral Retinal Lesions From Ultrawide-Field Fundus Images Using Deep Learning. Asia Pac J Ophthalmol (Phila) 2023; 12:284-292. [PMID: 36912572 DOI: 10.1097/apo.0000000000000599] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Accepted: 12/19/2022] [Indexed: 03/14/2023] Open
Abstract
PURPOSE To establish a multilabel-based deep learning (DL) algorithm for automatic detection and categorization of clinically significant peripheral retinal lesions using ultrawide-field fundus images. METHODS A total of 5958 ultrawide-field fundus images from 3740 patients were randomly split into a training set, validation set, and test set. A multilabel classifier was developed to detect rhegmatogenous retinal detachment, cystic retinal tuft, lattice degeneration, and retinal breaks. Referral decision was automatically generated based on the results of each disease class. t -distributed stochastic neighbor embedding heatmaps were used to visualize the features extracted by the neural networks. Gradient-weighted class activation mapping and guided backpropagation heatmaps were generated to investigate the image locations for decision-making by the DL models. The performance of the classifier(s) was evaluated by sensitivity, specificity, accuracy, F 1 score, area under receiver operating characteristic curve (AUROC) with 95% CI, and area under the precision-recall curve. RESULTS In the test set, all categories achieved a sensitivity of 0.836-0.918, a specificity of 0.858-0.989, an accuracy of 0.854-0.977, an F 1 score of 0.400-0.931, an AUROC of 0.9205-0.9882, and an area under the precision-recall curve of 0.6723-0.9745. The referral decisions achieved an AUROC of 0.9758 (95% CI= 0.9648-0.9869). The multilabel classifier had significantly better performance in cystic retinal tuft detection than the binary classifier (AUROC= 0.9781 vs 0.6112, P < 0.001). The model showed comparable performance with human experts. CONCLUSIONS This new DL model of a multilabel classifier is capable of automatic, accurate, and early detection of clinically significant peripheral retinal lesions with various sample sizes. It can be applied in peripheral retinal screening in clinics.
Collapse
Affiliation(s)
- Yi-Wen Tang
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Jie Ji
- Network and Information Center, Shantou University, Shantou, Guangdong, China
| | - Jian-Wei Lin
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Ji Wang
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Yun Wang
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Zibo Liu
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Zhanchi Hu
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Jian-Feng Yang
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Tsz Kin Ng
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
- Shantou University Medical College, Shantou, Guangdong, China
- Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong
| | - Mingzhi Zhang
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| | - Chi Pui Pang
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
- Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong
| | - Ling-Ping Cen
- Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China
| |
Collapse
|
14
|
Intelligent Diagnosis of Multiple Peripheral Retinal Lesions in Ultra-widefield Fundus Images Based on Deep Learning. Ophthalmol Ther 2023; 12:1081-1095. [PMID: 36692813 PMCID: PMC9872743 DOI: 10.1007/s40123-023-00651-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2022] [Accepted: 01/05/2023] [Indexed: 01/25/2023] Open
Abstract
INTRODUCTION Compared with traditional fundus examination techniques, ultra-widefield fundus (UWF) images provide 200° panoramic images of the retina, which allows better detection of peripheral retinal lesions. The advent of UWF provides effective solutions only for detection but still lacks efficient diagnostic capabilities. This study proposed a retinal lesion detection model to automatically locate and identify six relatively typical and high-incidence peripheral retinal lesions from UWF images which will enable early screening and rapid diagnosis. METHODS A total of 24,602 augmented ultra-widefield fundus images with labels corresponding to 6 peripheral retinal lesions and normal manifestation labelled by 5 ophthalmologists were included in this study. An object detection model named You Only Look Once X (YOLOX) was modified and trained to locate and classify the six peripheral retinal lesions including rhegmatogenous retinal detachment (RRD), retinal breaks (RB), white without pressure (WWOP), cystic retinal tuft (CRT), lattice degeneration (LD), and paving-stone degeneration (PSD). We applied coordinate attention block and generalized intersection over union (GIOU) loss to YOLOX and evaluated it for accuracy, sensitivity, specificity, precision, F1 score, and average precision (AP). This model was able to show the exact location and saliency map of the retinal lesions detected by the model thus contributing to efficient screening and diagnosis. RESULTS The model reached an average accuracy of 96.64%, sensitivity of 87.97%, specificity of 98.04%, precision of 87.01%, F1 score of 87.39%, and mAP of 86.03% on test dataset 1 including 248 UWF images and reached an average accuracy of 95.04%, sensitivity of 83.90%, specificity of 96.70%, precision of 78.73%, F1 score of 81.96%, and mAP of 80.59% on external test dataset 2 including 586 UWF images, showing this system performs well in distinguishing the six peripheral retinal lesions. CONCLUSION Focusing on peripheral retinal lesions, this work proposed a deep learning model, which automatically recognized multiple peripheral retinal lesions from UWF images and localized exact positions of lesions. Therefore, it has certain potential for early screening and intelligent diagnosis of peripheral retinal lesions.
Collapse
|
15
|
Sun G, Wang X, Xu L, Li C, Wang W, Yi Z, Luo H, Su Y, Zheng J, Li Z, Chen Z, Zheng H, Chen C. Deep Learning for the Detection of Multiple Fundus Diseases Using Ultra-widefield Images. Ophthalmol Ther 2023; 12:895-907. [PMID: 36565376 PMCID: PMC10011259 DOI: 10.1007/s40123-022-00627-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2022] [Accepted: 11/27/2022] [Indexed: 12/25/2022] Open
Abstract
INTRODUCTION To design and evaluate a deep learning model based on ultra-widefield images (UWFIs) that can detect several common fundus diseases. METHODS Based on 4574 UWFIs, a deep learning model was trained and validated that can identify normal fundus and eight common fundus diseases, namely referable diabetic retinopathy, retinal vein occlusion, pathologic myopia, retinal detachment, retinitis pigmentosa, age-related macular degeneration, vitreous opacity, and optic neuropathy. The model was tested on three test sets with data volumes of 465, 979, and 525. The performance of the three deep learning networks, EfficientNet-B7, DenseNet, and ResNet-101, was evaluated on the internal test set. Additionally, we compared the performance of the deep learning model with that of doctors in a tertiary referral hospital. RESULTS Compared to the other two deep learning models, EfficientNet-B7 achieved the best performance. The area under the receiver operating characteristic curves of the EfficientNet-B7 model on the internal test set, external test set A and external test set B were 0.9708 (0.8772, 0.9849) to 1.0000 (1.0000, 1.0000), 0.9683 (0.8829, 0.9770) to 1.0000 (0.9975, 1.0000), and 0.8919 (0.7150, 0.9055) to 0.9977 (0.9165, 1.0000), respectively. On a data set of 100 images, the total accuracy of the deep learning model was 93.00%, the average accuracy of three ophthalmologists who had been working for 2 years and three ophthalmologists who had been working in fundus imaging for more than 5 years was 88.00% and 94.00%, respectively. CONCLUSION High performance was achieved on all three test sets using our UWFI multidisease classification model with a small sample size and fast model inference. The performance of the artificial intelligence model was comparable to that of a physician with 2-5 years of experience in fundus diseases at a tertiary referral hospital. The model is expected to be used as an effective aid for fundus disease screening.
Collapse
Affiliation(s)
- Gongpeng Sun
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China
| | - Xiaoling Wang
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China
| | - Lizhang Xu
- Wuhan Aiyanbang Technology Co., Ltd, Wuhan, 430073, China
| | - Chang Li
- Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin International Joint Research and Development Centre of Ophthalmology and Vision Science, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin, 300384, China
| | - Wenyu Wang
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China
| | - Zuohuizi Yi
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China
| | - Huijuan Luo
- The People's Hospital of Yidu, Yidu, 443300, China
| | - Yu Su
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China
| | - Jian Zheng
- School of Electronic Information and Electric Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Zhiqing Li
- Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin International Joint Research and Development Centre of Ophthalmology and Vision Science, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin, 300384, China
| | - Zhen Chen
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China.
| | - Hongmei Zheng
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China.
| | - Changzheng Chen
- Eye Center, Renmin Hospital of Wuhan University, No. 9 ZhangZhiDong Street, Wuchang District, Wuhan, 430060, Hubei, China.
| |
Collapse
|
16
|
Ameen YA, Badary DM, Abonnoor AEI, Hussain KF, Sewisy AA. Which data subset should be augmented for deep learning? a simulation study using urothelial cell carcinoma histopathology images. BMC Bioinformatics 2023; 24:75. [PMID: 36869300 PMCID: PMC9983182 DOI: 10.1186/s12859-023-05199-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2022] [Accepted: 02/21/2023] [Indexed: 03/05/2023] Open
Abstract
BACKGROUND Applying deep learning to digital histopathology is hindered by the scarcity of manually annotated datasets. While data augmentation can ameliorate this obstacle, its methods are far from standardized. Our aim was to systematically explore the effects of skipping data augmentation; applying data augmentation to different subsets of the whole dataset (training set, validation set, test set, two of them, or all of them); and applying data augmentation at different time points (before, during, or after dividing the dataset into three subsets). Different combinations of the above possibilities resulted in 11 ways to apply augmentation. The literature contains no such comprehensive systematic comparison of these augmentation ways. RESULTS Non-overlapping photographs of all tissues on 90 hematoxylin-and-eosin-stained urinary bladder slides were obtained. Then, they were manually classified as either inflammation (5948 images), urothelial cell carcinoma (5811 images), or invalid (3132 images; excluded). If done, augmentation was eight-fold by flipping and rotation. Four convolutional neural networks (Inception-v3, ResNet-101, GoogLeNet, and SqueezeNet), pre-trained on the ImageNet dataset, were fine-tuned to binary classify images of our dataset. This task was the benchmark for our experiments. Model testing performance was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve. Model validation accuracy was also estimated. The best testing performance was achieved when augmentation was done to the remaining data after test-set separation, but before division into training and validation sets. This leaked information between the training and the validation sets, as evidenced by the optimistic validation accuracy. However, this leakage did not cause the validation set to malfunction. Augmentation before test-set separation led to optimistic results. Test-set augmentation yielded more accurate evaluation metrics with less uncertainty. Inception-v3 had the best overall testing performance. CONCLUSIONS In digital histopathology, augmentation should include both the test set (after its allocation), and the remaining combined training/validation set (before being split into separate training and validation sets). Future research should try to generalize our results.
Collapse
Affiliation(s)
- Yusra A Ameen
- Department of Computer Science, Faculty of Computers and Information, Assiut University, Asyut, Egypt.
| | - Dalia M Badary
- Department of Pathology, Faculty of Medicine, Assiut University, Asyut, Egypt
| | | | - Khaled F Hussain
- Department of Computer Science, Faculty of Computers and Information, Assiut University, Asyut, Egypt
| | - Adel A Sewisy
- Department of Computer Science, Faculty of Computers and Information, Assiut University, Asyut, Egypt
| |
Collapse
|
17
|
Ultra-wide-field fundus photography compared to ophthalmoscopy in diagnosing and classifying major retinal diseases. Sci Rep 2022; 12:19287. [PMID: 36369463 PMCID: PMC9650656 DOI: 10.1038/s41598-022-23170-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Accepted: 10/26/2022] [Indexed: 11/13/2022] Open
Abstract
To analyze the performance of ultra-wide-field (UWF) fundus photography compared with ophthalmoscopy in identifying and classifying retinal diseases. Patients examined for presumed major retinal disorders were consecutively enrolled. Each patient underwent indirect ophthalmoscopic evaluation, with scleral depression and/or fundus biomicroscopy, when clinically indicated, and mydriatic UWF fundus imaging by means of CLARUS 500™ fundus camera. Each eye was classified by a clinical grader and two image graders in the following groups: normal retina, diabetic retinopathy, vascular abnormalities, macular degenerations and dystrophies, retinal and choroidal tumors, peripheral degenerative lesions and retinal detachment and myopic alterations. 7024 eyes of new patients were included. The inter-grader agreement for images classification was perfect (kappa = 0.998, 95% Confidence Interval (95%CI) = 0.997-0.999), as the two methods concordance for retinal diseases diagnosis (kappa = 0.997, 95%CI = 0.996-0.999) without statistically significant difference. UWF fundus imaging might be an alternative to ophthalmoscopy, since it allows to accurately classify major retinal diseases, widening the range of disorders possibly diagnosed with teleophthalmology. Although the clinician should be aware of the possibility that a minority of the most peripheral lesions may be not entirely visualized, it might be considered a first line diagnostic modality, in the context of a full ophthalmological examination.
Collapse
|
18
|
Li Z, Guo C, Nie D, Lin D, Cui T, Zhu Y, Chen C, Zhao L, Zhang X, Dongye M, Wang D, Xu F, Jin C, Zhang P, Han Y, Yan P, Lin H. Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning. Eye (Lond) 2022; 36:1681-1686. [PMID: 34345030 PMCID: PMC9307785 DOI: 10.1038/s41433-021-01715-7] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2021] [Revised: 07/14/2021] [Accepted: 07/22/2021] [Indexed: 01/20/2023] Open
Abstract
BACKGROUND Retinal exudates and/or drusen (RED) can be signs of many fundus diseases that can lead to irreversible vision loss. Early detection and treatment of these diseases are critical for improving vision prognosis. However, manual RED screening on a large scale is time-consuming and labour-intensive. Here, we aim to develop and assess a deep learning system for automated detection of RED using ultra-widefield fundus (UWF) images. METHODS A total of 26,409 UWF images from 14,994 subjects were used to develop and evaluate the deep learning system. The Zhongshan Ophthalmic Center (ZOC) dataset was selected to compare the performance of the system to that of retina specialists in RED detection. The saliency map visualization technique was used to understand which areas in the UWF image had the most influence on our deep learning system when detecting RED. RESULTS The system for RED detection achieved areas under the receiver operating characteristic curve of 0.994 (95% confidence interval [CI]: 0.991-0.996), 0.972 (95% CI: 0.957-0.984), and 0.988 (95% CI: 0.983-0.992) in three independent datasets. The performance of the system in the ZOC dataset was comparable to that of an experienced retina specialist. Regions of RED were highlighted by saliency maps in UWF images. CONCLUSIONS Our deep learning system is reliable in the automated detection of RED in UWF images. As a screening tool, our system may promote the early diagnosis and management of RED-related fundus diseases.
Collapse
Affiliation(s)
- Zhongwen Li
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Chong Guo
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Danyao Nie
- Shenzhen Eye Hospital, Shenzhen Key Laboratory of Ophthalmology, Affiliated Shenzhen Eye Hospital of Jinan University, Shenzhen, China
| | - Duoru Lin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Tingxin Cui
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Yi Zhu
- Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Chuan Chen
- Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Lanqin Zhao
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Xulin Zhang
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Meimei Dongye
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Dongni Wang
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Fabao Xu
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Chenjin Jin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Ping Zhang
- Xudong Ophthalmic Hospital, Inner Mongolia, China
| | - Yu Han
- EYE & ENT Hospital of Fudan University, Shanghai, China
| | - Pisong Yan
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
| | - Haotian Lin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China.
- Center for Precision Medicine, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
19
|
Bhambra N, Antaki F, Malt FE, Xu A, Duval R. Deep learning for ultra-widefield imaging: a scoping review. Graefes Arch Clin Exp Ophthalmol 2022; 260:3737-3778. [PMID: 35857087 DOI: 10.1007/s00417-022-05741-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2021] [Revised: 05/16/2022] [Accepted: 06/22/2022] [Indexed: 11/04/2022] Open
Abstract
PURPOSE This article is a scoping review of published and peer-reviewed articles using deep-learning (DL) applied to ultra-widefield (UWF) imaging. This study provides an overview of the published uses of DL and UWF imaging for the detection of ophthalmic and systemic diseases, generative image synthesis, quality assessment of images, and segmentation and localization of ophthalmic image features. METHODS A literature search was performed up to August 31st, 2021 using PubMed, Embase, Cochrane Library, and Google Scholar. The inclusion criteria were as follows: (1) deep learning, (2) ultra-widefield imaging. The exclusion criteria were as follows: (1) articles published in any language other than English, (2) articles not peer-reviewed (usually preprints), (3) no full-text availability, (4) articles using machine learning algorithms other than deep learning. No study design was excluded from consideration. RESULTS A total of 36 studies were included. Twenty-three studies discussed ophthalmic disease detection and classification, 5 discussed segmentation and localization of ultra-widefield images (UWFIs), 3 discussed generative image synthesis, 3 discussed ophthalmic image quality assessment, and 2 discussed detecting systemic diseases via UWF imaging. CONCLUSION The application of DL to UWF imaging has demonstrated significant effectiveness in the diagnosis and detection of ophthalmic diseases including diabetic retinopathy, retinal detachment, and glaucoma. DL has also been applied in the generation of synthetic ophthalmic images. This scoping review highlights and discusses the current uses of DL with UWF imaging, and the future of DL applications in this field.
Collapse
Affiliation(s)
- Nishaant Bhambra
- Faculty of Medicine, McGill University, Montréal, Québec, Canada
| | - Fares Antaki
- Department of Ophthalmology, Université de Montréal, Montréal, Québec, Canada.,Centre Universitaire d'Ophtalmologie (CUO), Hôpital Maisonneuve-Rosemont, CIUSSS de L'Est-de-L'Île-de-Montréal, 5415 Assumption Blvd, Montréal, Québec, H1T 2M4, Canada
| | - Farida El Malt
- Faculty of Medicine, McGill University, Montréal, Québec, Canada
| | - AnQi Xu
- Faculty of Medicine, Université de Montréal, Montréal, Québec, Canada
| | - Renaud Duval
- Department of Ophthalmology, Université de Montréal, Montréal, Québec, Canada. .,Centre Universitaire d'Ophtalmologie (CUO), Hôpital Maisonneuve-Rosemont, CIUSSS de L'Est-de-L'Île-de-Montréal, 5415 Assumption Blvd, Montréal, Québec, H1T 2M4, Canada.
| |
Collapse
|
20
|
Detection and Localization of Retinal Breaks in Ultra-Widefield Fundus Photography using a YOLO v3 Architecture-Based Deep Learning Model. Retina 2022; 42:1889-1896. [DOI: 10.1097/iae.0000000000003550] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
21
|
Lim JS, Hong M, Lam WST, Zhang Z, Teo ZL, Liu Y, Ng WY, Foo LL, Ting DSW. Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology. Curr Opin Ophthalmol 2022; 33:174-187. [PMID: 35266894 DOI: 10.1097/icu.0000000000000846] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
PURPOSE OF REVIEW The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each. RECENT FINDINGS Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks. SUMMARY AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.
Collapse
Affiliation(s)
- Jane S Lim
- Singapore National Eye Centre, Singapore Eye Research Institute
| | | | - Walter S T Lam
- Yong Loo Lin School of Medicine, National University of Singapore
| | - Zheting Zhang
- Lee Kong Chian School of Medicine, Nanyang Technological University
| | - Zhen Ling Teo
- Singapore National Eye Centre, Singapore Eye Research Institute
| | - Yong Liu
- National University of Singapore, DukeNUS Medical School, Singapore
| | - Wei Yan Ng
- Singapore National Eye Centre, Singapore Eye Research Institute
| | - Li Lian Foo
- Singapore National Eye Centre, Singapore Eye Research Institute
| | - Daniel S W Ting
- Singapore National Eye Centre, Singapore Eye Research Institute
| |
Collapse
|
22
|
Li Z, Qiang W, Chen H, Pei M, Yu X, Wang L, Li Z, Xie W, Wu X, Jiang J, Wu G. Artificial intelligence to detect malignant eyelid tumors from photographic images. NPJ Digit Med 2022; 5:23. [PMID: 35236921 PMCID: PMC8891262 DOI: 10.1038/s41746-022-00571-3] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Accepted: 02/04/2022] [Indexed: 11/23/2022] Open
Abstract
Malignant eyelid tumors can invade adjacent structures and pose a threat to vision and even life. Early identification of malignant eyelid tumors is crucial to avoiding substantial morbidity and mortality. However, differentiating malignant eyelid tumors from benign ones can be challenging for primary care physicians and even some ophthalmologists. Here, based on 1,417 photographic images from 851 patients across three hospitals, we developed an artificial intelligence system using a faster region-based convolutional neural network and deep learning classification networks to automatically locate eyelid tumors and then distinguish between malignant and benign eyelid tumors. The system performed well in both internal and external test sets (AUCs ranged from 0.899 to 0.955). The performance of the system is comparable to that of a senior ophthalmologist, indicating that this system has the potential to be used at the screening stage for promoting the early detection and treatment of malignant eyelid tumors.
Collapse
Affiliation(s)
- Zhongwen Li
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China.
- School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China.
| | - Wei Qiang
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Hongyun Chen
- Zunyi First People's Hospital, Zunyi Medical University, Zunyi, 563000, China
| | - Mengjie Pei
- School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, 710121, China
| | - Xiaomei Yu
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Layi Wang
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Zhen Li
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Weiwei Xie
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Xuefang Wu
- Guizhou Provincial People's Hospital, Guizhou University, Guizhou, 550002, China
| | - Jiewei Jiang
- School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an, 710121, China.
| | - Guohai Wu
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China.
| |
Collapse
|
23
|
Li Z, Jiang J, Qiang W, Guo L, Liu X, Weng H, Wu S, Zheng Q, Chen W. Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images. iScience 2021; 24:103317. [PMID: 34778732 PMCID: PMC8577078 DOI: 10.1016/j.isci.2021.103317] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2021] [Revised: 10/11/2021] [Accepted: 10/15/2021] [Indexed: 01/01/2023] Open
Abstract
The performance of deep learning in disease detection from high-quality clinical images is identical to and even greater than that of human doctors. However, in low-quality images, deep learning performs poorly. Whether human doctors also have poor performance in low-quality images is unknown. Here, we compared the performance of deep learning systems with that of cornea specialists in detecting corneal diseases from low-quality slit lamp images. The results showed that the cornea specialists performed better than our previously established deep learning system (PEDLS) trained on only high-quality images. The performance of the system trained on both high- and low-quality images was superior to that of the PEDLS while inferior to that of a senior corneal specialist. This study highlights that cornea specialists perform better in low-quality images than the system trained on high-quality images. Adding low-quality images with sufficient diagnostic certainty to the training set can reduce this performance gap. Deep learning performs poorly in low-quality images for detecting corneal diseases Corneal specialists perform better than the PEDLS in low-quality images The performance of the NDLS is better than that of the PEDLS in low-quality images Adding low-quality images to the training set can improve the system's performance
Collapse
Affiliation(s)
- Zhongwen Li
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China.,School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China
| | - Jiewei Jiang
- School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
| | - Wei Qiang
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China
| | - Liufei Guo
- School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
| | - Xiaotian Liu
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China
| | - Hongfei Weng
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China
| | - Shanjun Wu
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China
| | - Qinxiang Zheng
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China.,School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China
| | - Wei Chen
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315000, China.,School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China
| |
Collapse
|
24
|
Foo LL, Ng WY, Lim GYS, Tan TE, Ang M, Ting DSW. Artificial intelligence in myopia: current and future trends. Curr Opin Ophthalmol 2021; 32:413-424. [PMID: 34310401 DOI: 10.1097/icu.0000000000000791] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
PURPOSE OF REVIEW Myopia is one of the leading causes of visual impairment, with a projected increase in prevalence globally. One potential approach to address myopia and its complications is early detection and treatment. However, current healthcare systems may not be able to cope with the growing burden. Digital technological solutions such as artificial intelligence (AI) have emerged as a potential adjunct for myopia management. RECENT FINDINGS There are currently four significant domains of AI in myopia, including machine learning (ML), deep learning (DL), genetics and natural language processing (NLP). ML has been demonstrated to be a useful adjunctive for myopia prediction and biometry for cataract surgery in highly myopic individuals. DL techniques, particularly convoluted neural networks, have been applied to various image-related diagnostic and predictive solutions. Applications of AI in genomics and NLP appear to be at a nascent stage. SUMMARY Current AI research is mainly focused on disease classification and prediction in myopia. Through greater collaborative research, we envision AI will play an increasingly critical role in big data analysis by aggregating a greater variety of parameters including genomics and environmental factors. This may enable the development of generalizable adjunctive DL systems that could help realize predictive and individualized precision medicine for myopic patients.
Collapse
Affiliation(s)
- Li Lian Foo
- Singapore National Eye Centre, Singapore Eye Research Institute
- Duke-NUS Medical School, National University of Singapore, Singapore, Singapore
| | - Wei Yan Ng
- Singapore National Eye Centre, Singapore Eye Research Institute
- Duke-NUS Medical School, National University of Singapore, Singapore, Singapore
| | | | - Tien-En Tan
- Singapore National Eye Centre, Singapore Eye Research Institute
| | - Marcus Ang
- Singapore National Eye Centre, Singapore Eye Research Institute
- Duke-NUS Medical School, National University of Singapore, Singapore, Singapore
| | - Daniel Shu Wei Ting
- Singapore National Eye Centre, Singapore Eye Research Institute
- Duke-NUS Medical School, National University of Singapore, Singapore, Singapore
| |
Collapse
|
25
|
Lin D, Xiong J, Liu C, Zhao L, Li Z, Yu S, Wu X, Ge Z, Hu X, Wang B, Fu M, Zhao X, Wang X, Zhu Y, Chen C, Li T, Li Y, Wei W, Zhao M, Li J, Xu F, Ding L, Tan G, Xiang Y, Hu Y, Zhang P, Han Y, Li JPO, Wei L, Zhu P, Liu Y, Chen W, Ting DSW, Wong TY, Chen Y, Lin H. Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system: a national real-world evidence study. LANCET DIGITAL HEALTH 2021; 3:e486-e495. [PMID: 34325853 DOI: 10.1016/s2589-7500(21)00086-8] [Citation(s) in RCA: 52] [Impact Index Per Article: 17.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Revised: 04/21/2021] [Accepted: 05/07/2021] [Indexed: 12/15/2022]
Abstract
BACKGROUND Medical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS for fundus diseases using data derived from the real world, and externally test the model using fundus photographs collected prospectively from the settings in which the model would most likely be adopted. METHODS In this national real-world evidence study, we trained a DLS, the Comprehensive AI Retinal Expert (CARE) system, to identify the 14 most common retinal abnormalities using 207 228 colour fundus photographs derived from 16 clinical settings with different disease distributions. CARE was internally validated using 21 867 photographs and externally tested using 18 136 photographs prospectively collected from 35 real-world settings across China where CARE might be adopted, including eight tertiary hospitals, six community hospitals, and 21 physical examination centres. The performance of CARE was further compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types. This study was registered with ClinicalTrials.gov, NCT04213430, and is currently closed. FINDINGS The area under the receiver operating characteristic curve (AUC) in the internal validation set was 0·955 (SD 0·046). AUC values in the external test set were 0·965 (0·035) in tertiary hospitals, 0·983 (0·031) in community hospitals, and 0·953 (0·042) in physical examination centres. The performance of CARE was similar to that of ophthalmologists. Large variations in sensitivity were observed among the ophthalmologists in different regions and with varying experience. The system retained strong identification performance when tested using the non-Chinese dataset (AUC 0·960, 95% CI 0·957-0·964 in referable diabetic retinopathy). INTERPRETATION Our DLS (CARE) showed satisfactory performance for screening multiple retinal abnormalities in real-world settings using prospectively collected fundus photographs, and so could allow the system to be implemented and adopted for clinical care. FUNDING This study was funded by the National Key R&D Programme of China, the Science and Technology Planning Projects of Guangdong Province, the National Natural Science Foundation of China, the Natural Science Foundation of Guangdong Province, and the Fundamental Research Funds for the Central Universities. TRANSLATION For the Chinese translation of the abstract see Supplementary Materials section.
Collapse
Affiliation(s)
- Duoru Lin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Jianhao Xiong
- Beijing Eaglevision Technology Development, Beijing, China
| | - Congxin Liu
- Beijing Eaglevision Technology Development, Beijing, China
| | - Lanqin Zhao
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Zhongwen Li
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Shanshan Yu
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Xiaohang Wu
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Zongyuan Ge
- Department of Electrical and Computer Systems Engineering, Faculty of Engineering, Monash University, Melbourne, VIC, Australia
| | - Xinyue Hu
- Beijing Eaglevision Technology Development, Beijing, China
| | - Bin Wang
- Beijing Eaglevision Technology Development, Beijing, China
| | - Meng Fu
- Beijing Eaglevision Technology Development, Beijing, China
| | - Xin Zhao
- Beijing Eaglevision Technology Development, Beijing, China
| | - Xin Wang
- Centre for Precision Medicine, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Yi Zhu
- Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Chuan Chen
- Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Tao Li
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Yonghao Li
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Wenbin Wei
- Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Mingwei Zhao
- Department of Ophthalmology, Ophthalmology and Optometry Centre, Peking University People's Hospital, Beijing, China
| | - Jianqiao Li
- Department of Ophthalmology, Qilu Hospital of Shandong University, Jinan, Shandong, China
| | - Fan Xu
- Department of Ophthalmology, People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, Guangxi, China
| | - Lin Ding
- Department of Ophthalmology, People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi, Shanxi, China
| | - Gang Tan
- Department of Ophthalmology, University of South China, Hengyang, Hunan, China
| | - Yi Xiang
- Department of Ophthalmology, The Central Hospital of Wuhan, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Yongcheng Hu
- Bayannur Paralympic Eye Hospital, Bayannur, Inner Mongolia, China
| | - Ping Zhang
- Bayannur Paralympic Eye Hospital, Bayannur, Inner Mongolia, China
| | - Yu Han
- Department of Ophthalmology, Eye and ENT Hospital, Fudan University, Shanghai, China
| | | | - Lai Wei
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Pengzhi Zhu
- Guangdong Medical Devices Quality Surveillance and Test Institute, Guangzhou, Guangdong, China
| | - Yizhi Liu
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Weirong Chen
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Daniel S W Ting
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Tien Y Wong
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Yuzhong Chen
- Beijing Eaglevision Technology Development, Beijing, China.
| | - Haotian Lin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China; Centre for Precision Medicine, Sun Yat-sen University, Guangzhou, Guangdong, China.
| |
Collapse
|
26
|
Preventing corneal blindness caused by keratitis using artificial intelligence. Nat Commun 2021; 12:3738. [PMID: 34145294 PMCID: PMC8213803 DOI: 10.1038/s41467-021-24116-6] [Citation(s) in RCA: 42] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2020] [Accepted: 06/01/2021] [Indexed: 12/14/2022] Open
Abstract
Keratitis is the main cause of corneal blindness worldwide. Most vision loss caused by keratitis can be avoidable via early detection and treatment. The diagnosis of keratitis often requires skilled ophthalmologists. However, the world is short of ophthalmologists, especially in resource-limited settings, making the early diagnosis of keratitis challenging. Here, we develop a deep learning system for the automated classification of keratitis, other cornea abnormalities, and normal cornea based on 6,567 slit-lamp images. Our system exhibits remarkable performance in cornea images captured by the different types of digital slit lamp cameras and a smartphone with the super macro mode (all AUCs>0.96). The comparable sensitivity and specificity in keratitis detection are observed between the system and experienced cornea specialists. Our system has the potential to be applied to both digital slit lamp cameras and smartphones to promote the early diagnosis and treatment of keratitis, preventing the corneal blindness caused by keratitis.
Collapse
|
27
|
Li JPO, Liu H, Ting DSJ, Jeon S, Chan RVP, Kim JE, Sim DA, Thomas PBM, Lin H, Chen Y, Sakomoto T, Loewenstein A, Lam DSC, Pasquale LR, Wong TY, Lam LA, Ting DSW. Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective. Prog Retin Eye Res 2021; 82:100900. [PMID: 32898686 PMCID: PMC7474840 DOI: 10.1016/j.preteyeres.2020.100900] [Citation(s) in RCA: 201] [Impact Index Per Article: 67.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2020] [Revised: 08/25/2020] [Accepted: 08/31/2020] [Indexed: 12/29/2022]
Abstract
The simultaneous maturation of multiple digital and telecommunications technologies in 2020 has created an unprecedented opportunity for ophthalmology to adapt to new models of care using tele-health supported by digital innovations. These digital innovations include artificial intelligence (AI), 5th generation (5G) telecommunication networks and the Internet of Things (IoT), creating an inter-dependent ecosystem offering opportunities to develop new models of eye care addressing the challenges of COVID-19 and beyond. Ophthalmology has thrived in some of these areas partly due to its many image-based investigations. Tele-health and AI provide synchronous solutions to challenges facing ophthalmologists and healthcare providers worldwide. This article reviews how countries across the world have utilised these digital innovations to tackle diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration, glaucoma, refractive error correction, cataract and other anterior segment disorders. The review summarises the digital strategies that countries are developing and discusses technologies that may increasingly enter the clinical workflow and processes of ophthalmologists. Furthermore as countries around the world have initiated a series of escalating containment and mitigation measures during the COVID-19 pandemic, the delivery of eye care services globally has been significantly impacted. As ophthalmic services adapt and form a "new normal", the rapid adoption of some of telehealth and digital innovation during the pandemic is also discussed. Finally, challenges for validation and clinical implementation are considered, as well as recommendations on future directions.
Collapse
Affiliation(s)
- Ji-Peng Olivia Li
- Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
| | - Hanruo Liu
- Beijing Tongren Hospital; Capital Medical University; Beijing Institute of Ophthalmology; Beijing, China
| | - Darren S J Ting
- Academic Ophthalmology, University of Nottingham, United Kingdom
| | - Sohee Jeon
- Keye Eye Center, Seoul, Republic of Korea
| | | | - Judy E Kim
- Medical College of Wisconsin, Milwaukee, WI, USA
| | - Dawn A Sim
- NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, United Kingdom
| | - Peter B M Thomas
- NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, United Kingdom
| | - Haotian Lin
- Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, China
| | - Youxin Chen
- Peking Union Medical College Hospital, Beijing, China
| | - Taiji Sakomoto
- Department of Ophthalmology, Kagoshima University Graduate School of Medical and Dental Sciences, Japan
| | | | - Dennis S C Lam
- C-MER Dennis Lam Eye Center, C-Mer International Eye Care Group Limited, Hong Kong, Hong Kong; International Eye Research Institute of the Chinese University of Hong Kong (Shenzhen), Shenzhen, China
| | - Louis R Pasquale
- Department of Ophthalmology, Icahn School of Medicine at Mount Sinai, New York, USA
| | - Tien Y Wong
- Singapore National Eye Center, Duke-NUS Medical School Singapore, Singapore
| | - Linda A Lam
- USC Roski Eye Institute, University of Southern California (USC) Keck School of Medicine, Los Angeles, CA, USA
| | - Daniel S W Ting
- Singapore National Eye Center, Duke-NUS Medical School Singapore, Singapore.
| |
Collapse
|
28
|
Li Z, Jiang J, Chen K, Zheng Q, Liu X, Weng H, Wu S, Chen W. Development of a deep learning-based image quality control system to detect and filter out ineligible slit-lamp images: A multicenter study. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 203:106048. [PMID: 33765481 DOI: 10.1016/j.cmpb.2021.106048] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/15/2020] [Accepted: 03/08/2021] [Indexed: 06/12/2023]
Abstract
BACKGROUND AND OBJECTIVE Previous studies developed artificial intelligence (AI) diagnostic systems only using eligible slit-lamp images for detecting corneal diseases. However, images of ineligible quality (including poor-field, defocused, and poor-location images), which are inevitable in the real world, can cause diagnostic information loss and thus affect downstream AI-based image analysis. Manual evaluation for the eligibility of slit-lamp images often requires an ophthalmologist, and this procedure can be time-consuming and labor-intensive when applied on a large scale. Here, we aimed to develop a deep learning-based image quality control system (DLIQCS) to automatically detect and filter out ineligible slit-lamp images (poor-field, defocused, and poor-location images). METHODS We developed and externally evaluated the DLIQCS based on 48,530 slit-lamp images (19,890 individuals) that were derived from 4 independent institutions using different types of digital slit lamp cameras. To find the best deep learning model for the DLIQCS, we used 3 algorithms (AlexNet, DenseNet121, and InceptionV3) to train models. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy were leveraged to assess the performance of each algorithm for the classification of poor-field, defocused, poor-location, and eligible images. RESULTS In an internal test dataset, the best algorithm DenseNet121 had AUCs of 0.999, 1.000, 1.000, and 1.000 in the detection of poor-field, defocused, poor-location, and eligible images, respectively. In external test datasets, the AUCs of the best algorithm DenseNet121 for identifying poor-field, defocused, poor-location, and eligible images were ranged from 0.997 to 0.997, 0.983 to 0.995, 0.995 to 0.998, and 0.999 to 0.999, respectively. CONCLUSIONS Our DLIQCS can accurately detect poor-field, defocused, poor-location, and eligible slit-lamp images in an automated fashion. This system may serve as a prescreening tool to filter out ineligible images and enable that only eligible images would be transferred to the subsequent AI diagnostic systems.
Collapse
Affiliation(s)
- Zhongwen Li
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China; School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China
| | - Jiewei Jiang
- School of Electronics Engineering, Xi'an University of Posts and Telecommunications, Xi'an, 710121, China
| | - Kuan Chen
- School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China
| | - Qinxiang Zheng
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China; School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China
| | - Xiaotian Liu
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Hongfei Weng
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China
| | - Shanjun Wu
- School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China
| | - Wei Chen
- Ningbo Eye Hospital, Wenzhou Medical University, Ningbo, 315000, China; School of Ophthalmology and Optometry and Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China.
| |
Collapse
|
29
|
Foo LL, Ang M, Wong CW, Ohno-Matsui K, Saw SM, Wong TY, Ting DS. Is artificial intelligence a solution to the myopia pandemic? Br J Ophthalmol 2021; 105:741-744. [PMID: 33712483 DOI: 10.1136/bjophthalmol-2021-319129] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Affiliation(s)
- Li Lian Foo
- Singapore National Eye Centre, Singapore.,Ophthalmology and Visual Sciences Department, Duke-NUS, Singapore.,Singapore Eye Research Institute, Singapore
| | - Marcus Ang
- Singapore National Eye Centre, Singapore.,Ophthalmology and Visual Sciences Department, Duke-NUS, Singapore.,Singapore Eye Research Institute, Singapore
| | - Chee Wai Wong
- Singapore National Eye Centre, Singapore.,Ophthalmology and Visual Sciences Department, Duke-NUS, Singapore.,Singapore Eye Research Institute, Singapore
| | - Kyoko Ohno-Matsui
- Ophthalmology and Visual Science, Tokyo Medical and Dental University, Bunkyo-ku, Japan
| | | | - Tien Yin Wong
- Singapore National Eye Centre, Singapore.,Ophthalmology and Visual Sciences Department, Duke-NUS, Singapore.,Singapore Eye Research Institute, Singapore
| | - Daniel S Ting
- Singapore National Eye Centre, Singapore .,Ophthalmology and Visual Sciences Department, Duke-NUS, Singapore.,Singapore Eye Research Institute, Singapore
| |
Collapse
|
30
|
Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study. Graefes Arch Clin Exp Ophthalmol 2021; 259:2225-2234. [PMID: 33538890 DOI: 10.1007/s00417-021-05105-3] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2020] [Revised: 01/10/2021] [Accepted: 01/26/2021] [Indexed: 10/22/2022] Open
Abstract
PURPOSE To investigate the detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus imaging system (Optos) with convolutional neural network technology. METHODS This study included 1500 Optos color images for tessellated fundus confirmation and peripheral retinal lesion (lattice degeneration, retinal breaks, and retinal detachment) assessment. Three retinal specialists evaluated all images and proposed the reference standard when an agreement was achieved. Then, 722 images were used to train and verify a combined deep-learning system of 3 optimal binary classification models trained using seResNext50 algorithm with 2 preprocessing methods (original resizing and cropping), and a test set of 189 images were applied to verify the performance compared to the reference standard. RESULTS With optimal preprocessing approach (original resizing method for lattice degeneration and retinal detachment, cropping method for retinal breaks), the combined deep-learning system exhibited an area under curve of 0.888, 0.953, and 1.000 for detection of lattice degeneration, retinal breaks, and retinal detachment respectively in tessellated eyes. The referral accuracy of this system was 79.8% compared to the reference standard. CONCLUSION A deep-learning system is feasible to detect lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field images. And this system may be considered for screening and telemedicine.
Collapse
|
31
|
Li Z, Guo C, Nie D, Lin D, Zhu Y, Chen C, Zhao L, Wu X, Dongye M, Xu F, Jin C, Zhang P, Han Y, Yan P, Lin H. Deep learning from "passive feeding" to "selective eating" of real-world data. NPJ Digit Med 2020; 3:143. [PMID: 33145439 PMCID: PMC7603327 DOI: 10.1038/s41746-020-00350-y] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2020] [Accepted: 09/24/2020] [Indexed: 12/23/2022] Open
Abstract
Artificial intelligence (AI) based on deep learning has shown excellent diagnostic performance in detecting various diseases with good-quality clinical images. Recently, AI diagnostic systems developed from ultra-widefield fundus (UWF) images have become popular standard-of-care tools in screening for ocular fundus diseases. However, in real-world settings, these systems must base their diagnoses on images with uncontrolled quality ("passive feeding"), leading to uncertainty about their performance. Here, using 40,562 UWF images, we develop a deep learning-based image filtering system (DLIFS) for detecting and filtering out poor-quality images in an automated fashion such that only good-quality images are transferred to the subsequent AI diagnostic system ("selective eating"). In three independent datasets from different clinical institutions, the DLIFS performed well with sensitivities of 96.9%, 95.6% and 96.6%, and specificities of 96.6%, 97.9% and 98.8%, respectively. Furthermore, we show that the application of our DLIFS significantly improves the performance of established AI diagnostic systems in real-world settings. Our work demonstrates that "selective eating" of real-world data is necessary and needs to be considered in the development of image-based AI systems.
Collapse
Affiliation(s)
- Zhongwen Li
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Chong Guo
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Danyao Nie
- Shenzhen Eye Hospital, Shenzhen Key Laboratory of Ophthalmology, Affiliated Shenzhen Eye Hospital of Jinan University, 518001 Shenzhen, China
| | - Duoru Lin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Yi Zhu
- Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, Miami, FL 33136 USA
| | - Chuan Chen
- Sylvester Comprehensive Cancer Centre, University of Miami Miller School of Medicine, Miami, FL 33136 USA
| | - Lanqin Zhao
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Xiaohang Wu
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Meimei Dongye
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Fabao Xu
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Chenjin Jin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Ping Zhang
- Xudong Ophthalmic Hospital, 015000 Inner Mongolia, China
| | - Yu Han
- EYE and ENT Hospital of Fudan University, 200031 Shanghai, China
| | - Pisong Yan
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
| | - Haotian Lin
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, 510060 Guangzhou, China
- Centre for Precision Medicine, Sun Yat-sen University, 510060 Guangzhou, China
| |
Collapse
|
32
|
Li Z, Guo C, Lin D, Nie D, Zhu Y, Chen C, Zhao L, Wang J, Zhang X, Dongye M, Wang D, Xu F, Jin C, Zhang P, Han Y, Yan P, Han Y, Lin H. Deep learning for automated glaucomatous optic neuropathy detection from ultra-widefield fundus images. Br J Ophthalmol 2020; 105:1548-1554. [DOI: 10.1136/bjophthalmol-2020-317327] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2020] [Revised: 08/22/2020] [Accepted: 08/25/2020] [Indexed: 12/28/2022]
Abstract
Background/AimsTo develop a deep learning system for automated glaucomatous optic neuropathy (GON) detection using ultra-widefield fundus (UWF) images.MethodsWe trained, validated and externally evaluated a deep learning system for GON detection based on 22 972 UWF images from 10 590 subjects that were collected at 4 different institutions in China and Japan. The InceptionResNetV2 neural network architecture was used to develop the system. The area under the receiver operating characteristic curve (AUC), sensitivity and specificity were used to assess the performance of detecting GON by the system. The data set from the Zhongshan Ophthalmic Center (ZOC) was selected to compare the performance of the system to that of ophthalmologists who mainly conducted UWF image analysis in clinics.ResultsThe system for GON detection achieved AUCs of 0.983–0.999 with sensitivities of 97.5–98.2% and specificities of 94.3–98.4% in four independent data sets. The most common reasons for false-negative results were confounding optic disc characteristics caused by high myopia or pathological myopia (n=39 (53%)). The leading cause for false-positive results was having other fundus lesions (n=401 (96%)). The performance of the system in the ZOC data set was comparable to that of an experienced ophthalmologist (p>0.05).ConclusionOur deep learning system can accurately detect GON from UWF images in an automated fashion. It may be used as a screening tool to improve the accessibility of screening and promote the early diagnosis and management of glaucoma.
Collapse
|
33
|
Interpretation of artificial intelligence studies for the ophthalmologist. Curr Opin Ophthalmol 2020; 31:351-356. [PMID: 32740068 DOI: 10.1097/icu.0000000000000695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
PURPOSE OF REVIEW The use of artificial intelligence (AI) in ophthalmology has increased dramatically. However, interpretation of these studies can be a daunting prospect for the ophthalmologist without a background in computer or data science. This review aims to share some practical considerations for interpretation of AI studies in ophthalmology. RECENT FINDINGS It can be easy to get lost in the technical details of studies involving AI. Nevertheless, it is important for clinicians to remember that the fundamental questions in interpreting these studies remain unchanged - What does this study show, and how does this affect my patients? Being guided by familiar principles like study purpose, impact, validity, and generalizability, these studies become more accessible to the ophthalmologist. Although it may not be necessary for nondomain experts to understand the exact AI technical details, we explain some broad concepts in relation to AI technical architecture and dataset management. SUMMARY The expansion of AI into healthcare and ophthalmology is here to stay. AI systems have made the transition from bench to bedside, and are already being applied to patient care. In this context, 'AI education' is crucial for ophthalmologists to be confident in interpretation and translation of new developments in this field to their own clinical practice.
Collapse
|
34
|
Abstract
PURPOSE OF REVIEW As artificial intelligence continues to develop new applications in ophthalmic image recognition, we provide here an introduction for ophthalmologists and a primer on the mechanisms of deep learning systems. RECENT FINDINGS Deep learning has lent itself to the automated interpretation of various retinal imaging modalities, including fundus photography and optical coherence tomography. Convolutional neural networks (CNN) represent the primary class of deep neural networks applied to these image analyses. These have been configured to aid in the detection of diabetes retinopathy, AMD, retinal detachment, glaucoma, and ROP, among other ocular disorders. Predictive models for retinal disease prognosis and treatment are also being validated. SUMMARY Deep learning systems have begun to demonstrate a reliable level of diagnostic accuracy equal or better to human graders for narrow image recognition tasks. However, challenges regarding the use of deep learning systems in ophthalmology remain. These include trust of unsupervised learning systems and the limited ability to recognize broad ranges of disorders.
Collapse
|