Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes

@article{Ting2017DevelopmentAV,
  title={Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes},
  author={Daniel Shu Wei Ting and Carol Yim-lui Cheung and Gilbert Lim and Gavin Siew Wei Tan and Nguyen Duc Quang and Alfred Tau Liang Gan and Haslina Hamzah and Renata Garcia-Franco and Ian Yew San Yeo and Shu-Yen Lee and Edmund Yick Mun Wong and Charumathi Sabanayagam and Mani Baskaran and Farah Ibrahim and Ngiap Chuan Tan and Eric Andrew Finkelstein and Ecosse Luc Lamoureux and Ian Y Wong and Neil M. Bressler and Sobha Sivaprasad and Rohit Varma and Jost Bruno Jonas and Mingguang He and Ching-Yu Cheng and Gemmy Chui Ming Cheung and Tin Aung and Wynne Hsu and Mong Li Lee and Tien Yin Wong},
  journal={JAMA},
  year={2017},
  volume={318},
  pages={2211–2223}
}
Importance A deep learning system (DLS) is a machine learning technology with potential for screening diabetic retinopathy and related eye diseases. [...] Key Method A DLS was trained for detecting diabetic retinopathy (using 76 370 images), possible glaucoma (125 189 images), and AMD (72 610 images), and performance of DLS was evaluated for detecting diabetic retinopathy (using 112 648 images), possible glaucoma (71 896 images), and AMD (35 948 images).Expand
A deep learning system for detecting diabetic retinopathy across the disease spectrum
TLDR
A deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy and grading as mild, moderate, severe and proliferative achieves area under the curves of 0.943, 0.960 and 0.970, which supports the system is efficient for diabetic Retinopathy grading. Expand
Application of deep learning image assessment software VeriSee™ for diabetic retinopathy screening.
TLDR
VeriSee™ had good sensitivity and specificity in grading the severity of DR from color fundus images and may offer clinical assistance to non-ophthalmologists in DR screening with nonmydriatic retinal fundus photography. Expand
Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography
  • Bing Li, Huan Chen, +12 authors Weihong Yu
  • Medicine
  • The British journal of ophthalmology
  • 2021
TLDR
The proposed DLS is effective in diagnosing normal fundus and 12 major fundus diseases, and thus has much potential for fundus Diseases screening in the real world. Expand
Predicting Risk of Developing Diabetic Retinopathy using Deep Learning
TLDR
The deep-learning systems predicted diabetic retinopathy development using colour fundus photographs, and the systems were independent of and more informative than available risk factors. Expand
Validation of a Deep Learning Algorithm for Diabetic Retinopathy.
TLDR
The deep learning algorithm (DLA) used to read diabetic retinopathy (DR) retinographies can be used as a high confidence diagnostic tool to help in DR screening, especially when it might be difficult for ophthalmologists or other professionals to identify. Expand
Deep learning for diabetic retinopathy detection and classification based on fundus images: A review
TLDR
A thorough analysis of the use of deep learning methods at the various steps of the diabetic retinopathy detection pipeline based on fundus retina images and discusses certain models that have been applied in real clinical settings. Expand
Deep learning-based automated detection for diabetic retinopathy and diabetic macular oedema in retinal fundus photographs
TLDR
This study showed that the deep ensemble model exhibited excellent performance in detecting DR and DMO, and had good robustness and generalization, which could potentially help support and expand DR/DMO screening programs. Expand
Development of Decision Support Software for Deep Learning-Based Automated Retinal Disease Screening Using Relatively Limited Fundus Photograph Data
TLDR
An automated detection algorithm for screening fundus abnormalities, including age-related macular degeneration, diabetic retinopathy, epiretinal membrane, retinal vascular occlusion, and suspected glaucoma among health screening program participants was developed. Expand
Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading
TLDR
It is suggested that a deep learning system could increase the cost-effectiveness of screening and diagnosis, while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading. Expand
Development and Validation of a Deep Learning System to Detect Glaucomatous Optic Neuropathy Using Fundus Photographs.
TLDR
Application of GD-CNN to fundus images from different settings and varying image quality demonstrated a high sensitivity, specificity, and generalizability for detecting GON, suggesting that automated DLS could enhance current screening programs in a cost-effective and time-efficient manner. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 50 REFERENCES
Automated Identification of Diabetic Retinopathy Using Deep Learning.
TLDR
A fully data-driven artificial intelligence-based grading algorithm can be used to screen fundus photographs obtained from diabetic patients and to identify, with high reliability, which cases should be referred to an ophthalmologist for further evaluation and treatment. Expand
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.
TLDR
An algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and diabetic macular edema in retinal fundus photographs from adults with diabetes. Expand
Artificial Intelligence With Deep Learning Technology Looks Into Diabetic Retinopathy Screening.
TLDR
Deep learning has substantial potential for health care and may allow the identification of which patients are likely to develop a particular disease and, among those with a particular condition, which patients need to be seen more frequently and perhaps treated more aggressively and determination of what specific treatments may be most appropriate for these patients. Expand
Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep Learning.
TLDR
A deep-learning enhanced algorithm for the automated detection of DR, achieves significantly better performance than a previously reported, otherwise essentially identical, algorithm that does not employ deep learning. Expand
Automated early detection of diabetic retinopathy.
TLDR
Diabetic retinopathy detection algorithms seem to be maturing, and further improvements in detection performance cannot be differentiated from best clinical practices, because the performance of competitive algorithm development now has reached the human intrareader variability limit. Expand
Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders.
TLDR
Retmarker and EyeArt systems achieved acceptable sensitivity for referable retinopathy when compared with that of human graders and had sufficient specificity to make them cost-effective alternatives to manual grading alone. Expand
Telemedicine for Diabetic Retinopathy Screening.
TLDR
The North Carolina Diabetic Retinopathy Telemedicine Network has been set up to serve the rural population of people with diabetes in North Carolina who have limited access to DR screening services and has reduced the longdistance travel requirement for DR screening by more than 90% and has improved the DR screening rate in the North Carolina region from 25.6% to 40.4%. Expand
Prevalence and determinants of undiagnosed diabetic retinopathy and vision-threatening retinopathy in a multiethnic Asian cohort: the Singapore Epidemiology of Eye Diseases (SEED) study
TLDR
It is suggested that screening for diabetes is successful, while screening for DR is currently inadequate in this population, and public health strategies to aid early diagnosis of DR in Singapore are urgently warranted to reduce blindness due to diabetes. Expand
Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales.
TLDR
There seems to be a genuine need for consistent international clinical classification systems for diabetic retinopathy and diabetic macular edema that are supported with solid evidence. Expand
Should We Add Screening of Age-Related Macular Degeneration to Current Screening Programs for Diabetic Retinopathy?
The report by Chan et al 1 in the current issue (p. 2278) details how screening for both diabetic retinopathy and age-related macular degeneration (AMD) can be conducted using fundus photographsExpand
...
1
2
3
4
5
...