A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images

Li, Zhongwen; Guo, Chong; Nie, Danyao; Lin, Duoru; Zhu, Yi; Chen, Chuan; Zhang, Li; Xu, Fabao; Jin, Chenjin; Zhang, Xiayin; Xiao, Hui; Zhang, Kai; Zhao, Lanqin; Yu, Shanshan; Zhang, Guoming; Wang, Jiantao; Lin, Haotian

doi:10.21037/atm.2019.11.28

Cited by 44 publications

(42 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other retinal abnormalities, such as macro aneurysms and retinoblastoma, will be added in our future studies. Furthermore, because of the limitation of traditional fundus photographs with limited visible scope, 27 CARE is not able to identify peripheral retinal pathologies. In addition, only a few diseases were included in the performance comparison between CARE and the ophthalmologists and the tests with non-Chinese ethnicities and unseen camera types.…”

Section: Discussionmentioning

confidence: 99%

Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system: a national real-world evidence study

Lin

Xiong

Liu

et al. 2021

The Lancet Digital Health

Self Cite

View full text Add to dashboard Cite

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. FindingsThe 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.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system: a national real-world evidence study

Lin

Xiong

Liu

et al. 2021

The Lancet Digital Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DLIFS was trained by a state-of-the-art deep convolutional neural network (CNN) architecture, InceptionResNetV2, which combines the architectural characteristics of ResNet and Inception, including skip connection and variable kernel sizes, and results in a more performant architecture than the two predecessors 38 . Our previous study also has demonstrated that the InceptionResNetV2 is the best algorithm for developing an AI system based on UWF images when compared to other three state-of-the-art algorithms (InceptionV3, ResNet50 and VGG16) 19 . Weights pretrained for ImageNet classification were applied to initialise the CNN architectures 39 .…”

Section: Methodsmentioning

confidence: 93%

“…Because retinal hard exudation is difficult to distinguish from drusen based on appearance alone and because cases with each of these conditions should be referred, we assigned them to the same group. Methods for developing a deep learning system to detect LDRB were described in our previous study 19 . For GON detection, images were classified into two categories: GON and non-GON.…”

Section: Methodsmentioning

confidence: 99%

Deep learning from “passive feeding” to “selective eating” of real-world data

Guo

Nie

et al. 2020

npj Digit. Med.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…With respect to the prediction of high myopia development by age 18 years, the model provided clinically acceptable accuracy over 3 years (the AUC ranged from 0.940 to 0.985), 5 years (the AUC ranged from 0.856 to 0.901), and even 8 years (the AUC ranged from 0.801 to 0.837), by predictors including age at examination, spherical equivalent (SE), and annual progression rate. In addition, Li et al 2019 , 2020 developed DL systems with high accuracy (over 96%) in detecting common comorbidities of high myopia, such as lattice degeneration, retinal breaks and retinal detachment, based on UWF images, which could further improve visual prognosis of myopia patients via timely medical intervention.…”

Section: Digital Innovations For Eye Diseasesmentioning

confidence: 99%

Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective

Liu

Ting

et al. 2021

Progress in Retinal and Eye Research

Self Cite

364

273

View full text Add to dashboard Cite

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.

show abstract

A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images

Cited by 44 publications

References 23 publications

Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system: a national real-world evidence study

Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system: a national real-world evidence study

Deep learning from “passive feeding” to “selective eating” of real-world data

Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective

Contact Info

Product

Resources

About