Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning

Li, Zhongwen; Guo, Chong; Nie, Danyao; Lin, Duoru; Cui, Tingxin; Chen, Chuan; Zhao, Lanqin; Zhang, Xu‐Lin; Dongye, Meimei; Wang, Dongni; Xu, Fabao; Jin, Chenjin; Zhang, Ping; Han, Yu; Yan, Pisong; Lin, Haotian

doi:10.1038/s41433-021-01715-7

Cited by 24 publications

(23 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In discerning corneas with contraindications for refractive surgery based on corneal tomographic images, comparable accuracy was observed between a deep learning system and refractive surgeons (95% versus 92.8; p = 0.72) (Xie et al, 2020). Our previous study also demonstrated that a senior cornea specialist and a deep learning system had similar performance (accuracy: 96.7% versus 97.3%; p = 0.50) in screening for keratitis from slit lamp images (Li et al, 2021a(Li et al, , 2021b(Li et al, , 2021c(Li et al, , 2021d.…”

Section: Introductionmentioning

confidence: 53%

“…Recently deep learning has attained remarkable performance in disease screening and diagnosis (Cheung et al, 2021;Hosny and Aerts, 2019;Li et al, 2020aLi et al, , 2020bLi et al, , 2020cLi et al, , 2020dMatheny et al, 2019;Zhou et al, 2021). The performance of deep learning is comparable with and even superior to that of human doctors in many clinical image analyses (Li et al, 2021a(Li et al, , 2021b(Li et al, , 2021c(Li et al, , 2021dLi et al, 2020aLi et al, , 2020bLi et al, , 2020cLi et al, , 2020dLi et al, 2019;Ting et al, 2017;Xie et al, 2020;Zhang et al, 2020). For example, the accuracy of a deep learning system in distinguishing coronavirus pneumonia from computed tomography images reached the level of senior radiologists (87.5% versus 84.5%; p ＞ 0.05) and exceeded the level of junior radiologists (87.5% versus 65.6%; p < .05) (Zhang et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…For facilitating feature extraction, most studies only utilize high-quality images to establish deep learning systems (Cheung et al, 2021;Esteva et al, 2017;Li et al, 2020aLi et al, , 2020bLi et al, , 2020cLi et al, , 2020dLi et al, 2021aLi et al, , 2021bLi et al, , 2021cLi et al, , 2021dLuo et al, 2019;Xie et al, 2020;Zhang et al, 2020). Although deep learning acquires good performance in high-quality images, its performance was poor in low-quality images, which were inevitable in real clinical scenarios due to many factors such as patient noncompliance, hardware imperfections, and operator errors (Li et al, 2020a(Li et al, , 2020b(Li et al, , 2020c(Li et al, , 2020dLi et al, 2021aLi et al, , 2021bLi et al, , 2021cLi et al, , 2021dTrucco et al, 2013). For instance, in screening for lattice degeneration/retinal breaks, glaucomatous optic neuropathy, and retinal exudation/drusen, deep learning systems achieved area under the receiver operating characteristic curves (AUCs) of 0.990, 0.995, and 0.982 in high-quality fundus images, respectively, whereas achieved AUCs of 0.635, 0.853, and 0.779 in low-quality fundus images, respectively (Li et al, 2020a(Li et al, , 2020b(Li et al, , 2020c(Li et al, , 2020d.…”

Section: Introductionmentioning

confidence: 99%

“…To explore this issue, our study aimed to compare the performance of a previously established deep learning system (PEDLS) (Li et al, 2021a(Li et al, , 2021b(Li et al, , 2021c(Li et al, , 2021d with that of cornea specialists in low-quality slit lamp images for classifying keratitis, other corneal abnormalities, and normal cornea. In addition, this study investigated whether the performance of the deep learning system in low-quality images would be improved by training a deep learning network with both high-and low-quality images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images

Jiang

Wei

et al. 2021

iScience

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 53%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images

Jiang

Wei

et al. 2021

iScience

Self Cite

View full text Add to dashboard Cite

show abstract

Deep Learning Performance of Ultra-Widefield Fundus Imaging for Screening Retinal Lesions in Rural Locales

Cui,

Lin,

et al. 2023

JAMA Ophthalmol

Self Cite

View full text Add to dashboard Cite

ImportanceRetinal diseases are the leading cause of irreversible blindness worldwide, and timely detection contributes to prevention of permanent vision loss, especially for patients in rural areas with limited medical resources. Deep learning systems (DLSs) based on fundus images with a 45° field of view have been extensively applied in population screening, while the feasibility of using ultra-widefield (UWF) fundus image–based DLSs to detect retinal lesions in patients in rural areas warrants exploration.ObjectiveTo explore the performance of a DLS for multiple retinal lesion screening using UWF fundus images from patients in rural areas.Design, Setting, and ParticipantsIn this diagnostic study, a previously developed DLS based on UWF fundus images was used to screen for 5 retinal lesions (retinal exudates or drusen, glaucomatous optic neuropathy, retinal hemorrhage, lattice degeneration or retinal breaks, and retinal detachment) in 24 villages of Yangxi County, China, between November 17, 2020, and March 30, 2021.InterventionsThe captured images were analyzed by the DLS and ophthalmologists.Main Outcomes and MeasuresThe performance of the DLS in rural screening was compared with that of the internal validation in the previous model development stage. The image quality, lesion proportion, and complexity of lesion composition were compared between the model development stage and the rural screening stage.ResultsA total of 6222 eyes in 3149 participants (1685 women [53.5%]; mean [SD] age, 70.9 [9.1] years) were screened. The DLS achieved a mean (SD) area under the receiver operating characteristic curve (AUC) of 0.918 (0.021) (95% CI, 0.892-0.944) for detecting 5 retinal lesions in the entire data set when applied for patients in rural areas, which was lower than that reported at the model development stage (AUC, 0.998 [0.002] [95% CI, 0.995-1.000]; P &lt; .001). Compared with the fundus images in the model development stage, the fundus images in this rural screening study had an increased frequency of poor quality (13.8% [860 of 6222] vs 0%), increased variation in lesion proportions (0.1% [6 of 6222]-36.5% [2271 of 6222] vs 14.0% [2793 of 19 891]-21.3% [3433 of 16 138]), and an increased complexity of lesion composition.Conclusions and RelevanceThis diagnostic study suggests that the DLS exhibited excellent performance using UWF fundus images as a screening tool for 5 retinal lesions in patients in a rural setting. However, poor image quality, diverse lesion proportions, and a complex set of lesions may have reduced the performance of the DLS; these factors in targeted screening scenarios should be taken into consideration in the model development stage to ensure good performance.

show abstract

Deep learning for ultra-widefield imaging: a scoping review

Bhambra

Antaki

Malt

et al. 2022

Graefes Arch Clin Exp Ophthalmol

View full text Add to dashboard Cite

Purpose: This article is a scoping review of published and peer-reviewed articles using deep-learning (DL) applied to ultra-wide eld (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, 20201 using PubMed, Embase, Cochrane Library, and Google Scholar. The inclusion criteria were as follows: (1) Deep Learning, (2) Ultra-Wide eld 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. 23 studies discussed ophthalmic disease detection and classi cation, 5 discussed segmentation and localization of UWF images, 3 discussed generative image synthesis, 3 discussed ophthalmic image quality assessment, and 2 discussed detecting systemic diseases via UWFI. Conclusion:The application of DL to UWFI has demonstrated signi cant effectiveness in the diagnosis and detection of ophthalmic diseases including diabetic retinopathy, retinal detachment, and glaucoma. DL has been used with UWFI to also diagnose systemic diseases like Alzheimer's, and also applied in the generation of synthetic ophthalmic images. This scoping review highlights and discusses the current uses of DL with UWFI, and the future of DL applications in this eld.

show abstract

Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning

Cited by 24 publications

References 42 publications

Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images

Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images

Deep Learning Performance of Ultra-Widefield Fundus Imaging for Screening Retinal Lesions in Rural Locales

Deep learning for ultra-widefield imaging: a scoping review

Contact Info

Product

Resources

About