Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks

Brown, James M.; Campbell, J. Peter; Beers, Andrew; Chang, Ken; Ostmo, Susan; Chan, Robison Vernon Paul; Dy, Jennifer G.; Erdoğmuş, Deni̇z; Ioannidis, Stratis; Kalpathy–Cramer, Jayashree; Chiang, Michael F.

doi:10.1001/jamaophthalmol.2018.1934

Cited by 515 publications

(376 citation statements)

References 45 publications

Supporting

Mentioning

341

Contrasting

Unclassified

Order By: Relevance

“…We have previously shown that this system has very high accuracy for plus disease in ROP 15. These results extend those findings beyond plus disease and demonstrate that despite only being trained to recognise plus disease, the system has high accuracy for broader diagnostic categories of ROP, particularly severe disease.…”

Section: Discussionsupporting

confidence: 79%

“…The i-ROP DL system was developed based on the concept of convolutional neural networks using methods previously published 15. Briefly, a reference standard diagnosis of plus disease was established by analysing 5511 wide-angle image sets from ROP screening in at-risk neonates.…”

Section: Methodsmentioning

confidence: 99%

“…These images and their respective RSD for plus disease were then presented to the system in an iterative fashion. The system consisted of two consecutive neural networks, one trained for retinal vessel segmentation and the second trained to detect plus disease 15. In the first network, images were reduced to 640×480 pixels and U-Net architecture was used to develop a ‘vessel-ness’ map by training on 200 manually labelled retinal images.…”

Section: Methodsmentioning

confidence: 99%

“…A dropout rate of 0.4 was also used to mitigate overfitting. From this process, the system learnt to identify retinal image features deemed important to the diagnosis of plus disease, with near-perfect receiver operating curve characteristics 15. Of note, information from the RSD regarding zone and stage was not provided to the system during this training.…”

Section: Methodsmentioning

confidence: 99%

“…This system has previously been shown to have very high accuracy for detecting plus disease from wide-angle posterior pole retinal images without the need for manual vessel segmentation and performs comparably or better than expert human examiners 15. However, the system has been trained only to recognise plus disease.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity

et al. 2018

Self Cite

View full text Add to dashboard Cite

BackgroundPrior work has demonstrated the near-perfect accuracy of a deep learning retinal image analysis system for diagnosing plus disease in retinopathy of prematurity (ROP). Here we assess the screening potential of this scoring system by determining its ability to detect all components of ROP diagnosis.MethodsClinical examination and fundus photography were performed at seven participating centres. A deep learning system was trained to detect plus disease, generating a quantitative assessment of retinal vascular abnormality (the i-ROP plus score) on a 1–9 scale. Overall ROP disease category was established using a consensus reference standard diagnosis combining clinical and image-based diagnosis. Experts then ranked ordered a second data set of 100 posterior images according to overall ROP severity.Results4861 examinations from 870 infants were analysed. 155 examinations (3%) had a reference standard diagnosis of type 1 ROP. The i-ROP deep learning (DL) vascular severity score had an area under the receiver operating curve of 0.960 for detecting type 1 ROP. Establishing a threshold i-ROP DL score of 3 conferred 94% sensitivity, 79% specificity, 13% positive predictive value and 99.7% negative predictive value for type 1 ROP. There was strong correlation between expert rank ordering of overall ROP severity and the i-ROP DL vascular severity score (Spearman correlation coefficient=0.93; p<0.0001).ConclusionThe i-ROP DL system accurately identifies diagnostic categories and overall disease severity in an automated fashion, after being trained only on posterior pole vascular morphology. These data provide proof of concept that a deep learning screening platform could improve objectivity of ROP diagnosis and accessibility of screening.

show abstract

Section: Discussionsupporting

confidence: 79%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

Automated Explainable Multidimensional Deep Learning Platform of Retinal Images for Retinopathy of Prematurity Screening

Wang

Zhang

et al. 2021

JAMA Netw Open

View full text Add to dashboard Cite

Key Points Question Can deep learning algorithms achieve a performance comparable with that of ophthalmologists on multidimensional identification of retinopathy of prematurity (ROP) using wide-field retinal images? Findings In this diagnostic study of 14 108 eyes of 8652 preterm infants, a deep learning–based ROP screening platform could identify retinal images using 5 classifiers, including image quality, stages of ROP, intraocular hemorrhage, preplus/plus disease, and posterior retina. The platform achieved an area under the curve of 0.983 to 0.998, and the referral system achieved an area under the curve of 0.9901 to 0.9956; the platform achieved a Cohen κ of 0.86 to 0.98 compared with 0.93 to 0.98 by the ROP experts. Meaning Results suggest that a deep learning platform could identify and classify multidimensional ROP pathological lesions in retinal images with high accuracy and could be suitable for routine ROP screening in general and children’s hospitals.

show abstract

Development and Validation of a Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of Prematurity

et al. 2022

JAMA Netw Open

View full text Add to dashboard Cite

IMPORTANCERetinopathy of prematurity (ROP) is the leading cause of childhood blindness worldwide. Prediction of ROP before onset holds great promise for reducing the risk of blindness. OBJECTIVE To develop and validate a deep learning (DL) system to predict the occurrence and severity of ROP before 45 weeks' postmenstrual age. DESIGN, SETTING, AND PARTICIPANTS This retrospective prognostic study included 7033 retinal photographs of 725 infants in the training set and 763 retinal photographs of 90 infants in the external validation set, along with 46 characteristics for each infant. All images of both eyes from the same infant taken at the first screening were labeled according to the final diagnosis made between the first screening and 45 weeks' postmenstrual age. The DL system was developed using retinal photographs from the first ROP screening and clinical characteristics before or at the first screening in infants born between June 3, 2017, and August 28, 2019. EXPOSURES Two models were specifically designed for predictions of the occurrence (occurrence network [OC-Net]) and severity (severity network [SE-Net]) of ROP. Five-fold cross-validation was applied for internal validation. MAIN OUTCOMES AND MEASURES Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity to evaluate the performance in ROP prediction. RESULTSThis study included 815 infants (450 [55.2%] boys) with mean birth weight of 1.91 kg (95% CI, 1.87-1.95 kg) and mean gestational age of 33.1 weeks (95% CI, 32.9-33.3 weeks).

show abstract

Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks

Cited by 515 publications

References 45 publications

Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity

Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity

Automated Explainable Multidimensional Deep Learning Platform of Retinal Images for Retinopathy of Prematurity Screening

Development and Validation of a Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of Prematurity

Contact Info

Product

Resources

About