A method for the automatic detection of myopia in Optos fundus images based on deep learning

Shi, Zhengjin; Wang, Tianyu; Huang, Zheng; Xie, Feng; Song, Guoli

doi:10.1002/cnm.3460

Cited by 19 publications

(13 citation statements)

References 32 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the Pearson and Lasso analyses, age had the highest negative correlation with AXL. This observation may result from the difference in (38). We chose AXL classifications as our prediction.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Axial Length From Choroidal Thickness on Optical Coherence Tomography Images With Machine Learning Based Algorithms

Chen

Huang

et al. 2022

Front. Med.

View full text Add to dashboard Cite

PurposeWe formulated and tested ensemble learning models to classify axial length (AXL) from choroidal thickness (CT) as indicated on fovea-centered, 2D single optical coherence tomography (OCT) images.DesignRetrospective cross-sectional study.ParticipantsWe analyzed 710 OCT images from 355 eyes of 188 patients. Each eye had 2 OCT images.MethodsThe CT was estimated from 3 points of each image. We used five machine-learning base algorithms to construct the classifiers. This study trained and validated the models to classify the AXLs eyes based on binary (AXL < or > 26 mm) and multiclass (AXL < 22 mm, between 22 and 26 mm, and > 26 mm) classifications.ResultsNo features were redundant or duplicated after an analysis using Pearson’s correlation coefficient, LASSO-Pattern search algorithm, and variance inflation factors. Among the positions, CT at the nasal side had the highest correlation with AXL followed by the central area. In binary classification, our classifiers obtained high accuracy, as indicated by accuracy, recall, positive predictive value (PPV), negative predictive value (NPV), F1 score, and area under ROC curve (AUC) values of 94.37, 100, 90.91, 100, 86.67, and 95.61%, respectively. In multiclass classification, our classifiers were also highly accurate, as indicated by accuracy, weighted recall, weighted PPV, weighted NPV, weighted F1 score, and macro AUC of 88.73, 88.73, 91.21, 85.83, 87.42, and 93.42%, respectively.ConclusionsOur binary and multiclass classifiers classify AXL well from CT, as indicated on OCT images. We demonstrated the effectiveness of the proposed classifiers and provided an assistance tool for physicians.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Regarding myopia prediction, Varadarajan et al ( 37 ) developed a model to predict SE from color fundus images. Shi et al used CNN to predict myopia with absolute mean error of 1.115 D in SE from a color fundus image ( 38 ). We chose AXL classifications as our prediction.…”

Section: Discussionmentioning

confidence: 99%

Predicting Axial Length From Choroidal Thickness on Optical Coherence Tomography Images With Machine Learning Based Algorithms

Chen

Huang

et al. 2022

Front. Med.

View full text Add to dashboard Cite

show abstract

“…Deep learning models trained by traditional 45 and 30° fundus photographs from the UK Biobank and the Age-Related Eye Disease Research Database could reach the MAE of 0.56D (95% CI: 0.55–0.56 D) and 0.91D (95% CI: 0.89–0.93 D) for refractive prediction ( 14 ) while most of the patients were low-grade myope or hyperope. Compared with refractive prediction utilizing 7,307 UWFI fundus images, the MAE could reach 1.115 D with more than a half of enrolled eyes were moderate myopia(−6D ≤ SE < −3D) ( 19 ).…”

Section: Discussionmentioning

confidence: 98%

“…Though deep learning models trained by fundus imaging have constantly been utilized for the detection and grading of ophthalmic pathologies ( 15 , 17 , 18 ), few studies have applied fundus photographs for refractive error prediction ( 14 , 19 ).…”

Section: Discussionmentioning

confidence: 99%

Prediction of Refractive Error Based on Ultrawide Field Images With Deep Learning Models in Myopia Patients

Yang

et al. 2022

Front. Med.

View full text Add to dashboard Cite

SummaryUltrawide field fundus images could be applied in deep learning models to predict the refractive error of myopic patients. The predicted error was related to the older age and greater spherical power.PurposeTo explore the possibility of predicting the refractive error of myopic patients by applying deep learning models trained with ultrawide field (UWF) images.MethodsUWF fundus images were collected from left eyes of 987 myopia patients of Eye and ENT Hospital, Fudan University between November 2015 and January 2019. The fundus images were all captured with Optomap Daytona, a 200° UWF imaging device. Three deep learning models (ResNet-50, Inception-v3, Inception-ResNet-v2) were trained with the UWF images for predicting refractive error. 133 UWF fundus images were also collected after January 2021 as an the external validation data set. The predicted refractive error was compared with the “true value” measured by subjective refraction. Mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient (R2) value were calculated in the test set. The Spearman rank correlation test was applied for univariate analysis and multivariate linear regression analysis on variables affecting MAE. The weighted heat map was generated by averaging the predicted weight of each pixel.ResultsResNet-50, Inception-v3 and Inception-ResNet-v2 models were trained with the UWF images for refractive error prediction with R2 of 0.9562, 0.9555, 0.9563 and MAE of 1.72(95%CI: 1.62–1.82), 1.75(95%CI: 1.65–1.86) and 1.76(95%CI: 1.66–1.86), respectively. 29.95%, 31.47% and 29.44% of the test set were within the predictive error of 0.75D in the three models. 64.97%, 64.97%, and 64.47% was within 2.00D predictive error. The predicted MAE was related to older age (P < 0.01) and greater spherical power(P < 0.01). The optic papilla and macular region had significant predictive power in the weighted heat map.ConclusionsIt was feasible to predict refractive error in myopic patients with deep learning models trained by UWF images with the accuracy to be improved.

show abstract

“…Second, residual SE attention mechanism is to add residual connection to SE branch. Shi et al [ 70 ] combined dense connection with residual SE to propose myopic eye detection network (MDNet), which introduced residual SE correction for dense unit feature mapping channels, reduced the number of parameters, and improved network performance; network detected spherical equivalent mean absolute error up to 1.1150 d (Diopter); feasibility and applicability were verified in fundus images.…”

Section: Development Of Densenetmentioning

confidence: 99%

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao

XinYu

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Dense convolutional network (DenseNet) is a hot topic in deep learning research in recent years, which has good applications in medical image analysis. In this paper, DenseNet is summarized from the following aspects. First, the basic principle of DenseNet is introduced; second, the development of DenseNet is summarized and analyzed from five aspects: broaden DenseNet structure, lightweight DenseNet structure, dense unit, dense connection mode, and attention mechanism; finally, the application research of DenseNet in the field of medical image analysis is summarized from three aspects: pattern recognition, image segmentation, and object detection. The network structures of DenseNet are systematically summarized in this paper, which has certain positive significance for the research and development of DenseNet.

show abstract

A method for the automatic detection of myopia in Optos fundus images based on deep learning

Cited by 19 publications

References 32 publications

Predicting Axial Length From Choroidal Thickness on Optical Coherence Tomography Images With Machine Learning Based Algorithms

Predicting Axial Length From Choroidal Thickness on Optical Coherence Tomography Images With Machine Learning Based Algorithms

Prediction of Refractive Error Based on Ultrawide Field Images With Deep Learning Models in Myopia Patients

Dense Convolutional Network and Its Application in Medical Image Analysis

Contact Info

Product

Resources

About