A self-adaptive deep learning method for automated eye laterality detection based on color fundus photography

Liu, Chi; Han, Xiaotong; Li, Zhixi; Ha, Jason; Peng, Guankai; Meng, Wei; He, Mingguang

doi:10.1371/journal.pone.0222025

Cited by 12 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, our DLS module achieved a sensitivity of 94.7% (95% CI 89.7%–99.7%) and a specificity of 97.4% (95% CI 93.8%–100.0%) in eye laterality identification, which is similar to the performance of the algorithm for the fundus laterality detection 7 , 8 . Even for an experienced ophthalmologist, the accuracy of the eye side labeling is lower in the anterior segment images than labeling in the fundus images.…”

Section: Discussionsupporting

confidence: 74%

Development and validation of deep learning algorithms for automated eye laterality detection with anterior segment photography

Zheng

Xie

Wang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

This paper aimed to develop and validate a deep learning (DL) model for automated detection of the laterality of the eye on anterior segment photographs. Anterior segment photographs for training a DL model were collected with the Scheimpflug anterior segment analyzer. We applied transfer learning and fine-tuning of pre-trained deep convolutional neural networks (InceptionV3, VGG16, MobileNetV2) to develop DL models for determining the eye laterality. Testing datasets, from Scheimpflug and slit-lamp digital camera photography, were employed to test the DL model, and the results were compared with a classification performed by human experts. The performance of the DL model was evaluated by accuracy, sensitivity, specificity, operating characteristic curves, and corresponding area under the curve values. A total of 14,468 photographs were collected for the development of DL models. After training for 100 epochs, the DL models of the InceptionV3 mode achieved the area under the receiver operating characteristic curve of 0.998 (with 95% CI 0.924–0.958) for detecting eye laterality. In the external testing dataset (76 primary gaze photographs taken by a digital camera), the DL model achieves an accuracy of 96.1% (95% CI 91.7%–100%), which is better than an accuracy of 72.3% (95% CI 62.2%–82.4%), 82.8% (95% CI 78.7%–86.9%) and 86.8% (95% CI 82.5%–91.1%) achieved by human graders. Our study demonstrated that this high-performing DL model can be used for automated labeling for the laterality of eyes. Our DL model is useful for managing a large volume of the anterior segment images with a slit-lamp camera in the clinical setting.

show abstract

Section: Discussionsupporting

confidence: 74%

Development and validation of deep learning algorithms for automated eye laterality detection with anterior segment photography

Zheng

Xie

Wang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Laterality ( right and left ) internal/external test performance was competitive when compared to previous DL based approaches ( AUROC : 1.000 18 , 0.995 20 , 0.989 25 , 0.976 22 , 0.920 19 , accuracy: 98.98% 21 , ≥ 98.6 23 , sensitivity : left 90.1% and right 91.6% 24 ) despite the laterality model classifying both multifield retinal images and non-retinal ( e.g., anterior eye ) images, whereas prior approaches focused on macula or nasal field images alone. However, the laterality model also had excellent classification performance when stratified by retinal field (Supplementary Table S5 ).…”

Section: Discussionmentioning

confidence: 86%

Automated image curation in diabetic retinopathy screening using deep learning

Nderitu

Rio

Webster

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Diabetic retinopathy (DR) screening images are heterogeneous and contain undesirable non-retinal, incorrect field and ungradable samples which require curation, a laborious task to perform manually. We developed and validated single and multi-output laterality, retinal presence, retinal field and gradability classification deep learning (DL) models for automated curation. The internal dataset comprised of 7743 images from DR screening (UK) with 1479 external test images (Portugal and Paraguay). Internal vs external multi-output laterality AUROC were right (0.994 vs 0.905), left (0.994 vs 0.911) and unidentifiable (0.996 vs 0.680). Retinal presence AUROC were (1.000 vs 1.000). Retinal field AUROC were macula (0.994 vs 0.955), nasal (0.995 vs 0.962) and other retinal field (0.997 vs 0.944). Gradability AUROC were (0.985 vs 0.918). DL effectively detects laterality, retinal presence, retinal field and gradability of DR screening images with generalisation between centres and populations. DL models could be used for automated image curation within DR screening.

show abstract

“…Second, we did not address torsion for the left eye or both eyes; however, others have successfully developed models that distinguished between images from the left and right eyes. 35 , 39 , 55 Automated screening for skews and fourth nerve palsies will be most useful when the fundi of both eyes are assessed and compared. Third, our holdout testing set was relatively small and not balanced for all classes (more extorsions than intorsions).…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Model for Static Ocular Torsion Detection Using Synthetically Generated Fundus Images

Wang

Bai

Tsang

et al. 2023

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Purpose The objective of the study is to develop deep learning models using synthetic fundus images to assess the direction (intorsion versus extorsion) and amount (physiologic versus pathologic) of static ocular torsion. Static ocular torsion assessment is an important clinical tool for classifying vertical ocular misalignment; however, current methods are time-intensive with steep learning curves for frontline providers. Methods We used a dataset ( n = 276) of right eye fundus images. The disc-foveal angle was calculated using ImageJ to generate synthetic images via image rotation. Using synthetic datasets ( n = 12,740 images per model) and transfer learning (the reuse of a pretrained deep learning model on a new task), we developed a binary classifier (intorsion versus extorsion) and a multiclass classifier (physiologic versus pathologic intorsion and extorsion). Model performance was evaluated on unseen synthetic and nonsynthetic data. Results On the synthetic dataset, the binary classifier had an accuracy and area under the receiver operating characteristic curve (AUROC) of 0.92 and 0.98, respectively, whereas the multiclass classifier had an accuracy and AUROC of 0.77 and 0.94, respectively. The binary classifier generalized well on the nonsynthetic data (accuracy = 0.94; AUROC = 1.00). Conclusions The direction of static ocular torsion can be detected from synthetic fundus images using deep learning methods, which is key to differentiate between vestibular misalignment (skew deviation) and ocular muscle misalignment (superior oblique palsies). Translational Relevance Given the robust performance of our models on real fundus images, similar strategies can be adopted for deep learning research in rare neuro-ophthalmologic diseases with limited datasets.

show abstract

A self-adaptive deep learning method for automated eye laterality detection based on color fundus photography

Cited by 12 publications

References 20 publications

Development and validation of deep learning algorithms for automated eye laterality detection with anterior segment photography

Development and validation of deep learning algorithms for automated eye laterality detection with anterior segment photography

Automated image curation in diabetic retinopathy screening using deep learning

Deep Learning Model for Static Ocular Torsion Detection Using Synthetically Generated Fundus Images

Contact Info

Product

Resources

About