Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning

Zheng, Ce; Ye, Qian; Lu, Jiewei; Xie, Xiaolin; Lin, Stanley L.; Wang, Zhong Lin; Wang, Siyin; Fan, Zhun; Qiao, Tong

doi:10.1167/tvst.10.1.33

Cited by 24 publications

(25 citation statements)

References 28 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several attempts have been made to study ocular movements using images of different gaze positions [ 22 – 26 ]. Figueiredo et al [ 23 ] developed a web application using a CNN to classify eye versions into the nine gaze positions, but it was not clear how this could contribute to the actual examination of strabismus.…”

Section: Discussionmentioning

confidence: 99%

“…Figueiredo et al [ 23 ] developed a web application using a CNN to classify eye versions into the nine gaze positions, but it was not clear how this could contribute to the actual examination of strabismus. Zheng et al [ 26 ] implemented a DL algorithm to classify horizontal strabismus using primary gaze photographs of children; however, this study lacked other types of strabismus and different gaze positions. To overcome these difficulties, we attempted to build a powerful CNN model to segment the limbus and sclera areas as accurate as possible as it is crucial for objective measurement of strabismus.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Mathematical Algorithm for Quantitative Measurement of Strabismus Based on Photographs of Nine Cardinal Gaze Positions

Kang

Yang

Kim

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

This study presents an automated algorithm that measures ocular deviation quantitatively using photographs of the nine cardinal points of gaze by means of deep learning (DL) and image processing techniques. Photographs were collected from patients with strabismus. The images were used as inputs for the DL segmentation models that segmented the sclerae and limbi. Subsequently, the images were registered for the mathematical algorithm. Two-dimensional sclera and limbus were modeled, and the corneal light reflex points of the primary gaze images were determined. Limbus recognition was performed to measure the pixel-wise distance between the corneal reflex point and limbus center. The segmentation models exhibited high performance, with 96.88% dice similarity coefficient (DSC) for the sclera segmentation and 95.71% DSC for the limbus segmentation. The mathematical algorithm was tested on two cranial nerve palsy patients to evaluate its ability to measure and compare ocular deviation in different directions. These results were consistent with the symptoms of such disorders. This algorithm successfully measured the distance of ocular deviation in patients with strabismus. With complementation in the dimension calculations, we expect that this algorithm can be used further in clinical settings to diagnose and measure strabismus at a low cost.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Automated Mathematical Algorithm for Quantitative Measurement of Strabismus Based on Photographs of Nine Cardinal Gaze Positions

Kang

Yang

Kim

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…Lu et al [ 19 ] presented a strabismus-detection method that includes a CNN architecture for eye region segmentation from the facial image and another CNN architecture for strabismus classification. In another similar study, Zheng et al [ 20 ] employed a pretrained CNN architecture in the classification stage and trained it on the primary gaze photographs. To ensure that the input to the classification network is an eye region image, they performed manual adjustments on the results from the segmentation network.…”

Section: Discussionmentioning

confidence: 99%

“…Lu et al [ 19 ] proposed a deep learning method for strabismus detection using a telemedicine dataset. Also, Zheng et al [ 20 ] applied a pretrained deep learning model on the gaze photographs to achieve strabismus screening. Although the deep learning methods have achieved excellent performance, the screening results are difficult to interpret due to their opaque internal learning.…”

Section: Introductionmentioning

confidence: 99%

An automatic screening method for strabismus detection based on image processing

2021

View full text Add to dashboard Cite

Purpose This study aims to provide an automatic strabismus screening method for people who live in remote areas with poor medical accessibility. Materials and methods The proposed method first utilizes a pretrained convolutional neural network-based face-detection model and a detector for 68 facial landmarks to extract the eye region for a frontal facial image. Second, Otsu’s binarization and the HSV color model are applied to the image to eliminate the influence of eyelashes and canthi. Then, the method samples all of the pixel points on the limbus and applies the least square method to obtain the coordinate of the pupil center. Lastly, we calculated the distances from the pupil center to the medial and lateral canthus to measure the deviation of the positional similarity of two eyes for strabismus screening. Result We used a total of 60 frontal facial images (30 strabismus images, 30 normal images) to validate the proposed method. The average value of the iris positional similarity of normal images was smaller than one of the strabismus images via the method (p-value<0.001). The sample mean and sample standard deviation of the positional similarity of the normal and strabismus images were 1.073 ± 0.014 and 0.039, as well as 1.924 ± 0.169 and 0.472, respectively. Conclusion The experimental results of 60 images show that the proposed method is a promising automatic strabismus screening method for people living in remote areas with poor medical accessibility.

show abstract

“…The application achieved an accuracy ranging from 42% to 92% and precision ranging from 28% to 84% depending on the type of eye version. Recently, Zheng et al 64 also developed a DL approach for screening referable horizontal strabismus in children based on primary gaze photographs. A total of 7026 images were used to train the model and 277 images from an independent dataset were tested.…”

Section: Detection Of Eye Movement Disordersmentioning

confidence: 99%

Artificial Intelligence Meets Neuro-Ophthalmology

Leong

Vasseneix

Finkelstein

et al. 2022

Asia-Pacific Journal of Ophthalmology

View full text Add to dashboard Cite

Recent advances in artificial intelligence have provided ophthalmologists with fast, accurate, and automated means for diagnosing and treating ocular conditions, paving the way to a modern and scalable eye care system. Compared to other ophthalmic disciplines, neuro-ophthalmology has, until recently, not benefitted from significant advances in the area of artificial intelligence. In this narrative review, we summarize and discuss recent advancements utilizing artificial intelligence for the detection of structural and functional optic nerve head abnormalities, and ocular movement disorders in neuro-ophthalmology.

show abstract

Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning

Abstract: Detection of referable horizontal strabismus in children's primary gaze photographs using deep learning.

Cited by 24 publications

References 28 publications

Automated Mathematical Algorithm for Quantitative Measurement of Strabismus Based on Photographs of Nine Cardinal Gaze Positions

Automated Mathematical Algorithm for Quantitative Measurement of Strabismus Based on Photographs of Nine Cardinal Gaze Positions

An automatic screening method for strabismus detection based on image processing

Artificial Intelligence Meets Neuro-Ophthalmology

Contact Info

Product

Resources

About