Cargando…
Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning
PURPOSE: This study implements and demonstrates a deep learning (DL) approach for screening referable horizontal strabismus based on primary gaze photographs using clinical assessments as a reference. The purpose of this study was to develop and evaluate deep learning algorithms that screen referabl...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Association for Research in Vision and Ophthalmology
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7846951/ https://www.ncbi.nlm.nih.gov/pubmed/33532144 http://dx.doi.org/10.1167/tvst.10.1.33 |
_version_ | 1783644840556232704 |
---|---|
author | Zheng, Ce Yao, Qian Lu, Jiewei Xie, Xiaolin Lin, Shibin Wang, Zilei Wang, Siyin Fan, Zhun Qiao, Tong |
author_facet | Zheng, Ce Yao, Qian Lu, Jiewei Xie, Xiaolin Lin, Shibin Wang, Zilei Wang, Siyin Fan, Zhun Qiao, Tong |
author_sort | Zheng, Ce |
collection | PubMed |
description | PURPOSE: This study implements and demonstrates a deep learning (DL) approach for screening referable horizontal strabismus based on primary gaze photographs using clinical assessments as a reference. The purpose of this study was to develop and evaluate deep learning algorithms that screen referable horizontal strabismus in children's primary gaze photographs. METHODS: DL algorithms were developed and trained using primary gaze photographs from two tertiary hospitals of children with primary horizontal strabismus who underwent surgery as well as orthotropic children who underwent routine refractive tests. A total of 7026 images (3829 non-strabismus from 3021 orthoptics [healthy] subjects and 3197 strabismus images from 2772 subjects) were used to develop the DL algorithms. The DL model was evaluated by 5-fold cross-validation and tested on an independent validation data set of 277 images. The diagnostic performance of the DL algorithm was assessed by calculating the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS: Using 5-fold cross-validation during training, the average AUCs of the DL models were approximately 0.99. In the external validation data set, the DL algorithm achieved an AUC of 0.99 with a sensitivity of 94.0% and a specificity of 99.3%. The DL algorithm's performance (with an accuracy of 0.95) in diagnosing referable horizontal strabismus was better than that of the resident ophthalmologists (with accuracy ranging from 0.81 to 0.85). CONCLUSIONS: We developed and evaluated a DL model to automatically identify referable horizontal strabismus using primary gaze photographs. The diagnostic performance of the DL model is comparable to or better than that of ophthalmologists. TRANSLATIONAL RELEVANCE: DL methods that automate the detection of referable horizontal strabismus can facilitate clinical assessment and screening for children at risk of strabismus. |
format | Online Article Text |
id | pubmed-7846951 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | The Association for Research in Vision and Ophthalmology |
record_format | MEDLINE/PubMed |
spelling | pubmed-78469512021-02-01 Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning Zheng, Ce Yao, Qian Lu, Jiewei Xie, Xiaolin Lin, Shibin Wang, Zilei Wang, Siyin Fan, Zhun Qiao, Tong Transl Vis Sci Technol Article PURPOSE: This study implements and demonstrates a deep learning (DL) approach for screening referable horizontal strabismus based on primary gaze photographs using clinical assessments as a reference. The purpose of this study was to develop and evaluate deep learning algorithms that screen referable horizontal strabismus in children's primary gaze photographs. METHODS: DL algorithms were developed and trained using primary gaze photographs from two tertiary hospitals of children with primary horizontal strabismus who underwent surgery as well as orthotropic children who underwent routine refractive tests. A total of 7026 images (3829 non-strabismus from 3021 orthoptics [healthy] subjects and 3197 strabismus images from 2772 subjects) were used to develop the DL algorithms. The DL model was evaluated by 5-fold cross-validation and tested on an independent validation data set of 277 images. The diagnostic performance of the DL algorithm was assessed by calculating the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS: Using 5-fold cross-validation during training, the average AUCs of the DL models were approximately 0.99. In the external validation data set, the DL algorithm achieved an AUC of 0.99 with a sensitivity of 94.0% and a specificity of 99.3%. The DL algorithm's performance (with an accuracy of 0.95) in diagnosing referable horizontal strabismus was better than that of the resident ophthalmologists (with accuracy ranging from 0.81 to 0.85). CONCLUSIONS: We developed and evaluated a DL model to automatically identify referable horizontal strabismus using primary gaze photographs. The diagnostic performance of the DL model is comparable to or better than that of ophthalmologists. TRANSLATIONAL RELEVANCE: DL methods that automate the detection of referable horizontal strabismus can facilitate clinical assessment and screening for children at risk of strabismus. The Association for Research in Vision and Ophthalmology 2021-01-27 /pmc/articles/PMC7846951/ /pubmed/33532144 http://dx.doi.org/10.1167/tvst.10.1.33 Text en Copyright 2021 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. |
spellingShingle | Article Zheng, Ce Yao, Qian Lu, Jiewei Xie, Xiaolin Lin, Shibin Wang, Zilei Wang, Siyin Fan, Zhun Qiao, Tong Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning |
title | Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning |
title_full | Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning |
title_fullStr | Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning |
title_full_unstemmed | Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning |
title_short | Detection of Referable Horizontal Strabismus in Children's Primary Gaze Photographs Using Deep Learning |
title_sort | detection of referable horizontal strabismus in children's primary gaze photographs using deep learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7846951/ https://www.ncbi.nlm.nih.gov/pubmed/33532144 http://dx.doi.org/10.1167/tvst.10.1.33 |
work_keys_str_mv | AT zhengce detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT yaoqian detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT lujiewei detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT xiexiaolin detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT linshibin detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT wangzilei detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT wangsiyin detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT fanzhun detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning AT qiaotong detectionofreferablehorizontalstrabismusinchildrensprimarygazephotographsusingdeeplearning |