Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach

Purpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR).Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable D...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yueye Wang, Danli Shi, Zachary Tan, Yong Niu, Yu Jiang, Ruilin Xiong, Guankai Peng, Mingguang He
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/e5415a0bd07849f2b6c9bdee5cbfde62
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:e5415a0bd07849f2b6c9bdee5cbfde62
record_format dspace
spelling oai:doaj.org-article:e5415a0bd07849f2b6c9bdee5cbfde622021-12-01T01:40:53ZScreening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach2296-858X10.3389/fmed.2021.740987https://doaj.org/article/e5415a0bd07849f2b6c9bdee5cbfde622021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.740987/fullhttps://doaj.org/toc/2296-858XPurpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR).Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009–2010 (“baseline images”) and annual follow-up between 2011 and 2017. To begin, a validated DLA automatically graded baseline images for referable DR and classified them as positive, negative, or ungradable. Following, each positive image, all other available images from patients who had a positive image, and a 5% random sample of all negative images were selected and regraded by trained human graders. A reference standard diagnosis was assigned once all graders achieved consistent grading outcomes or with a senior ophthalmologist's final diagnosis. The semi-automated DLA assisted approach combined initial DLA screening and subsequent human grading for images identified as high-risk. This approach was further validated within the follow-up image datasets and its time and economic costs evaluated against fully human grading.Results: For evaluation of baseline images, a total of 33,115 images were included and automatically graded by the DLA. 2,604 images (480 positive results, 624 available other images from participants with a positive result, and 1500 random negative samples) were selected and regraded by graders. The DLA achieved an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.953, 0.970, 0.879, and 88.6%, respectively. In further validation within the follow-up image datasets, a total of 88,363 images were graded using this semi-automated approach and human grading was performed on 8975 selected images. The DLA achieved an AUC, sensitivity, and specificity of 0.914, 0.852, 0.853, respectively. Compared against fully human grading, the semi-automated DLA-assisted approach achieved an estimated 75.6% time and 90.1% economic cost saving.Conclusions: The DLA described in this study was able to achieve high accuracy, sensitivity, and specificity in grading fundus images for referable DR. Validated against long-term follow-up datasets, a semi-automated DLA-assisted approach was able to accurately identify suspect cases, and minimize misdiagnosis whilst balancing safety, time, and economic cost.Yueye WangDanli ShiZachary TanYong NiuYu JiangRuilin XiongGuankai PengMingguang HeMingguang HeMingguang HeMingguang HeFrontiers Media S.A.articlediabetic retinopathyartificial intelligencescreeningcost-saving analysisdeep learningMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021)
institution DOAJ
collection DOAJ
language EN
topic diabetic retinopathy
artificial intelligence
screening
cost-saving analysis
deep learning
Medicine (General)
R5-920
spellingShingle diabetic retinopathy
artificial intelligence
screening
cost-saving analysis
deep learning
Medicine (General)
R5-920
Yueye Wang
Danli Shi
Zachary Tan
Yong Niu
Yu Jiang
Ruilin Xiong
Guankai Peng
Mingguang He
Mingguang He
Mingguang He
Mingguang He
Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
description Purpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR).Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009–2010 (“baseline images”) and annual follow-up between 2011 and 2017. To begin, a validated DLA automatically graded baseline images for referable DR and classified them as positive, negative, or ungradable. Following, each positive image, all other available images from patients who had a positive image, and a 5% random sample of all negative images were selected and regraded by trained human graders. A reference standard diagnosis was assigned once all graders achieved consistent grading outcomes or with a senior ophthalmologist's final diagnosis. The semi-automated DLA assisted approach combined initial DLA screening and subsequent human grading for images identified as high-risk. This approach was further validated within the follow-up image datasets and its time and economic costs evaluated against fully human grading.Results: For evaluation of baseline images, a total of 33,115 images were included and automatically graded by the DLA. 2,604 images (480 positive results, 624 available other images from participants with a positive result, and 1500 random negative samples) were selected and regraded by graders. The DLA achieved an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.953, 0.970, 0.879, and 88.6%, respectively. In further validation within the follow-up image datasets, a total of 88,363 images were graded using this semi-automated approach and human grading was performed on 8975 selected images. The DLA achieved an AUC, sensitivity, and specificity of 0.914, 0.852, 0.853, respectively. Compared against fully human grading, the semi-automated DLA-assisted approach achieved an estimated 75.6% time and 90.1% economic cost saving.Conclusions: The DLA described in this study was able to achieve high accuracy, sensitivity, and specificity in grading fundus images for referable DR. Validated against long-term follow-up datasets, a semi-automated DLA-assisted approach was able to accurately identify suspect cases, and minimize misdiagnosis whilst balancing safety, time, and economic cost.
format article
author Yueye Wang
Danli Shi
Zachary Tan
Yong Niu
Yu Jiang
Ruilin Xiong
Guankai Peng
Mingguang He
Mingguang He
Mingguang He
Mingguang He
author_facet Yueye Wang
Danli Shi
Zachary Tan
Yong Niu
Yu Jiang
Ruilin Xiong
Guankai Peng
Mingguang He
Mingguang He
Mingguang He
Mingguang He
author_sort Yueye Wang
title Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
title_short Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
title_full Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
title_fullStr Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
title_full_unstemmed Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach
title_sort screening referable diabetic retinopathy using a semi-automated deep learning algorithm assisted approach
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/e5415a0bd07849f2b6c9bdee5cbfde62
work_keys_str_mv AT yueyewang screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT danlishi screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT zacharytan screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT yongniu screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT yujiang screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT ruilinxiong screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT guankaipeng screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT mingguanghe screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT mingguanghe screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT mingguanghe screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
AT mingguanghe screeningreferablediabeticretinopathyusingasemiautomateddeeplearningalgorithmassistedapproach
_version_ 1718405993359998976