Artificial intelligence can assist with diagnosing retinal vein occlusion
AIM: To assist with retinal vein occlusion (RVO) screening, artificial intelligence (AI) methods based on deep learning (DL) have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible. METHODS: A total of 8600 color fundus photograph...
Guardado en:
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Press of International Journal of Ophthalmology (IJO PRESS)
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/fac787bbfb824c69816f918325d8960e |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:fac787bbfb824c69816f918325d8960e |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:fac787bbfb824c69816f918325d8960e2021-11-26T04:02:12ZArtificial intelligence can assist with diagnosing retinal vein occlusion2222-39592227-489810.18240/ijo.2021.12.13https://doaj.org/article/fac787bbfb824c69816f918325d8960e2021-12-01T00:00:00Zhttp://ies.ijo.cn/en_publish/2021/12/20211213.pdfhttps://doaj.org/toc/2222-3959https://doaj.org/toc/2227-4898AIM: To assist with retinal vein occlusion (RVO) screening, artificial intelligence (AI) methods based on deep learning (DL) have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible. METHODS: A total of 8600 color fundus photographs (CFPs) were included for training, validation, and testing of disease recognition models and lesion segmentation models. Four disease recognition and four lesion segmentation models were established and compared. Finally, one disease recognition model and one lesion segmentation model were selected as superior. Additionally, 224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models. RESULTS: Using the Inception-v3 model for disease identification, the mean sensitivity, specificity, and F1 for the three disease types and normal CFPs were 0.93, 0.99, and 0.95, respectively, and the mean area under the curve (AUC) was 0.99. Using the DeepLab-v3 model for lesion segmentation, the mean sensitivity, specificity, and F1 for four lesion types (abnormally dilated and tortuous blood vessels, cotton-wool spots, flame-shaped hemorrhages, and hard exudates) were 0.74, 0.97, and 0.83, respectively. CONCLUSION: DL models show good performance when recognizing RVO and identifying lesions using CFPs. Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists, DL models will be helpful for diagnosing RVO early in life and reducing vision impairment.Qiong ChenWei-Hong YuSong LinBo-Shi LiuYong WangQi-Jie WeiXi-Xi HeFei DingGang YangYou-Xin ChenXiao-Rong LiBo-Jie HuPress of International Journal of Ophthalmology (IJO PRESS)articleartificial intelligencedisease recognitionlesion segmentationretinal vein occlusionOphthalmologyRE1-994ENInternational Journal of Ophthalmology, Vol 14, Iss 12, Pp 1895-1902 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
artificial intelligence disease recognition lesion segmentation retinal vein occlusion Ophthalmology RE1-994 |
spellingShingle |
artificial intelligence disease recognition lesion segmentation retinal vein occlusion Ophthalmology RE1-994 Qiong Chen Wei-Hong Yu Song Lin Bo-Shi Liu Yong Wang Qi-Jie Wei Xi-Xi He Fei Ding Gang Yang You-Xin Chen Xiao-Rong Li Bo-Jie Hu Artificial intelligence can assist with diagnosing retinal vein occlusion |
description |
AIM: To assist with retinal vein occlusion (RVO) screening, artificial intelligence (AI) methods based on deep learning (DL) have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible. METHODS: A total of 8600 color fundus photographs (CFPs) were included for training, validation, and testing of disease recognition models and lesion segmentation models. Four disease recognition and four lesion segmentation models were established and compared. Finally, one disease recognition model and one lesion segmentation model were selected as superior. Additionally, 224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models. RESULTS: Using the Inception-v3 model for disease identification, the mean sensitivity, specificity, and F1 for the three disease types and normal CFPs were 0.93, 0.99, and 0.95, respectively, and the mean area under the curve (AUC) was 0.99. Using the DeepLab-v3 model for lesion segmentation, the mean sensitivity, specificity, and F1 for four lesion types (abnormally dilated and tortuous blood vessels, cotton-wool spots, flame-shaped hemorrhages, and hard exudates) were 0.74, 0.97, and 0.83, respectively. CONCLUSION: DL models show good performance when recognizing RVO and identifying lesions using CFPs. Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists, DL models will be helpful for diagnosing RVO early in life and reducing vision impairment. |
format |
article |
author |
Qiong Chen Wei-Hong Yu Song Lin Bo-Shi Liu Yong Wang Qi-Jie Wei Xi-Xi He Fei Ding Gang Yang You-Xin Chen Xiao-Rong Li Bo-Jie Hu |
author_facet |
Qiong Chen Wei-Hong Yu Song Lin Bo-Shi Liu Yong Wang Qi-Jie Wei Xi-Xi He Fei Ding Gang Yang You-Xin Chen Xiao-Rong Li Bo-Jie Hu |
author_sort |
Qiong Chen |
title |
Artificial intelligence can assist with diagnosing retinal vein occlusion |
title_short |
Artificial intelligence can assist with diagnosing retinal vein occlusion |
title_full |
Artificial intelligence can assist with diagnosing retinal vein occlusion |
title_fullStr |
Artificial intelligence can assist with diagnosing retinal vein occlusion |
title_full_unstemmed |
Artificial intelligence can assist with diagnosing retinal vein occlusion |
title_sort |
artificial intelligence can assist with diagnosing retinal vein occlusion |
publisher |
Press of International Journal of Ophthalmology (IJO PRESS) |
publishDate |
2021 |
url |
https://doaj.org/article/fac787bbfb824c69816f918325d8960e |
work_keys_str_mv |
AT qiongchen artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT weihongyu artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT songlin artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT boshiliu artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT yongwang artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT qijiewei artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT xixihe artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT feiding artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT gangyang artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT youxinchen artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT xiaorongli artificialintelligencecanassistwithdiagnosingretinalveinocclusion AT bojiehu artificialintelligencecanassistwithdiagnosingretinalveinocclusion |
_version_ |
1718409941884076032 |