Cargando…

Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images

PURPOSE: To develop a new intelligent system based on deep learning for automatically optical coherence tomography (OCT) images categorization. METHODS: A total of 60,407 OCT images were labeled by 17 licensed retinal experts and 25,134 images were included. One hundred one-layer convolutional neura...

Descripción completa

Detalles Bibliográficos
Autores principales: Lu, Wei, Tong, Yan, Yu, Yue, Xing, Yiqiao, Chen, Changzheng, Shen, Yin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6314222/
https://www.ncbi.nlm.nih.gov/pubmed/30619661
http://dx.doi.org/10.1167/tvst.7.6.41
_version_ 1783384081198743552
author Lu, Wei
Tong, Yan
Yu, Yue
Xing, Yiqiao
Chen, Changzheng
Shen, Yin
author_facet Lu, Wei
Tong, Yan
Yu, Yue
Xing, Yiqiao
Chen, Changzheng
Shen, Yin
author_sort Lu, Wei
collection PubMed
description PURPOSE: To develop a new intelligent system based on deep learning for automatically optical coherence tomography (OCT) images categorization. METHODS: A total of 60,407 OCT images were labeled by 17 licensed retinal experts and 25,134 images were included. One hundred one-layer convolutional neural networks (ResNet) were trained for the categorization. We applied 10-fold cross-validation method to train and optimize our algorithms. The area under the receiver operating characteristic curve (AUC), accuracy and kappa value were calculated to evaluate the performance of the intelligent system in categorizing OCT images. We also compared the performance of the system with results obtained by two experts. RESULTS: The intelligent system achieved an AUC of 0.984 with an accuracy of 0.959 in detecting macular hole, cystoid macular edema, epiretinal membrane, and serous macular detachment. Specifically, the accuracies in discriminating normal images, cystoid macular edema, serous macular detachment, epiretinal membrane, and macular hole were 0.973, 0.848, 0.947, 0.957, and 0.978, respectively. The system had a kappa value of 0.929, while the two physicians' kappa values were 0.882 and 0.889 independently. CONCLUSIONS: This deep learning-based system is able to automatically detect and differentiate various OCT images with excellent accuracy. Moreover, the performance of the system is at a level comparable to or better than that of human experts. This study is a promising step in revolutionizing current disease diagnostic pattern and has the potential to generate a significant clinical impact. TRANSLATIONAL RELEVANCE: This intelligent system has great value in increasing retinal diseases' diagnostic efficiency in clinical circumstances.
format Online
Article
Text
id pubmed-6314222
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-63142222019-01-07 Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images Lu, Wei Tong, Yan Yu, Yue Xing, Yiqiao Chen, Changzheng Shen, Yin Transl Vis Sci Technol Articles PURPOSE: To develop a new intelligent system based on deep learning for automatically optical coherence tomography (OCT) images categorization. METHODS: A total of 60,407 OCT images were labeled by 17 licensed retinal experts and 25,134 images were included. One hundred one-layer convolutional neural networks (ResNet) were trained for the categorization. We applied 10-fold cross-validation method to train and optimize our algorithms. The area under the receiver operating characteristic curve (AUC), accuracy and kappa value were calculated to evaluate the performance of the intelligent system in categorizing OCT images. We also compared the performance of the system with results obtained by two experts. RESULTS: The intelligent system achieved an AUC of 0.984 with an accuracy of 0.959 in detecting macular hole, cystoid macular edema, epiretinal membrane, and serous macular detachment. Specifically, the accuracies in discriminating normal images, cystoid macular edema, serous macular detachment, epiretinal membrane, and macular hole were 0.973, 0.848, 0.947, 0.957, and 0.978, respectively. The system had a kappa value of 0.929, while the two physicians' kappa values were 0.882 and 0.889 independently. CONCLUSIONS: This deep learning-based system is able to automatically detect and differentiate various OCT images with excellent accuracy. Moreover, the performance of the system is at a level comparable to or better than that of human experts. This study is a promising step in revolutionizing current disease diagnostic pattern and has the potential to generate a significant clinical impact. TRANSLATIONAL RELEVANCE: This intelligent system has great value in increasing retinal diseases' diagnostic efficiency in clinical circumstances. The Association for Research in Vision and Ophthalmology 2018-12-28 /pmc/articles/PMC6314222/ /pubmed/30619661 http://dx.doi.org/10.1167/tvst.7.6.41 Text en Copyright 2018 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 Articles
Lu, Wei
Tong, Yan
Yu, Yue
Xing, Yiqiao
Chen, Changzheng
Shen, Yin
Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
title Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
title_full Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
title_fullStr Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
title_full_unstemmed Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
title_short Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images
title_sort deep learning-based automated classification of multi-categorical abnormalities from optical coherence tomography images
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6314222/
https://www.ncbi.nlm.nih.gov/pubmed/30619661
http://dx.doi.org/10.1167/tvst.7.6.41
work_keys_str_mv AT luwei deeplearningbasedautomatedclassificationofmulticategoricalabnormalitiesfromopticalcoherencetomographyimages
AT tongyan deeplearningbasedautomatedclassificationofmulticategoricalabnormalitiesfromopticalcoherencetomographyimages
AT yuyue deeplearningbasedautomatedclassificationofmulticategoricalabnormalitiesfromopticalcoherencetomographyimages
AT xingyiqiao deeplearningbasedautomatedclassificationofmulticategoricalabnormalitiesfromopticalcoherencetomographyimages
AT chenchangzheng deeplearningbasedautomatedclassificationofmulticategoricalabnormalitiesfromopticalcoherencetomographyimages
AT shenyin deeplearningbasedautomatedclassificationofmulticategoricalabnormalitiesfromopticalcoherencetomographyimages