Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images
PurposeA common ocular manifestation, macular edema (ME) is the primary cause of visual deterioration. In this study, an artificial intelligence method based on multi-feature fusion was introduced to enable automatic ME classification on spectral-domain optical coherence tomography (SD-OCT) images,...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-01-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1097291/full |
_version_ | 1811175385938788352 |
---|---|
author | Fan Gan Fan Gan Fei-Peng Wu Yu-Lin Zhong |
author_facet | Fan Gan Fan Gan Fei-Peng Wu Yu-Lin Zhong |
author_sort | Fan Gan |
collection | DOAJ |
description | PurposeA common ocular manifestation, macular edema (ME) is the primary cause of visual deterioration. In this study, an artificial intelligence method based on multi-feature fusion was introduced to enable automatic ME classification on spectral-domain optical coherence tomography (SD-OCT) images, to provide a convenient method of clinical diagnosis.MethodsFirst, 1,213 two-dimensional (2D) cross-sectional OCT images of ME were collected from the Jiangxi Provincial People’s Hospital between 2016 and 2021. According to OCT reports of senior ophthalmologists, there were 300 images with diabetic (DME), 303 images with age-related macular degeneration (AMD), 304 images with retinal-vein occlusion (RVO), and 306 images with central serous chorioretinopathy (CSC). Then, traditional omics features of the images were extracted based on the first-order statistics, shape, size, and texture. After extraction by the alexnet, inception_v3, resnet34, and vgg13 models and selected by dimensionality reduction using principal components analysis (PCA), the deep-learning features were fused. Next, the gradient-weighted class-activation map (Grad-CAM) was used to visualize the-deep-learning process. Finally, the fusion features set, which was fused from the traditional omics features and the deep-fusion features, was used to establish the final classification models. The performance of the final models was evaluated by accuracy, confusion matrix, and the receiver operating characteristic (ROC) curve.ResultsCompared with other classification models, the performance of the support vector machine (SVM) model was best, with an accuracy of 93.8%. The area under curves AUC of micro- and macro-averages were 99%, and the AUC of the AMD, DME, RVO, and CSC groups were 100, 99, 98, and 100%, respectively.ConclusionThe artificial intelligence model in this study could be used to classify DME, AME, RVO, and CSC accurately from SD-OCT images. |
first_indexed | 2024-04-10T19:35:15Z |
format | Article |
id | doaj.art-2d349f79ff204db2b5379875398f2e85 |
institution | Directory Open Access Journal |
issn | 1662-453X |
language | English |
last_indexed | 2024-04-10T19:35:15Z |
publishDate | 2023-01-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroscience |
spelling | doaj.art-2d349f79ff204db2b5379875398f2e852023-01-30T05:45:11ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-01-011710.3389/fnins.2023.10972911097291Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) imagesFan Gan0Fan Gan1Fei-Peng Wu2Yu-Lin Zhong3Medical College of Nanchang University, Nanchang, ChinaDepartment of Ophthalmology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Ophthalmology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Ophthalmology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaPurposeA common ocular manifestation, macular edema (ME) is the primary cause of visual deterioration. In this study, an artificial intelligence method based on multi-feature fusion was introduced to enable automatic ME classification on spectral-domain optical coherence tomography (SD-OCT) images, to provide a convenient method of clinical diagnosis.MethodsFirst, 1,213 two-dimensional (2D) cross-sectional OCT images of ME were collected from the Jiangxi Provincial People’s Hospital between 2016 and 2021. According to OCT reports of senior ophthalmologists, there were 300 images with diabetic (DME), 303 images with age-related macular degeneration (AMD), 304 images with retinal-vein occlusion (RVO), and 306 images with central serous chorioretinopathy (CSC). Then, traditional omics features of the images were extracted based on the first-order statistics, shape, size, and texture. After extraction by the alexnet, inception_v3, resnet34, and vgg13 models and selected by dimensionality reduction using principal components analysis (PCA), the deep-learning features were fused. Next, the gradient-weighted class-activation map (Grad-CAM) was used to visualize the-deep-learning process. Finally, the fusion features set, which was fused from the traditional omics features and the deep-fusion features, was used to establish the final classification models. The performance of the final models was evaluated by accuracy, confusion matrix, and the receiver operating characteristic (ROC) curve.ResultsCompared with other classification models, the performance of the support vector machine (SVM) model was best, with an accuracy of 93.8%. The area under curves AUC of micro- and macro-averages were 99%, and the AUC of the AMD, DME, RVO, and CSC groups were 100, 99, 98, and 100%, respectively.ConclusionThe artificial intelligence model in this study could be used to classify DME, AME, RVO, and CSC accurately from SD-OCT images.https://www.frontiersin.org/articles/10.3389/fnins.2023.1097291/fullartificial intelligencemacular edemamulti-feature fusionSD-OCT imagesclassification models |
spellingShingle | Fan Gan Fan Gan Fei-Peng Wu Yu-Lin Zhong Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images Frontiers in Neuroscience artificial intelligence macular edema multi-feature fusion SD-OCT images classification models |
title | Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images |
title_full | Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images |
title_fullStr | Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images |
title_full_unstemmed | Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images |
title_short | Artificial intelligence method based on multi-feature fusion for automatic macular edema (ME) classification on spectral-domain optical coherence tomography (SD-OCT) images |
title_sort | artificial intelligence method based on multi feature fusion for automatic macular edema me classification on spectral domain optical coherence tomography sd oct images |
topic | artificial intelligence macular edema multi-feature fusion SD-OCT images classification models |
url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1097291/full |
work_keys_str_mv | AT fangan artificialintelligencemethodbasedonmultifeaturefusionforautomaticmacularedemameclassificationonspectraldomainopticalcoherencetomographysdoctimages AT fangan artificialintelligencemethodbasedonmultifeaturefusionforautomaticmacularedemameclassificationonspectraldomainopticalcoherencetomographysdoctimages AT feipengwu artificialintelligencemethodbasedonmultifeaturefusionforautomaticmacularedemameclassificationonspectraldomainopticalcoherencetomographysdoctimages AT yulinzhong artificialintelligencemethodbasedonmultifeaturefusionforautomaticmacularedemameclassificationonspectraldomainopticalcoherencetomographysdoctimages |