Dataset Information

Development and Validation of a Deep Learning System for Diagnosing Glaucoma Using Optical Coherence Tomography.

ABSTRACT: This study aimed to develop and validate a deep learning system for diagnosing glaucoma using optical coherence tomography (OCT). A training set of 1822 eyes (332 control, 1490 glaucoma) with 7288 OCT images, an internal validation set of 425 eyes (104 control, 321 glaucoma) with 1700 images, and an external validation set of 355 eyes (108 control, 247 glaucoma) with 1420 images were included. Deviation and thickness maps of retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (GCIPL) analyses were used to develop the deep learning system for glaucoma diagnosis based on the visual geometry group deep convolutional neural network (VGG-19) model. The diagnostic abilities of deep learning models using different OCT maps were evaluated, and the best model was compared with the diagnostic results produced by two glaucoma specialists. The glaucoma-diagnostic ability was highest when the deep learning system used the RNFL thickness map alone (area under the receiver operating characteristic curve (AUROC) 0.987), followed by the RNFL deviation map (AUROC 0.974), the GCIPL thickness map (AUROC 0.966), and the GCIPL deviation map (AUROC 0.903). Among combination sets, use of the RNFL and GCIPL deviation map showed the highest diagnostic ability, showing similar results when tested via an external validation dataset. The inclusion of the axial length did not significantly affect the diagnostic performance of the deep learning system. The location of glaucomatous damage showed generally high level of agreement between the heatmap and the diagnosis of glaucoma specialists, with 90.0% agreement when using the RNFL thickness map and 88.0% when using the GCIPL thickness map. In conclusion, our deep learning system showed high glaucoma-diagnostic abilities using OCT thickness and deviation maps. It also showed detection patterns similar to those of glaucoma specialists, showing promising results for future clinical application as an interpretable computer-aided diagnosis.

SUBMITTER: Kim KE

PROVIDER: S-EPMC7408821 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and Validation of a Deep Learning System for Diagnosing Glaucoma Using Optical Coherence Tomography.

Kim Ko Eun KE Kim Joon Mo JM Song Ji Eun JE Kee Changwon C Han Jong Chul JC Hyun Seung Hyup SH

Journal of clinical medicine 20200709 7

This study aimed to develop and validate a deep learning system for diagnosing glaucoma using optical coherence tomography (OCT). A training set of 1822 eyes (332 control, 1490 glaucoma) with 7288 OCT images, an internal validation set of 425 eyes (104 control, 321 glaucoma) with 1700 images, and an external validation set of 355 eyes (108 control, 247 glaucoma) with 1420 images were included. Deviation and thickness maps of retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform laye ...[more]

PMID: 32659918

Similar Datasets

Project description:ImportanceConventional segmentation of the retinal nerve fiber layer (RNFL) is prone to errors that may affect the accuracy of spectral-domain optical coherence tomography (SD-OCT) scans in detecting glaucomatous damage.ObjectiveTo develop a segmentation-free deep learning (DL) algorithm for assessment of glaucomatous damage using the entire circle B-scan image from SD-OCT.Design, setting, and participantsThis cross-sectional study at a single institution used data from SD-OCT images of eyes with glaucoma (perimetric and preperimetric) and normal eyes. The data set was randomly split at the patient level into a training (50%), validation (20%), and test data set (30%). Data were collected from March 2008 to April 2019, and analysis began April 2018.ExposuresA convolutional neural network was trained to discriminate glaucomatous from normal eyes using the SD-OCT circle B-scan without segmentation lines.Main outcomes and measuresThe ability to discriminate glaucoma from healthy eyes was evaluated by comparing the area under the receiver operating characteristic curve and sensitivity at 80% or 95% specificity for the DL algorithm's predicted probability of glaucoma vs conventional RNFL thickness parameters given by SD-OCT software. The performance was also assessed in preperimetric glaucoma, as well as by visual field severity using Hodapp-Parrish-Anderson criteria.ResultsA total of 20 806 SD-OCT images from 1154 eyes of 635 individuals (612 [53%] with glaucoma and 542 normal eyes [47%]) were included. The mean (SD) age at SD-OCT scan was 70.8 (10.4) years in individuals with glaucoma and 55.8 (14.1) years in controls. There were 187 women (53.3%) in the glaucoma group and 165 (59.8%) in the control group. Of 612 eyes with glaucoma, 432 (70.4%) had perimetric and 180 (29.6%) had preperimetric glaucoma. The DL algorithm had a significantly higher area under the receiver operating characteristic curve than global RNFL thickness (0.96 vs 0.87; difference = 0.08 [95% CI, 0.04-0.12]) and each RNFL thickness sector for discriminating between glaucoma and controls (all P < .001). At 95% specificity, the DL algorithm (81%; 95% CI, 64%-97%) was more sensitive than global RNFL thickness (67%; 95% CI, 58%-76%). The areas under the receiver operating characteristic curve were also significantly greater for the DL algorithm compared with RNFL thickness at each stage of disease, especially preperimetric and mild perimetric glaucoma.Conclusions and relevanceA segmentation-free DL algorithm performed better than conventional RNFL thickness parameters for diagnosing glaucomatous damage on OCT scans, especially in early disease. Future studies should investigate how such an approach contributes to diagnostic decisions when combined with other relevant clinical information, such as risk factors and perimetry results.

Project description:Importance:Whether optical coherence tomography angiography (OCT-A) outperforms OCT to detect glaucoma remains inconclusive. Objective:To compare (1) the diagnostic performance for detection of glaucoma and (2) the structure-function association between inner macular vessel density and inner macular thickness. Design, Setting, and Participants:This cross-sectional study included 115 patients with glaucoma and 35 healthy individuals for measurements of retinal thickness and retinal vessel density, segmented between the anterior boundary of internal limiting membrane and the posterior boundary of the inner plexiform layer, over the 3 × 3-mm2 macula using swept-source OCT. All participants were Chinese. Visual sensitivity corresponding to the 3 × 3-mm2 macular region was expressed in unlogged 1/lambert for investigation of the structure-function associations. Diagnostic performance was evaluated with area under the receiver operating characteristic curves (AUCs). The study was conducted between January 12, 2016, and December 12, 2016. Main Outcomes and Measures:Area under the receiver operating characteristic curve and R2 analysis. Results:Of the 115 patients with glaucoma, 42 (36.5%) were women (mean [SD] age, 53.5 [13.4] years); of the 35 individuals with healthy eyes, 25 (71.4%) were women (age, 60.6 [5.9] years). Inner macular vessel density and thickness were 4.3% (95% CI, 2.4%-6.1%) and 21.1 μm (95% CI, 17.4-24.9 μm) smaller, respectively, in eyes with glaucoma compared with healthy eyes. The AUC of mean inner macular thickness for glaucoma detection was greater than that of mean inner macular vessel density (difference, 0.17; 95% CI, 0.01-0.31; P = .03). At 90% specificity, the sensitivity of mean inner macular thicknesses for detection of glaucoma was greater than that of mean inner macular vessel densities (difference, 29.2%; 95% CI, 11.5%-64.6%; P = .02). The strength of the structure-function association was stronger for mean inner macular thickness than mean inner macular vessel density in the linear (difference in R2 = 0.38; 95% CI, 0.22-0.54; P < .001) and nonlinear (difference in R2 = 0.36; 95% CI, 0.21-0.51; P < .001) regression models. Conclusions and Relevance:In this study, OCT measurement of inner macular thickness shows a higher diagnostic performance to detect glaucoma and a stronger structure-function association than the currently used OCT-A measurement of inner macular vessel density. These findings may suggest that OCT-A of the macula has a limited role in the diagnostic evaluation of glaucoma.

Dataset Information

Development and Validation of a Deep Learning System for Diagnosing Glaucoma Using Optical Coherence Tomography.

Publications

Development and Validation of a Deep Learning System for Diagnosing Glaucoma Using Optical Coherence Tomography.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets