2023
DOI: 10.1101/2023.03.06.23286879
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Glaucoma Detection and Feature Visualization from OCT Images Using Deep Learning

Abstract: Purpose: In this paper, we aimed to clinically interpret Temporal-Superior-Nasal-Inferior-Temporal (TSNIT) retinal optical coherence tomography (OCT) images in a convolutional neural network (CNN) model to differentiate between normal and glaucomatous optic neuropathy. Methods: Three modified pre-trained deep learning (DL) models: SqueezeNet, ResNet18, and VGG16, were fine-tuned for transfer learning to visualize CNN features and detect glaucoma using 780 segmented and 780 raw TSNIT OCT B-scans of 370 glaucoma… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 43 publications
0
1
0
Order By: Relevance
“…[8][9][10][11][12] For instance, Akter et al employed VGG16, SqueezeNet, and ResNet18 models on a dataset of 780 segmented and 780 raw TSNIT OCT B-scans, resulting in an AUC of 0.93 on test data. 13 Another multi-institutional study developed a DL model to diagnose early-onset glaucoma using spectral-domain OCT images. Pre-trained on 4,316 OCT images from 1,371 eyes with open-angle glaucoma and 193 normal eyes, and then trained on a dataset from 94 patients with early glaucoma and 84 normal subjects, the model achieved an AUC of 0.937, outperforming random forests and support vector machine models.…”
Section: Introductionmentioning
confidence: 99%
“…[8][9][10][11][12] For instance, Akter et al employed VGG16, SqueezeNet, and ResNet18 models on a dataset of 780 segmented and 780 raw TSNIT OCT B-scans, resulting in an AUC of 0.93 on test data. 13 Another multi-institutional study developed a DL model to diagnose early-onset glaucoma using spectral-domain OCT images. Pre-trained on 4,316 OCT images from 1,371 eyes with open-angle glaucoma and 193 normal eyes, and then trained on a dataset from 94 patients with early glaucoma and 84 normal subjects, the model achieved an AUC of 0.937, outperforming random forests and support vector machine models.…”
Section: Introductionmentioning
confidence: 99%