Research

Jump to: Review

10 pages, 1414 KiB

Open AccessArticle

Clinical Research of Lupus Retinopathy: Quantitative Analysis of Retinal Vessels by Optical Coherence Tomography Angiography in Patients with Systemic Lupus Erythematosus

by Ximin Wang, Huan Xie, Yao Yi, Jinhan Zhou, Huimin Yang and Jin Li

Diagnostics 2023, 13(20), 3222; https://doi.org/10.3390/diagnostics13203222 - 16 Oct 2023

Viewed by 815

Abstract

Background: Lupus retinopathy, an ocular manifestation of systemic lupus erythematosus (SLE), is the major pathology attributed to retinal vasculopathy. Our study is to analyze the changes in retinal vessels in patients with SLE by optical coherence tomography angiography. Methods: A total of 61 [...] Read more.

Background: Lupus retinopathy, an ocular manifestation of systemic lupus erythematosus (SLE), is the major pathology attributed to retinal vasculopathy. Our study is to analyze the changes in retinal vessels in patients with SLE by optical coherence tomography angiography. Methods: A total of 61 SLE patients without obvious retinal manifestation and 71 healthy people were included. The SLE patients were further divided into a lupus nephritis (LN) group and a non-LN group. The changes in central macular thickness (CMT) and the retinal vessel densities were compared between the two groups, and the correlation between retinal vascular changes and disease activity was analyzed. Results: Compared with healthy control, the CMT and the retinal vascular densities in both superficial and deep retina were decreased significantly in SLE patients. There was no significant difference in retinal vascular densities between LN groups and non-LN groups. Conclusion: The CMT and retinal vessel densities were decreased in SLE patients without clinical manifestations, which might serve as a sensitive biomarker for early changes of lupus retinopathy in SLE patients. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

16 pages, 2482 KiB

Open AccessArticle

Counteracting Data Bias and Class Imbalance—Towards a Useful and Reliable Retinal Disease Recognition System

by Adam R. Chłopowiec, Konrad Karanowski, Tomasz Skrzypczak, Mateusz Grzesiuk, Adrian B. Chłopowiec and Martin Tabakov

Diagnostics 2023, 13(11), 1904; https://doi.org/10.3390/diagnostics13111904 - 29 May 2023

Viewed by 1318

Abstract

Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained on large diverse dataset. No study has addressed a class imbalance problem in one giant [...] Read more.

Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained on large diverse dataset. No study has addressed a class imbalance problem in one giant dataset originating from multiple large diverse eye fundus image collections. To ensure a real-life clinical environment and mitigate the problem of biased medical image data, 22 publicly available datasets were merged. To secure medical validity only Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD) and Glaucoma (GL) were included. The state-of-the-art models ConvNext, RegNet and ResNet were utilized. In the resulting dataset, there were 86,415 normal, 3787 GL, 632 AMD and 34,379 DR fundus images. ConvNextTiny achieved the best results in terms of recognizing most of the examined eye diseases with the most metrics. The overall accuracy was 80.46 ± 1.48. Specific accuracy values were: 80.01 ± 1.10 for normal eye fundus, 97.20 ± 0.66 for GL, 98.14 ± 0.31 for AMD, 80.66 ± 1.27 for DR. A suitable screening model for the most prevalent retinal diseases in ageing societies was designed. The model was developed on a diverse, combined large dataset which made the obtained results less biased and more generalizable. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

10 pages, 2406 KiB

Open AccessArticle

The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation

by Natsuda Kaothanthong, Jirawut Limwattanayingyong, Sukhum Silpa-archa, Mongkol Tadarati, Atchara Amphornphruet, Panisa Singhanetr, Pawas Lalitwongsa, Pantid Chantangphol, Anyarak Amornpetchsathaporn, Methaphon Chainakul and Paisan Ruamviboonsuk

Diagnostics 2023, 13(2), 189; https://doi.org/10.3390/diagnostics13020189 - 04 Jan 2023

Cited by 2 | Viewed by 1907

Abstract

We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular degeneration, polypoidal choroidal [...] Read more.

We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, diabetic macular edema, retinal vein occlusion, cystoid macular edema in Irvine-Gass syndrome, and other macular diseases, along with the normal fellow eyes. A total of 14,327 OCT images were used to train DL models. Three experiments were conducted: classification alone (CA), use of automated segmentation of the OCT images by RelayNet, and the graph-cut technique before the classification (combination method 1 (CM1) and 2 (CM2), respectively). For validation of classification of the macular diseases, the sensitivity, specificity, and accuracy of CA were found at 62.55%, 95.16%, and 93.14%, respectively, whereas the sensitivity, specificity, and accuracy of CM1 were found at 72.90%, 96.20%, and 93.92%, respectively, and of CM2 at 71.36%, 96.42%, and 94.80%, respectively. The accuracy of CM2 was statistically higher than that of CA (p = 0.05878). All three methods achieved AUC at 97%. Applying DL for segmentation of OCT images prior to classification of the images by another DL model may improve the performance of the classification. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

13 pages, 3117 KiB

Open AccessArticle

A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders

by Ebenezer Chan, Zhiqun Tang, Raymond P. Najjar, Arun Narayanaswamy, Kanchalika Sathianvichitr, Nancy J. Newman, Valérie Biousse, Dan Milea and for the BONSAI Group

Diagnostics 2023, 13(1), 160; https://doi.org/10.3390/diagnostics13010160 - 03 Jan 2023

Cited by 3 | Viewed by 1966

Abstract

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, [...] Read more.

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of “good”, “borderline”, or “poor” quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance “good” quality photographs (AUC = 0.93 (95% CI, 0.91–0.95), accuracy = 91.4% (95% CI, 90.0–92.9%), sensitivity = 93.8% (95% CI, 92.5–95.2%), specificity = 75.9% (95% CI, 69.7–82.1%) and “poor” quality photographs (AUC = 1.00 (95% CI, 0.99–1.00), accuracy = 99.1% (95% CI, 98.6–99.6%), sensitivity = 81.5% (95% CI, 70.6–93.8%), specificity = 99.7% (95% CI, 99.6–100.0%). “Borderline” quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88–0.93), accuracy = 90.6% (95% CI, 89.1–92.2%), sensitivity = 65.4% (95% CI, 56.6–72.9%), specificity = 93.4% (95% CI, 92.1–94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1–92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

11 pages, 3609 KiB

Open AccessArticle

Deep Learning Approach in Image Diagnosis of Pseudomonas Keratitis

by Ming-Tse Kuo, Benny Wei-Yun Hsu, Yi Sheng Lin, Po-Chiung Fang, Hun-Ju Yu, Yu-Ting Hsiao and Vincent S. Tseng

Diagnostics 2022, 12(12), 2948; https://doi.org/10.3390/diagnostics12122948 - 25 Nov 2022

Cited by 3 | Viewed by 2447

Abstract

This investigation aimed to explore deep learning (DL) models’ potential for diagnosing Pseudomonas keratitis using external eye images. In the retrospective research, the images of bacterial keratitis (BK, n = 929), classified as Pseudomonas (n = 618) and non-Pseudomonas (n [...] Read more.

This investigation aimed to explore deep learning (DL) models’ potential for diagnosing Pseudomonas keratitis using external eye images. In the retrospective research, the images of bacterial keratitis (BK, n = 929), classified as Pseudomonas (n = 618) and non-Pseudomonas (n = 311) keratitis, were collected. Eight DL algorithms, including ResNet50, DenseNet121, ResNeXt50, SE-ResNet50, and EfficientNets B0 to B3, were adopted as backbone models to train and obtain the best ensemble 2-, 3-, 4-, and 5-DL models. Five-fold cross-validation was used to determine the ability of single and ensemble models to diagnose Pseudomonas keratitis. The EfficientNet B2 model had the highest accuracy (71.2%) of the eight single-DL models, while the best ensemble 4-DL model showed the highest accuracy (72.1%) among the ensemble models. However, no statistical difference was shown in the area under the receiver operating characteristic curve and diagnostic accuracy among these single-DL models and among the four best ensemble models. As a proof of concept, the DL approach, via external eye photos, could assist in identifying Pseudomonas keratitis from BK patients. All the best ensemble models can enhance the performance of constituent DL models in diagnosing Pseudomonas keratitis, but the enhancement effect appears to be limited. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

16 pages, 4161 KiB

Open AccessArticle

Deep Learning-Based Glaucoma Screening Using Regional RNFL Thickness in Fundus Photography

by Hyunmo Yang, Yujin Ahn, Sanzhar Askaruly, Joon S. You, Sang Woo Kim and Woonggyu Jung

Diagnostics 2022, 12(11), 2894; https://doi.org/10.3390/diagnostics12112894 - 21 Nov 2022

Cited by 3 | Viewed by 1894

Abstract

Since glaucoma is a progressive and irreversible optic neuropathy, accurate screening and/or early diagnosis is critical in preventing permanent vision loss. Recently, optical coherence tomography (OCT) has become an accurate diagnostic tool to observe and extract the thickness of the retinal nerve fiber [...] Read more.

Since glaucoma is a progressive and irreversible optic neuropathy, accurate screening and/or early diagnosis is critical in preventing permanent vision loss. Recently, optical coherence tomography (OCT) has become an accurate diagnostic tool to observe and extract the thickness of the retinal nerve fiber layer (RNFL), which closely reflects the nerve damage caused by glaucoma. However, OCT is less accessible than fundus photography due to higher cost and expertise required for operation. Though widely used, fundus photography is effective for early glaucoma detection only when used by experts with extensive training. Here, we introduce a deep learning-based approach to predict the RNFL thickness around optic disc regions in fundus photography for glaucoma screening. The proposed deep learning model is based on a convolutional neural network (CNN) and utilizes images taken with fundus photography and with RNFL thickness measured with OCT for model training and validation. Using a dataset acquired from normal tension glaucoma (NTG) patients, the trained model can estimate RNFL thicknesses in 12 optic disc regions from fundus photos. Using intuitive thickness labels to identify localized damage of the optic nerve head and then estimating regional RNFL thicknesses from fundus images, we determine that screening for glaucoma could achieve 92% sensitivity and 86.9% specificity. Receiver operating characteristic (ROC) analysis results for specificity of 80% demonstrate that use of the localized mean over superior and inferior regions reaches 90.7% sensitivity, whereas 71.2% sensitivity is reached using the global RNFL thicknesses for specificity at 80%. This demonstrates that the new approach of using regional RNFL thicknesses in fundus images holds good promise as a potential screening technique for early stage of glaucoma. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

14 pages, 1239 KiB

Open AccessArticle

Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

by Nergis C. Khan, Chandrashan Perera, Eliot R. Dow, Karen M. Chen, Vinit B. Mahajan, Prithvi Mruthyunjaya, Diana V. Do, Theodore Leng and David Myung

Diagnostics 2022, 12(7), 1714; https://doi.org/10.3390/diagnostics12071714 - 14 Jul 2022

Cited by 12 | Viewed by 4783

Abstract

While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial [...] Read more.

While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

Review

Jump to: Research

19 pages, 2472 KiB

Open AccessReview

Deep Learning in Optical Coherence Tomography Angiography: Current Progress, Challenges, and Future Directions

by Dawei Yang, An Ran Ran, Truong X. Nguyen, Timothy P. H. Lin, Hao Chen, Timothy Y. Y. Lai, Clement C. Tham and Carol Y. Cheung

Diagnostics 2023, 13(2), 326; https://doi.org/10.3390/diagnostics13020326 - 16 Jan 2023

Cited by 9 | Viewed by 3457

Abstract

Optical coherence tomography angiography (OCT-A) provides depth-resolved visualization of the retinal microvasculature without intravenous dye injection. It facilitates investigations of various retinal vascular diseases and glaucoma by assessment of qualitative and quantitative microvascular changes in the different retinal layers and radial peripapillary layer [...] Read more.

Optical coherence tomography angiography (OCT-A) provides depth-resolved visualization of the retinal microvasculature without intravenous dye injection. It facilitates investigations of various retinal vascular diseases and glaucoma by assessment of qualitative and quantitative microvascular changes in the different retinal layers and radial peripapillary layer non-invasively, individually, and efficiently. Deep learning (DL), a subset of artificial intelligence (AI) based on deep neural networks, has been applied in OCT-A image analysis in recent years and achieved good performance for different tasks, such as image quality control, segmentation, and classification. DL technologies have further facilitated the potential implementation of OCT-A in eye clinics in an automated and efficient manner and enhanced its clinical values for detecting and evaluating various vascular retinopathies. Nevertheless, the deployment of this combination in real-world clinics is still in the “proof-of-concept” stage due to several limitations, such as small training sample size, lack of standardized data preprocessing, insufficient testing in external datasets, and absence of standardized results interpretation. In this review, we introduce the existing applications of DL in OCT-A, summarize the potential challenges of the clinical deployment, and discuss future research directions. Full article

(This article belongs to the Special Issue Deep Learning Applications in Ophthalmology)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Deep Learning Applications in Ophthalmology

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI