Dataset Information

Quantitative Assessment of Fundus Tessellated Density in Highly Myopic Glaucoma Using Deep Learning.

ABSTRACT:

Purpose

To characterize the fundus tessellated density (FTD) in highly myopic glaucoma (HMG) and high myopia (HM) for discovering early signs and diagnostic markers.

Methods

This retrospective cross-sectional study included hospital in-patients with HM (133 eyes) and HMG (73 eyes) with an axial length ≥26 mm at Zhongshan Ophthalmic Center. Using deep learning, FTD was quantified as the average exposed choroid area per unit area on fundus photographs in the global, macular, and disc regions. FTD-associated factors were assessed using partial correlation. Diagnostic efficacy was analyzed using the area under the curve (AUC).

Results

HMG patients had lower global (0.20 ± 0.12 versus 0.36 ± 0.09) and macular FTD (0.25 ± 0.14 vs. 0.40 ± 0.09) but larger disc FTD (0.24 ± 0.11 vs. 0.19 ± 0.07) than HM patients in the tessellated fundus (all P < 0.001). In the macular region, nasal FTD was lowest in the HM (0.26 ± 0.13) but highest in the HMG (0.32 ± 0.13) compared with the superior, inferior, and temporal subregions (all P < 0.05). A fundus with a macular region nasal/temporal (NT) FTD ratio > 0.96 (AUC = 0.909) was 15.7 times more indicative of HMG than HM. A higher macular region NT ratio with a lower horizontal parapapillary atrophy/disc ratio indicated a higher possibility of HMG than HM (AUC = 0.932).

Conclusions

FTD differs in degree and distribution between HMG and HM. A higher macular NT alone or with a lower horizontal parapapillary atrophy/disc ratio may help differentiate HMG.

Translational relevance

Deep learning-based FTD measurement could potentially assist glaucoma diagnosis in HM.

SUBMITTER: Chen X

PROVIDER: S-EPMC11008756 | biostudies-literature | 2024 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Quantitative Assessment of Fundus Tessellated Density in Highly Myopic Glaucoma Using Deep Learning.

Chen Xiaohong X Chen Xuhao X Chen Jianqi J Li Zhidong Z Huang Shaofen S Shen Xinyue X Xiao Yue Y Wu Zhenquan Z Zhu Yingting Y Lu Lin L Zhuo Yehong Y

Translational vision science & technology 20240401 4

<h4>Purpose</h4>To characterize the fundus tessellated density (FTD) in highly myopic glaucoma (HMG) and high myopia (HM) for discovering early signs and diagnostic markers.<h4>Methods</h4>This retrospective cross-sectional study included hospital in-patients with HM (133 eyes) and HMG (73 eyes) with an axial length ≥26 mm at Zhongshan Ophthalmic Center. Using deep learning, FTD was quantified as the average exposed choroid area per unit area on fundus photographs in the global, macular, and dis ...[more]

PMID: 38591943

Similar Datasets

Project description:PurposeTo explore associations of fundus tessellated density (FTD) and compare characteristics of different fundus tessellation (FT) distribution patterns, based on artificial intelligence technology using deep learning.MethodsComprehensive ocular examinations were conducted in 577 children aged 7 years old from a population-based cross-sectional study, including biometric measurement, refraction, optical coherence tomography angiography, and 45° nonmydriatic fundus photography. FTD was defined as the average exposed choroid area per unit area of the fundus, and obtained by artificial intelligence technology. The distribution of FT was classified into the macular pattern and the peripapillary pattern according to FTD.ResultsThe mean FTD was 0.024 ± 0.026 in whole fundus. Multivariate regression analysis showed that greater FTD was significantly correlated with thinner subfoveal choroidal thickness, larger parapapillary atrophy, greater vessel density inside the optic disc, larger vertical diameter of optic disc, thinner retinal nerve fiber layer, and longer distance from optic disc center to macular fovea (all P < 0.05). The peripapillary distributed group had larger parapapillary atrophy (0.052 ± 0.119 vs 0.031 ± 0.072), greater FTD (0.029 ± 0.028 vs 0.015 ± 0.018), thinner subfoveal choroidal thickness (297.66 ± 60.61 vs 315.33 ± 66.46), and thinner retinal thickness (285.55 ± 10.89 vs 288.03 ± 10.31) than the macular distributed group (all P < 0.05).ConclusionsFTD can be applied as a quantitative biomarker to estimate subfoveal choroidal thickness in children. The role of blood flow inside optic disc in FT progression needs further investigation. The distribution of FT and the peripapillary pattern correlated more with myopia-related fundus changes than the macular pattern.Translational relevanceArtificial intelligence can evaluate FT quantitatively in children, and has potential value for assisting in myopia prevention and control.

Project description:To compare the diagnostic accuracy and explainability of a Vision Transformer deep learning technique, Data-efficient image Transformer (DeiT), and ResNet-50, trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG) and identify the salient areas of the photographs most important for each model's decision-making process. Evaluation of a diagnostic technology. Overall 66 715 photographs from 1636 OHTS participants and an additional 5 external datasets of 16 137 photographs of healthy and glaucoma eyes. Data-efficient image Transformer models were trained to detect 5 ground-truth OHTS POAG classifications: OHTS end point committee POAG determinations because of disc changes (model 1), visual field (VF) changes (model 2), or either disc or VF changes (model 3) and Reading Center determinations based on disc (model 4) and VFs (model 5). The best-performing DeiT models were compared with ResNet-50 models on OHTS and 5 external datasets. Diagnostic performance was compared using areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities. The explainability of the DeiT and ResNet-50 models was compared by evaluating the attention maps derived directly from DeiT to 3 gradient-weighted class activation map strategies. Compared with our best-performing ResNet-50 models, the DeiT models demonstrated similar performance on the OHTS test sets for all 5 ground-truth POAG labels; AUROC ranged from 0.82 (model 5) to 0.91 (model 1). Data-efficient image Transformer AUROC was consistently higher than ResNet-50 on the 5 external datasets. For example, AUROC for the main OHTS end point (model 3) was between 0.08 and 0.20 higher in the DeiT than ResNet-50 models. The saliency maps from the DeiT highlight localized areas of the neuroretinal rim, suggesting important rim features for classification. The same maps in the ResNet-50 models show a more diffuse, generalized distribution around the optic disc. Vision Transformers have the potential to improve generalizability and explainability in deep learning models, detecting eye disease and possibly other medical conditions that rely on imaging for clinical diagnosis and management.

Project description:PurposeColor fundus photography is widely used in clinical and screening settings for eye diseases. Poor image quality greatly affects the reliability of further evaluation and diagnosis. In this study, we developed an automated assessment module for color fundus photography image quality assessment using deep learning.MethodsA total of 55,931 color fundus photography images from multiple centers in Shanghai and the public database were collected and annotated as training, validation, and testing data sets. The pre-diagnosis image quality assessment module based on the multi-task deep neural network was designed. The detailed criterion of color fundus photography image quality including three subcategories with three levels of grading was applied to improve precision and objectivity. The auxiliary tasks such as the localization of the optic nerve head and macula, the classification of laterality, and the field of view were also included to assist the quality assessment. Finally, we validated our module internally and externally by evaluating the area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, and quadratic weighted Kappa.ResultsThe "Location" subcategory achieved area under the receiver operating characteristic curves of 0.991, 0.920, and 0.946 for the three grades, respectively. The "Clarity" subcategory achieved area under the receiver operating characteristic curves of 0.980, 0.917, and 0.954 for the three grades, respectively. The "Artifact" subcategory achieved area under the receiver operating characteristic curves of 0.976, 0.952, and 0.986 for the three grades, respectively. The accuracy and Kappa of overall quality reach 88.15% and 89.70%, respectively, on the internal set. These two indicators on the external set were 86.63% and 88.55%, respectively, which were very close to that of the internal set.ConclusionsThis work showed that our deep module was able to evaluate the color fundus photography image quality using more detailed three subcategories with three grade criteria. The promising results on both internal and external validation indicated the strength and generalizability of our module.

Project description:ImportanceUntil now, other than complex neurologic tests, there have been no readily accessible and reliable indicators of neurologic dysfunction among patients with Parkinson disease (PD). This study was conducted to determine the role of fundus photography as a noninvasive and readily available tool for assessing neurologic dysfunction among patients with PD using deep learning methods.ObjectiveTo develop an algorithm that can predict Hoehn and Yahr (H-Y) scale and Unified Parkinson's Disease Rating Scale part III (UPDRS-III) score using fundus photography among patients with PD.Design, settings, and participantsThis was a prospective decision analytical model conducted at a single tertiary-care hospital. The fundus photographs of participants with PD and participants with non-PD atypical motor abnormalities who visited the neurology department of Kangbuk Samsung Hospital from October 7, 2020, to April 30, 2021, were analyzed in this study. A convolutional neural network was developed to predict both the H-Y scale and UPDRS-III score based on fundus photography findings and participants' demographic characteristics.Main outcomes and measuresThe area under the receiver operating characteristic curve (AUROC) was calculated for sensitivity and specificity analyses for both the internal and external validation data sets.ResultsA total of 615 participants were included in the study: 266 had PD (43.3%; mean [SD] age, 70.8 [8.3] years; 134 male individuals [50.4%]), and 349 had non-PD atypical motor abnormalities (56.7%; mean [SD] age, 70.7 [7.9] years; 236 female individuals [67.6%]). For the internal validation data set, the sensitivity was 83.23% (95% CI, 82.07%-84.38%) and 82.61% (95% CI, 81.38%-83.83%) for the H-Y scale and UPDRS-III score, respectively. The specificity was 66.81% (95% CI, 64.97%-68.65%) and 65.75% (95% CI, 62.56%-68.94%) for the H-Y scale and UPDRS-III score, respectively. For the external validation data set, the sensitivity and specificity were 70.73% (95% CI, 66.30%-75.16%) and 66.66% (95% CI, 50.76%-82.25%), respectively. Lastly, the calculated AUROC and accuracy were 0.67 (95% CI, 0.55-0.79) and 70.45% (95% CI, 66.85%-74.04%), respectively.Conclusions and relevanceThis decision analytical model reveals amalgamative insights into the neurologic dysfunction among PD patients by providing information on how to apply a deep learning method to evaluate the association between the retina and brain. Study data may help clarify recent research findings regarding dopamine pathologic cascades between the retina and brain among patients with PD; however, further research is needed to expand the clinical implication of this algorithm.

Dataset Information

Quantitative Assessment of Fundus Tessellated Density in Highly Myopic Glaucoma Using Deep Learning.

Purpose

Methods

Results

Conclusions

Translational relevance

Publications

Quantitative Assessment of Fundus Tessellated Density in Highly Myopic Glaucoma Using Deep Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets