Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add more filters










Database
Language
Publication year range
1.
Transl Vis Sci Technol ; 13(5): 23, 2024 May 01.
Article in English | MEDLINE | ID: mdl-38809531

ABSTRACT

Purpose: To develop convolutional neural network (CNN)-based models for predicting the axial length (AL) using color fundus photography (CFP) and explore associated clinical and structural characteristics. Methods: This study enrolled 1105 fundus images from 467 participants with ALs ranging from 19.91 to 32.59 mm, obtained at National Taiwan University Hospital between 2020 and 2021. The AL measurements obtained from a scanning laser interferometer served as the gold standard. The accuracy of prediction was compared among CNN-based models with different inputs, including CFP, age, and/or sex. Heatmaps were interpreted by integrated gradients. Results: Using age, sex, and CFP as input, the mean ± standard deviation absolute error (MAE) for AL prediction by the model was 0.771 ± 0.128 mm, outperforming models that used age and sex alone (1.263 ± 0.115 mm; P < 0.001) and CFP alone (0.831 ± 0.216 mm; P = 0.016) by 39.0% and 7.31%, respectively. The removal of relatively poor-quality CFPs resulted in a slight MAE reduction to 0.759 ± 0.120 mm without statistical significance (P = 0.24). The inclusion of age and CFP improved prediction accuracy by 5.59% (P = 0.043), while adding sex had no significant improvement (P = 0.41). The optic disc and temporal peripapillary area were highlighted as the focused areas on the heatmaps. Conclusions: Deep learning-based prediction of AL using CFP was fairly accurate and enhanced by age inclusion. The optic disc and temporal peripapillary area may contain crucial structural information for AL prediction in CFP. Translational Relevance: This study might aid AL assessments and the understanding of the morphologic characteristics of the fundus related to AL.


Subject(s)
Axial Length, Eye , Neural Networks, Computer , Photography , Humans , Male , Female , Middle Aged , Adult , Photography/methods , Aged , Axial Length, Eye/diagnostic imaging , Fundus Oculi , Young Adult , Aged, 80 and over
2.
J Clin Med ; 10(24)2021 Dec 13.
Article in English | MEDLINE | ID: mdl-34945121

ABSTRACT

The purpose of this article is to investigate the diagnostic value of Pulsar perimetry (PP), optical coherence tomography (OCT), and optical coherence tomography angiography (OCTA) in pre-perimetric glaucoma (PPG) and perimetric glaucoma (PG). This retrospective cross-sectional study included 202 eyes (145 eyes in the control group, 40 eyes in the PPG group, and 17 eyes in the PG group) from 105 subjects. The results were analyzed by paired t-tests and Wilcoxon signed-rank test. The area under the curve (AUC), sensitivity, and specificity were used to evaluate the diagnostic accuracy. Pearson correlation was used to investigate the relationships of each parameter. The most sensitive parameters for differentiating the control group from the PPG group by using Pulsar, OCT, and OCTA were square loss variance of PP (AUC = 0.673, p < 0.001), superior ganglion cell complex thickness (AUC = 0.860, p < 0.001), and superior-hemi retina thickness (AUC = 0.817, p < 0.001). In the PG group, the most sensitive parameters were mean defect of PP (AUC = 0.885, p < 0.001), whole image of ganglion cell complex thickness (AUC = 0.847, p < 0.001), and perifoveal retina thickness (AUC = 0.833, p < 0.001). The mean defect of PP was significantly correlated with vascular parameters (radial peripapillary capillary (RPC), p = 0.008; vessel density of macular superficial vascular complex (VDms), p = 0.001; vessel density of macular deep vascular complex (VDmd), p = 0.002). In conclusion, structural measurements using OCT were more sensitive than vascular measurements of OCTA and functional measurements of PP for PPG, while PP was more sensitive than the structural and vascular measurements for PG. The mean defect of PP was also shown to be highly correlated with the reduction of vessel density.

SELECTION OF CITATIONS
SEARCH DETAIL