Myopic Vascular Changes Revealed by Optical Tomography Angiography and Their Association with Myopic Fundus Manifestations

DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification

Fundus tessellation (FT) is a prevalent clinical feature associated with myopia and has implications in the development of myopic maculopathy, which causes irreversible visual impairment. Accurate classification of FT in color fundus photo can help predict the disease progression and prognosis. However, the lack of precise detection and classification tools has created an unmet medical need, underscoring the importance of exploring the clinical utility of FT. Thus, to address this gap, we introduce an automatic FT grading system (called DeepGraFT) using classification-and-segmentation co-decision models by deep learning. ConvNeXt, utilizing transfer learning from pretrained ImageNet weights, was employed for the classification algorithm, aligning with a region of interest based on the ETDRS grading system to boost performance. A segmentation model was developed to detect FT exits, complementing the classification for improved grading accuracy. The training set of DeepGraFT was from our in-house cohort (MAGIC), and the validation sets consisted of the rest part of in-house cohort and an independent public cohort (UK Biobank). DeepGraFT demonstrated a high performance in the training stage and achieved an impressive accuracy in validation phase (in-house cohort: 86.85 %; public cohort: 81.50 %). Furthermore, our findings demonstrated that DeepGraFT surpasses machine learning-based classification models in FT classification, achieving a 5.57 % increase in accuracy. Ablation analysis revealed that the introduced modules significantly enhanced classification effectiveness and elevated accuracy from 79.85 % to 86.85 %. Further analysis using the results provided by DeepGraFT unveiled a significant negative association between FT and spherical equivalent (SE) in the UK Biobank cohort. In conclusion, DeepGraFT accentuates potential benefits of the deep learning model in automating the grading of FT and allows for potential utility as a clinical-decision support tool for predicting progression of pathological myopia.

Comparison of choroidal structural changes between term and preterm children with and without retinopathy of prematurity

PURPOSE

To evaluate the effects of prematurity and retinopathy of prematurity (ROP) treatment on choroidal structure using the image binarization method and compare with term children.

METHODS

Children aged 6-11 years were included in this prospective case-control study. There were 36 (72 eyes) term children and 52 (103 eyes) preterm children included in the study. Subfoveal choroidal thickness (SFCT) and choroidal thickness (CT) at 500, 1500, and 2500 μm temporal and nasal from the fovea were measured. Images were binarized using the Image J program. The choroidal vascularity index (CVI) was calculated by dividing the luminal area by the total subfoveal choroidal area.

RESULTS

There was no significant difference in SCFT between children born at term (290.44±57.617 μm) and preterm (288±69.270 μm) (p = 0.800). CVI was found to be significantly higher in term children (71.90±2.60 %) than in preterm children (69.58±2.72 %) (p<0.001), and the difference was also significant when compared to preterm children without ROP (p = 0.033). In the preterm subgroups, although CVI was higher in preterm children without ROP (70.42±2.24 %) than in those with spontaneous regression (69.34±3.30 %) and those treated with laser photocoagulation (68.91±2.35 %), there was no significant difference (p = 0.330, p = 0.089 respectively). CVI was similar between children with spontaneous regression and those treated with laser photocoagulation (p = 0.909). CVI and logMAR best corrected visual acuity (BCVA) were inversely correlated (r=-0.295 p<0.001).

CONCLUSION

Reduced CVI in preterm children indicates that prematurity is related to the choroid. Choroidal vascularity index appears to be a more reliable marker than CT for evaluating the relationship between choroid and ROP.