Optic disc morphology in unilateral branch retinal vein occlusion using spectral domain optical coherence tomography

Artificial intelligence to distinguish retinal vein occlusion patients using color fundus photographs

PURPOSE

Our aim is to establish an AI model for distinguishing color fundus photographs (CFP) of RVO patients from normal individuals.

METHODS

The training dataset included 2013 CFP from fellow eyes of RVO patients and 8536 age- and gender-matched normal CFP. Model performance was assessed in two independent testing datasets. We evaluated the performance of the AI model using the area under the receiver operating characteristic curve (AUC), accuracy, precision, specificity, sensitivity, and confusion matrices. We further explained the probable clinical relevance of the AI by extracting and comparing features of the retinal images.

RESULTS

Our model achieved an average AUC was 0.9866 (95% CI: 0.9805-0.9918), accuracy was 0.9534 (95% CI: 0.9421-0.9639), precision was 0.9123 (95% CI: 0.8784-9453), specificity was 0.9810 (95% CI: 0.9729-0.9884), and sensitivity was 0.8367 (95% CI: 0.7953-0.8756) for identifying fundus images of RVO patients in training dataset. In independent external datasets 1, the AUC of the RVO group was 0.8102 (95% CI: 0.7979-0.8226), the accuracy of 0.7752 (95% CI: 0.7633-0.7875), the precision of 0.7041 (95% CI: 0.6873-0.7211), specificity of 0.6499 (95% CI: 0.6305-0.6679) and sensitivity of 0.9124 (95% CI: 0.9004-0.9241) for RVO group. There were significant differences in retinal arteriovenous ratio, optic cup to optic disc ratio, and optic disc tilt angle (p = 0.001, p = 0.0001, and p = 0.0001, respectively) between the two groups in training dataset.

CONCLUSION

We trained an AI model to classify color fundus photographs of RVO patients with stable performance both in internal and external datasets. This may be of great importance for risk prediction in patients with retinal venous occlusion.

Retinal vein occlusions associated or complicated with glaucoma. Aspects of prediction and paths of progression

Background and Objectives: The aim of the study is to evaluate prediction factors and progression paths when retinal vein occlusions are associated with preexisting glaucoma or complicated with neovascular glaucoma. Materials and Methods: The study included 111 patients diagnosed with retinal vein occlusions, of whom 21 with preexisting open angle glaucoma and 12 with neovascular glaucoma as complication. The study was conducted from September 2020 to September 2022 in Timişoara, Romania. We assessed intraocular pressure, cup-disc ratio and retinal nerve fiber layer from the moment of retinal vein occlusion diagnosis until at least one year of follow-up, considering these aspects as values of prediction concerning the paths of progression when glaucoma and retinal vein occlusions come together. Results: The mean initial IOP for the affected eyes was higher (15.89 ± 2.73) than for fellow eyes (15.20 ± 3.11), with an increase of the IOP after one year, but with no statistically significant differences for the affected eyes (p=0.116) or for the other eyes (p=0.684), neither for the affected eyes associated with glaucoma in comparison with affected eyes without glaucoma association. The mean cup-disc ratio was higher for the affected eyes in comparison with the fellow eyes (0.4812 ± 0.219 for the affected eyes and 0.4738 ± 0.229 for the fellow ones in cases without associated glaucoma and 0.681 ± 0.157 for the affected eyes and 0.600 ± 0.241 for the fellow eyes in cases with associated glaucoma), with statistical significant differences in the evolution for both groups in comparison with the unaffected eyes (p=0.0056 for the first group and p=0.0003 for the second group). Comparing the evolution of the affected eyes with the preexisting glaucoma and the affected eyes without preexisting glaucoma, no statistical difference has been found (p=0.1104). The mean retinal nerve fiber layer decreased significantly in affected eyes without glaucoma (from 96 ± 14.71 to 89.16 ± 13.07) and in affected eyes with associated glaucoma (from 78.50 ± 4.23 to 75.50 ± 5.83), but with no significant differences (p=0.182). The level of decreasing was significantly more consistent in association with a venous occlusion (p= 0.0001). Conclusions: The findings of the current study fortify the correlation between glaucoma as a risk factor for retinal venous occlusion development, the intraocular pressure and optic nerve cupping as prediction factors in retinal venous occlusions, the association of a well-controlled preexisting glaucoma with no effect on the progression of the retinal venous occlusions and the development of a neovascular glaucoma with a much aggressive and different path of disease progression.

New Developments in the Classification, Pathogenesis, Risk Factors, Natural History, and Treatment of Branch Retinal Vein Occlusion

For years, branch retinal vein occlusion is still a controversial disease in many aspects. An increasing amount of data is available regarding classification, pathogenesis, risk factors, natural history, and therapy of branch retinal vein occlusion. Some of the conclusions may even change our impression of branch retinal vein occlusion. It will be beneficial for our doctors to get a deeper understanding of this disease and improve the treatment skills. The aims of this review is to collect the information above and report new ideas especially from the past a few years.