A retrospective study assessing the factors associated with visual outcome in retinal vein occlusion patients after anti-VEGF therapy

Radiomics Analysis Based on Optical Coherence Tomography to Prognose the Efficacy of Anti-VEGF Therapy of Retinal Vein Occlusion-Related Macular Edema

Purpose

Anti-vascular endothelial growth factor (anti-VEGF) agents are the first-line treatment for retinal vein occlusion-related macular edema (RVO-ME). However, the availability of reliable radiomic markers for evaluating the effectiveness of these agents is currently limited. The aim of this study was to develop machine learning approaches to evaluate the post-therapeutic effect of anti-VEGF treatment based on optical coherence tomography (OCT) images.

Methods

A total of 152 patients diagnosed with RVO-ME who received at least one intravitreal injection of anti-VEGF were included in this study, as well as 81 patients as the external validation set. Pre-therapeutic B-scans of spectral-domain OCT images were collected and segmented using the Pyradiomics module within the 3D Slicer software platform. Radiomic features were extracted from the segmented images. We trained the logistic regression model and machine learning models using the selected features, and evaluated the performance of the three classifier models.

Results

In the back propagation neural network (BPNN) model, the area under the curve (AUC) of the training, test, and external validation sets were 0.977, 0.912, and 0.804, respectively. In the support vector machine (SVM) model, the AUC of the 3 sets were 0.916, 0.882, and 0.802. The OCT-omics scores indicated a high overall net benefit, as determined by decision curve analysis.

Conclusions

The machine learning models based on OCT technology developed here demonstrated a promising ability to prognose anti-VEGF therapeutic responses for RVO-ME. The utilization of machine learning provides a new promising approach to assessing radiomic markers in research related to RVO-ME, having a good prospect for the application of the using of precision medicine in ophthalmology.

Prognosis and factors related to anti-VEGF therapy in patients with retinal vein occlusion and concomitant carotid artery disease

To evaluate the prognosis and influencing factors of retinal vein occlusion (RVO) in patients with concomitant carotid artery disease receiving anti-vascular endothelial growth factor (VEGF) treatment. Patients diagnosed with RVO and receiving anti-VEGF treatment were included. Eye and clinical data were collected. The patients were divided into a group with concomitant carotid artery disease (Group A) and a group without concomitant carotid artery disease (Group B). The risk factors affecting the visual prognosis of RVO patients with concomitant carotid artery disease were analyzed. Among 177 eligible patients with RVO, 101 had concomitant carotid artery disease (Group A), while 76 did not (Group B). Group A had a significantly lower treatment effectiveness rate than Group B (P < 0.001). The age and platelet distribution width of Group A were significantly higher than Group B (P < 0.001). Multivariate logistic regression analysis showed that baseline best-corrected visual acuity (BCVA), disorganization of retinal inner layers (DRIL), external limiting membrane (ELM) disruption, and red blood cell distribution width (RDW) were significantly associated with the posttreatment visual prognosis of RVO patients with concomitant carotid artery disease(P < 0.05). RVO patients with concomitant carotid artery disease had a significantly lower treatment effectiveness rate than RVO patients without carotid artery disease. The poor baseline BCVA, DRIL, ELM disruption, and a greater RDW are risk factors for low anti-VEGF treatment efficacy among RVO patients with concomitant carotid artery disease.

Widefield, Swept-Source Optical Coherence Tomography Angiography Metrics as Predictors of Anti-VEGF Treatment in Retinal Vein Occlusions

BACKGROUND AND OBJECTIVE

Our objective was to assess baseline widefield swept-source optical coherence tomography angiography (WF SSOCTA) microvascular metrics as predictors for the number of anti-vascular endothelial growth factor (VEGF) injections and visual acuity (VA) at 12-months follow-up in patients with retinal vein occlusion (RVO).

PATIENTS AND METHODS

This was a prospective study including 49 RVO eyes from 49 patients who had not received an anti-VEGF injection for at least 3 months prior to imaging. Microvascular metrics from 6×6-mm and 12×12-mm angiograms were assessed using linear regression models, adjusting for age.

RESULTS

Reductions in the vessel density (VD) and vessel skeletonized density (VSD) vascular metrics were associated both with a higher number of anti-VEGF injections at all follow-up time points and reduced VA 12 months after imaging in all RVO eyes.

CONCLUSIONS

WF SS-OCTA VD and VSD micro-vascular metrics at baseline can prognosticate VA and number of anti-VEGF injections required at 3, 6, and 12 months in RVO eyes. [Ophthalmic Surg Lasers Imaging Retina 2024;55:374-382.].

Multimodal deep transfer learning to predict retinal vein occlusion macular edema recurrence after anti-VEGF therapy

Purpose

To develop a multimodal deep transfer learning (DTL) fusion model using optical coherence tomography angiography (OCTA) images to predict the recurrence of retinal vein occlusion (RVO) and macular edema (ME) after three consecutive anti-VEGF therapies.

Methods

This retrospective cross-sectional study consisted of 2800 B-scan OCTA macular images collected from 140 patients with RVO-ME. The central macular thickness (CMT) > 250 μm was used as a criterion for recurrence in the three-month follow-up after three injections of anti-VEGF therapy. The qualified OCTA image preprocessing and the lesion area segmentation were performed by senior ophthalmologists. We developed and validated the clinical, DTL, and multimodal fusion models based on clinical and extracted OCTA imaging features. The performance of the models and experts predictions were evaluated using several performance metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

Results

The DTL models exhibited higher prediction efficacy than the clinical models and experts' predictions. Among the DTL models, the Vgg19 performed better than that of the other models, with an AUC of 0.968 (95 % CI, 0.943-0.994), accuracy of 0.913, sensitivity of 0.922, and specificity of 0.902 in the validation cohort. Moreover, the fusion Vgg19 model showed the highest prediction efficacy among all the models, with an AUC of 0.972 (95 % CI, 0.946-0.997), accuracy of 0.935, sensitivity of 0.935, and specificity of 0.934 in the validation cohort.

Conclusions

Multimodal fusion DTL models showed robust performance in predicting RVO-ME recurrence and may be applied to assist clinicians in determining patients' follow-up time after anti-VEGF therapy.