Predicting treat-and-extend outcomes and treatment intervals in neovascular age-related macular degeneration from retinal optical coherence tomography using artificial intelligence

Abstract

PurposeTo predict visual outcomes and treatment needs in a treat & extend (T&E) regimen in neovascular age-related macular degeneration (nAMD) using a machine learning model based on quantitative optical coherence tomography (OCT) imaging biomarkers.Materials and methodsStudy eyes of 270 treatment-naïve subjects, randomized to receiving ranibizumab therapy in the T&E arm of a randomized clinical trial were considered. OCT volume scans were processed at baseline and at the first follow-up visit 4 weeks later. Automated image segmentation was performed, where intraretinal (IRF), subretinal (SRF) fluid, pigment epithelial detachment (PED), hyperreflective foci, and the photoreceptor layer were delineated using a convolutional neural network (CNN). A set of respective quantitative imaging biomarkers were computed across an Early Treatment Diabetic Retinopathy Study (ETDRS) grid to describe the retinal pathomorphology spatially and its change after the first injection. Lastly, using the computed set of OCT features and available clinical and demographic information, predictive models of outcomes and retreatment intervals were built using machine learning and their performance evaluated with a 10-fold cross-validation.ResultsData of 228 evaluable patients were included, as some had missing scans or were lost to follow-up. Of those patients, 55% reached and maintained long (8, 10, 12 weeks) and another 45% stayed at short (4, 6 weeks) treatment intervals. This provides further evidence for a high disease activity in a major proportion of patients. The model predicted the extendable treatment interval group with an AUROC of 0.71, and the visual outcome with an AUROC of up to 0.87 when utilizing both, clinical and imaging features. The volume of SRF and the volume of IRF, remaining at the first follow-up visit, were found to be the most important predictive markers for treatment intervals and visual outcomes, respectively, supporting the important role of quantitative fluid parameters on OCT.ConclusionThe proposed Artificial intelligence (AI) methodology was able to predict visual outcomes and retreatment intervals of a T&E regimen from a single injection. The result of this study is an urgently needed step toward AI-supported management of patients with active and progressive nAMD.

Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network

“…Our model was able to determine recurrence by analyzing four consecutive OCT images obtained during three loading injections. Previous studies predicted the treatment burden by learning from the pre-treatment OCT images and OCT images after one injection, and reported an improvement in the area under the curve (AUC) from 0.64 with pre-treatment OCT images alone to 0.69 when post-treatment OCT images were also utilized 15 . We confirmed that the prediction accuracy improved when OCT images obtained during the injection treatment process were additionally learned.…”

“…With the advancement of artificial intelligence (AI), numerous research findings have been reported on the diagnosis and treatment of retinal diseases. A model predicting whether the injection interval would be less than 5 weeks (high treatment burden) or more than 10 weeks (low treatment burden) when administering T&E using anti-VEGF agents for nAMD treatment has been reported 14 , 15 . Predicting the patients requiring immediate T&E treatment (owing to recurrence within 3 months after the three loading injections for nAMD), those with a longer T&E interval, and those considering PRN treatment after 3 months could aid in treatment planning.…”

AI-based support for optical coherence tomography in age-related macular degeneration

“…Despite the importance of all high-order biomarkers on disease classification and progression, [ 57 , 58 ] post hoc analysis from TREND study and from the Fight Retinal Blindness! dataset using DL and ML showed that retinal fluid is still the most important anatomical biomarker for predicting disease activity, treatment demand and visual outcomes in nAMD [ 59 , 60 ]. Indeed, recent analysis showed that not only the location of fluid is important for disease progression, however the dynamic fluctuation of each retinal fluid has a high impact on the outomes [ 61 ].…”

“…Higher IRF and PED were associated with worse visual outcomes, despite IRF being the fluid type with faster response to anti-VEGF therapy. SRF showed slower resolution, intuitively leading to an increased number of injections during the first year in a pro-re-nata regimen, however no significant correlation with worse functional outcomes was found presumably due to the predominant location of SRF outside of the central 1 mm of the fovea [ 59 , 60 , 62 ]. This highlights the notion that traditional treatment patterns have to undergo a reality check by a rigorous structure/function correlation.…”

Artificial intelligence-based prediction of diabetic retinopathy evolution (EviRed): protocol for a prospective cohort

“…More recently, AI has also been applied to the prediction of pathological evolution in patients. This includes predicting the need for antivascular endothelial growth factor treatment25 or outcomes26 using OCT; the conversion to wet age-related macular degeneration within 6 months using OCT27; the development of DR within 2 years using standard FP28 or the progression of DR severity by at least two ETDRS Diabetic Retinopathy Severity Scale steps within 1 year using FP 29. Prediction performance is promising in the latter DR-related applications, but there likely is room for improvement because input data used for prediction is limited to only one, and outdated, imaging modality.…”