Spatial Arrangement of Leakage Patterns in Diabetic Macular Edema is Associated with Tolerance of Aibercept Treatment Interval Length: Preliminary Findings

摘要

Diabetic macular edema (DME) is a leading cause of vision loss in diabetic patients. The underlying cause forthe onset of DME is the degradation of the blood-retinal barrier, whose primary function is maintaining theextracellular uid at an optimal range. Vascular endothelial growth factor (VEGF) has proven to be a catalystin altering the permeability of the blood-retinal barrier, thereby initiating a cascade of events that ultimatelyresults in a loss of visual acuity. The primary imaging techniques to recognize and diagnose DME are uoresceinangiography (FA) and spectral-domain optical coherence tomography (SD-OCT). Taking a multimodal approachof FA in combination with SD-OCT provides images of vasculature and other eye structures to help better identifykey features such as level, location, and amount of leakage. First-line treatments for DME have now evolved tousing anti-VEGF to inhibit the effects VEGF has on increasing the permeability of the blood-retinal barrier.Because VEGF also increases the chance of leakage, we can also expect anti-VEGF treatments to decrease theamount of leakage DME patients suffer from. Anti-VEGF treatments also have a peripheral effect of modifyingthe disease burden and allowing for extended time in between treatments. Although current conventionaltreatment parameters exist to determine the e cacy of such VEGF treatments, many of these markers rely onclinicians to make a judgment call based on a minor qualitative difference of retinal scans or involve clinicianstaking a uid assessment, an option deemed too invasive to demand from all patients. In this work, we seek to nd new imaging features that derive from a sub-visual feature analysis, and ideally provide a prognostic metricfor clinicians to help streamline the diagnostic process. The rationale for these new biomarkers derives fromleakage properties and their activity in the retina once edema develops. A decrease in leakage within certainstructures in the eye would also lead to a change in the densities of leakage patterns, correlating with betterclinical outcomes.In this work, we use morphological and graph-based attributes to model the global properties and spatialdistribution of leakage areas on baseline FA scans of patients subsequently treated with intravitreal anti-VEGFtherapy (i.e. aibercept). The features were then used in conjunction with a classifier to distinguish betweeneyes tolerating extended dosing intervals (N=15) and those eyes requiring more frequent dosing (N=12), basedon initial response following treatment interval extension. The cross-validated area under the receiver operatingcharacteristic curve (AUC) was found to be 0.74 0.11% using the computed imaging attributes. Edge lengthdisorder of minimum spanning tree showed a statistically significant difference (p=0.007) between the two groups.Clinical parameters such as central subfield thickness and macular volume were not statistically significantlydifferent. Our results indicate that there may be differences in spatial distribution of leakage areas between eyesthat will exhibit favorable response to extended interval aibercept dosing and eyes that require more frequentdosing.