Abstract

Objective: Diabetic macular edema (DME) and retinal vein occlusion (RVO) are the leading causes of visual impairments across the world. Vascular endothelial growth factor (VEGF) stimulates breakdown of blood-retinal barrier that causes accumulation of fluid within macula. Anti-VEGF therapy is the first-line treatment for both the diseases; however, the degree of response varies for individual patients. The main objective of this work was to identify the (i) texture-based radiomics features within individual fluid and retinal tissue compartments of baseline spectral-domain optical coherence tomography (SD-OCT) images and (ii) the specific spatial compartments that contribute most pertinent features for predicting therapeutic response. Methods: A total of 962 texture-based radiomics features were extracted from each of the fluid and retinal tissue compartments of OCT images, obtained from the PERMEATE study. Top-performing features selected from the consensus of different feature selection methods were evaluated in conjunction with four different machine learning classifiers: Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Random Forest (RF), and Support Vector Machine (SVM) in a cross-validated approach to distinguish eyes tolerating extended interval dosing (non-rebounders) and those requiring more frequent dosing (rebounders). Results: Combination of fluid and retinal tissue features yielded a cross-validated area under receiver operating characteristic curve (AUC) of 0.78±0.08 in distinguishing rebounders from non-rebounders. Conclusions: This study revealed that the texture-based radiomics features pertaining to IRF subcompartment were most discriminating between rebounders and non-rebounders to anti-VEGF therapy. Clinical Impact: With further validation, OCT-based imaging biomarkers could be used for treatment management of DME patients.

Highlights

  • DIABETIC retinopathy (DR) is a progressive, chronic microvascular disorder that may be accompanied with vision-threatening complications, such as diabetic macular edema (DME)

  • The main objective of this work was to evaluate (i) the role of the texture-based radiomics features to capture the morphological characteristics of the anatomic subcompartments visualized with spectral-domain optical coherence tomography (SD-Optical Coherence Tomography (OCT)) to predict response to anti-Vascular endothelial growth factor (VEGF) therapy and (ii) the relative importance of the radiomic features extracted from the different fluid [e.g., Intraretinal Fluid (IRF) and Subretinal Fluid (SRF)] and the retinal tissue compartments [e.g., Inner Limiting Membrane (ILM) to Retinal Pigment Epithelium (RPE), Ellipsoid Zone (EZ) to RPE, Internal Limiting Membrane (ILM) to EZ] for therapeutic response assessment

  • We found that the significant textural differences that exist within the retinal fluid subcompartments (IRF and subretinal fluid (SRF)) between the rebounders and the non-rebounders are well captured by the texture-based radiomics descriptors

Read more

Summary

Introduction

DIABETIC retinopathy (DR) is a progressive, chronic microvascular disorder that may be accompanied with vision-threatening complications, such as diabetic macular edema (DME). The excessive retinal vascular permeability caused by the damage to the blood-retinal barrier leads to retinal fluid accumulation within the macular region [1], [2]. Retinal vein occlusion (RVO) occurs typically due to intravascular thrombosis and may result in macular edema secondary to increased vascular permeability. Vascular endothelial growth factor (VEGF) has been recognized as a critical cytokine that induces retinal vascular hyperpermeability in both DME and RVO [3] by. Stimulating the breakdown of the intercellular junction of the blood-retinal barrier. This in turn causes the accumulation of intraretinal fluid (IRF) and/or subretinal fluid (SRF) within the retina. Elevated VEGF levels in eyes with RVO and DME may exacerbate microangiopathy and ischemia [4]

Objectives
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call