Efficient Visual Field Sensitivity Estimation via a Lightweight Global Context-Aware CNN Using Standard 2D OCT Thickness Maps

Glaucoma is a chronic progressive optic neuropathy causing irreversible blindness globally, underscoring the need for reliable diagnostic tools. While visual field (VF) testing remains the clinical standard, it has significant limitations, including subjective variability and patient cooperation difficulties. Optical coherence tomography (OCT) offers objective structural assessment. Recent deep learning approaches for VF prediction from OCT data can achieve high accuracy, but require raw three-dimensional volumetric data and substantial computational infrastructure that limit their deployment in routine clinical practice. We developed a lightweight convolutional neural network that predicts VF sensitivity from standard two-dimensional OCT thickness maps routinely available in clinical settings. The architecture integrates multiscale depthwise separable convolutions with attention mechanisms and employs an Exponentially Weighted Mean Squared Error loss function to enhance accuracy in clinically critical low-sensitivity regions. Using data from 241 subjects with five-fold cross-validation, our model achieved mean absolute error of 3.32 ± 2.35 dB and correlation of 0.74. This approach addresses the practical deployment limitations of existing methods while maintaining competitive accuracy, enabling implementation in resource-constrained clinical settings for patients who cannot reliably perform standard perimetry.