Bilateral deformable attention transformer for screening of high myopia using optical coherence tomography

Abstract

Myopia is a visual impairment caused by excessive refractive power of the cornea or lens or elongation of the eyeball. Due to the various classification criteria associated with high myopia, such as spherical equivalent (SE) and axial length (AL), existing methods primarily rely on individual classification criteria for model design. In this paper, to comprehensively utilize multiple indicators, we design a multi-label classification model for high myopia. Moreover, image data play a pivotal role in studying high myopia and pathological myopia. Notable features of high myopia, including increased retinal curvature, choroidal thinning, and scleral shadowing, are observable in Optical Coherence Tomography (OCT) images of the retina. We propose a model named Bilateral Deformable Attention Transformer (BDA-Tran) for multi-label screening of high myopia in OCT data. Based on the vision transformer, we introduce a bilateral deformable attention mechanism (BDA) where the queries in self-attention are composed of both the global queries and the data-dependent queries from the left and right sides. This flexible approach allows attention to focus on relevant regions and capture more myopia-related information features, thereby concentrating attention primarily on regions related to the choroid and sclera, among other areas associated with high myopia. BDA-Tran is trained and tested on OCT images of 243 patients, achieving the accuracies of 83.1 % and 87.7 % for SE and AL, respectively. Furthermore, we visualize attention maps to provide transparent and interpretable judgments. Experimental results demonstrate that BDA-Tran outperforms existing methods in terms of effectiveness and reliability under the same experimental conditions.