A Hybrid Transformers-based Convolutional Neural Network Model for Keratoconus Detection in Scheimpflug-based Dynamic Corneal Deformation Videos

To assess the performance of a hybrid Transformer-based convolutional neural network (CNN) model for automated detection of keratoconus in stand-alone Scheimpflug-based dynamic corneal deformation videos (DCDVs). We used transfer learning for feature extraction from DCDVs. These feature maps were augmented by self-attention to model long-range dependencies before classification to identify keratoconus directly. Model performance was evaluated by objective accuracy metrics based on DCDVs from two independent cohorts with 275 and 546 subjects. The model's sensitivity and specificity in detecting keratoconus were 93% and 84%, respectively. The AUC of the keratoconus probability score based on the external validation database was 0.97. The hybrid Transformer-based model was highly sensitive and specific in discriminating normal from keratoconic eyes using DCDV(s) at levels that may prove useful in clinical practice.