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

Purpose: 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).

Methods: 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.

Results: 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.

Conclusion: 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.