Elastic deformation of optical coherence tomography images of diabetic macular edema for deep-learning models training: how far to go?

This work addresses the problem of limited training data for medical imaging models in ophthalmology, specifically for diabetic patients, and is incremental as it builds on existing data augmentation techniques.

The study investigated the clinical validity of using elastic deformation for data augmentation in OCT images to train deep-learning models for detecting diabetic macular edema, finding that this approach can enhance model training but with limitations on how far it can be effectively applied.