L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction

arXiv:2403.16272v1 Announce Type: new
Abstract: Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of typical SSL is not straightforward in medical imaging. Additionally, those pretext tasks often lack context, which is critical for computer-aided clinical decision support. In this paper, we developed a longitudinal masked auto-encoder (MAE) based on the well-known Transformer-based MAE. In particular, …

abstract application arxiv auto computer computer vision cs.ai cs.cv encoder encoding images medical natural prediction pre-training self-supervised learning ssl strategies supervised learning tasks training type vision