Training a high-performance retinal foundation model with half-the-data and 400 times less compute

arXiv:2405.00117v1 Announce Type: new
Abstract: Artificial Intelligence holds tremendous potential in medicine, but is traditionally limited by the lack of massive datasets to train models on. Foundation models, pre-trained models that can be adapted to downstream tasks with small datasets, could alleviate this problem. Researchers at Moorfields Eye Hospital (MEH) proposed RETFound-MEH, a foundation model for retinal imaging that was trained on 900,000 images, including private hospital data. Recently, data-efficient DERETFound was proposed that provides comparable performance while being trained …

abstract artificial artificial intelligence arxiv compute cs.ai cs.cv data datasets foundation foundation model intelligence massive medicine performance pre-trained models researchers small tasks train training type