Fig. 1: EVA-X Framework.
From: EVA-X: a foundation model for general chest x-ray analysis with self-supervised learning
a Pre-training Dataset: EVA-X pre-training collects and leverages a diverse set of X-ray images encompassing various health conditions.3,4,5b EVA-X Pre-training: EVA-X employs a novel self-supervised pre-training approach that synergistically integrates the strengths of contrastive learning14,15,16,17,18 and mask image modeling19,20. c General Visual Representations: EVA-X exhibits a high degree of transferability, enhancing the comprehensive analysis of X-ray imagery. d Transfer Performance: EVA-X demonstrates state-of-the-art performance across 11 distinct tasks3,4,9,10,11,12,13, outperforming established benchmarks set by previous pre-trained models. (Some icons in the figure sourced from biorender.com).
