A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling

TL;DR

CheXficient is an efficient chest X-ray foundation model pretrained on a small, curated subset of data, achieving high performance while reducing computational costs and improving generalization to rare conditions.

Contribution

We introduce CheXficient, a data-efficient pretraining approach that selectively prioritizes informative samples, reducing data and compute requirements without sacrificing performance.

Findings

Pretrained on 22.7% of data, CheXficient matches or exceeds full-data models.

Selective sampling improves generalization to rare and under-represented conditions.

Achieves comparable performance across 20 benchmarks with less compute.

Abstract

Foundation models for medical imaging are typically pretrained on increasingly large datasets, following a "scale-at-all-costs" paradigm. However, this strategy faces two critical challenges: large-scale medical datasets often contain substantial redundancy and severe class imbalance that bias representation learning toward over-represented patterns, and indiscriminate training regardless of heterogeneity in data quality incurs considerable computational inefficiency. Here we demonstrate that active, principled data curation during pretraining can serve as a viable, cost-effective alternative to brute-force dataset enlargement. We introduce CheXficient, a chest X-ray (CXR) foundation model that selectively prioritizes informative training samples. CheXficient is pretrained on only 22.7% of 1,235,004 paired CXR images and reports while consuming under 27.3% of the total compute budget, yet achieving comparable or superior performance to its full-data counterpart and other large-scale pretrained models. We assess CheXficient across 20 individual benchmarks spanning 5 task types, including non-adapted off-the-shelf evaluations (zero-shot findings classification and crossmodal retrieval) and adapted downstream tasks (disease prediction, semantic segmentation, and radiology report generation). Further analyses show that CheXficient systematically prioritizes under-represented training samples, improving generalizability on long-tailed or rare conditions. Overall, our work offers practical insights into the data and computation demands for efficient pretraining and downstream adaptation of medical vision-language foundation models.