Confounder-Aware Medical Data Selection for Fine-Tuning Pretrained Vision Models
This addresses the problem of efficient medical data curation for researchers and practitioners, though it appears incremental as an enhancement to existing data selection methods.
The paper tackles the challenge of selecting appropriate medical data for fine-tuning pretrained vision models by developing a confounder-aware approach that identifies and mitigates confounding variables while preserving dataset distribution. The method demonstrates effectiveness across diverse medical imaging modalities compared to other data selection approaches.
The emergence of large-scale pre-trained vision foundation models has greatly advanced the medical imaging field through the pre-training and fine-tuning paradigm. However, selecting appropriate medical data for downstream fine-tuning remains a significant challenge considering its annotation cost, privacy concerns, and the detrimental effects of confounding variables. In this work, we present a confounder-aware medical data selection approach for medical dataset curation aiming to select minimal representative data by strategically mitigating the undesirable impact of confounding variables while preserving the natural distribution of the dataset. Our approach first identifies confounding variables within data and then develops a distance-based data selection strategy for confounder-aware sampling with a constrained budget in the data size. We validate the superiority of our approach through extensive experiments across diverse medical imaging modalities, highlighting its effectiveness in addressing the substantial impact of confounding variables and enhancing the fine-tuning efficiency in the medical imaging domain, compared to other data selection approaches.