MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification

MedFMC is a Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification. We aim at approaches adapting the foundation models for medical image classification and present a novel dataset and benchmark for the evaluation, i.e., examining the overall performance of accommodating the large-scale foundation models downstream on a set of diverse real-world clinical tasks. We collect five sets of medical imaging data from multiple institutes targeting a variety of real-world clinical tasks (22,349 images in total), i.e., thoracic diseases screening in X-rays, pathological tumor tissue screening, lesion detection in endoscopy images, neonatal jaundice evaluation, and diabetic retinopathy grading. Results of multiple baseline methods are demonstrated using the proposed dataset from both accuracy and cost-effective perspectives. We aim at examining the overall performance of accommodating large-scale foundation models downstream on a set of diverse real-world clinical tasks.