MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification
This provides a benchmark for researchers in medical AI to test foundation model adaptation, but it is incremental as it focuses on dataset creation rather than novel methods.
The authors tackled the shortage of public data and benchmarks for adapting foundation models in medical image classification by introducing MedFMC, a dataset with 22,349 images across five real-world clinical tasks, and demonstrated baseline method results for evaluation.
Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications. Recent advances further enable adapting foundation models in downstream tasks efficiently using only a few training samples, e.g., in-context learning. Yet, the application of such learning paradigms in medical image analysis remains scarce due to the shortage of publicly accessible data and benchmarks. In this paper, 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 lesion 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.