Developing advanced medical imaging retrieval systems is challenging due to the varying definitions of `similar images' across different medical contexts. This challenge is compounded by the lack of large-scale, high-quality medical imaging retrieval datasets and benchmarks. In this paper, we propose a novel methodology that leverages dense radiology reports to define image-wise similarity ordering at multiple granularities in a scalable and fully automatic manner. Using this approach, we construct two comprehensive medical imaging retrieval datasets: MIMIC-IR for Chest X-rays and CTRATE-IR for CT scans, providing detailed image-image ranking annotations conditioned on diverse anatomical structures. Furthermore, we develop two retrieval systems, RadIR-CXR and model-ChestCT, which demonstrate superior performance in traditional image-image and image-report retrieval tasks. These systems also enable flexible, effective image retrieval conditioned on specific anatomical structures described in text, achieving state-of-the-art results on 77 out of 78 metrics.
@article{arxiv.2503.04653,
title = {RadIR: A Scalable Framework for Multi-Grained Medical Image Retrieval via Radiology Report Mining},
author = {Tengfei Zhang and Ziheng Zhao and Chaoyi Wu and Xiao Zhou and Ya Zhang and Yanfeng Wang and Weidi Xie},
journal= {arXiv preprint arXiv:2503.04653},
year = {2025}
}