BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval
This addresses the workload of medical professionals by providing a dataset and method for retrieving similar case studies, though it is incremental as it builds on existing text-image retrieval solutions.
The study tackled the lack of robust benchmarks in 3D medical text-image retrieval by introducing BIMCV-R, a dataset with 8,069 CT volumes and over 2 million slices paired with radiological reports, and developed MedFinder, a dual-stream retrieval method that achieved preliminary results for text-to-image, image-to-text, and keyword-based tasks.
The burgeoning integration of 3D medical imaging into healthcare has led to a substantial increase in the workload of medical professionals. To assist clinicians in their diagnostic processes and alleviate their workload, the development of a robust system for retrieving similar case studies presents a viable solution. While the concept holds great promise, the field of 3D medical text-image retrieval is currently limited by the absence of robust evaluation benchmarks and curated datasets. To remedy this, our study presents a groundbreaking dataset, {BIMCV-R}, which includes an extensive collection of 8,069 3D CT volumes, encompassing over 2 million slices, paired with their respective radiological reports. Expanding upon the foundational work of our dataset, we craft a retrieval strategy, MedFinder. This approach employs a dual-stream network architecture, harnessing the potential of large language models to advance the field of medical image retrieval beyond existing text-image retrieval solutions. It marks our preliminary step towards developing a system capable of facilitating text-to-image, image-to-text, and keyword-based retrieval tasks. Our project is available at \url{https://huggingface.co/datasets/cyd0806/BIMCV-R}.