Retrieval-Based Chest X-Ray Report Generation Using a Pre-trained Contrastive Language-Image Model
Mark Endo*, Rayan Krishnan*, Viswesh Krishna, Andrew Y. Ng, Pranav Rajpurkar
Abstract: We propose CXR-RePaiR: a retrieval-based radiology report generation approach using a pre-trained contrastive language-image model. Our method generates clinically accurate reports on both in-distribution and out-of-distribution data. CXR-RePaiR outperforms or matches prior report generation methods on clinical metrics, achieving an average F1-score of 0.540 (+/-22.7%) on an external radiology dataset (CheXpert). Further, we implement a compression approach used to reduce the size of the reference corpus and speed up the runtime of our retrieval method. With compression, our model maintains similar performance while producing reports 70% faster than the best generative model. Our approach can be broadly useful in improving the diagnostic performance and generalizability of report generation models and enabling their use in clinical workflows.