no code implementations • 5 May 2023 • Mercy Ranjit, Gopinath Ganapathy, Ranjit Manuel, Tanuja Ganu
We propose Retrieval Augmented Generation (RAG) as an approach for automated radiology report writing that leverages multimodally aligned embeddings from a contrastively pretrained vision language model for retrieval of relevant candidate radiology text for an input radiology image and a general domain generative model like OpenAI text-davinci-003, gpt-3. 5-turbo and gpt-4 for report generation using the relevant radiology text retrieved.