# KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization Source: [KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:33:16.495Z Authors: Gangwoo Kim, Hajung Kim, Lei Ji, Seongsu Bae, Chanhwi Kim, Mujeen Sung, Hyunjae Kim, Kun Yan, Eric Chang, Jaewoo Kang Published: 2023-07-10T21:18:01.000Z ## Abstract In this paper, we introduce CheXOFA, a new pre-trained vision-language model (VLM) for the chest X-ray domain. Our model is initially pre-trained on various multimodal datasets within the general domain before being transferred to the chest X-ray domain. Following a prominent VLM, we unify various domain-specific tasks into a simple sequence-to-sequence schema. It enables the model to effectively learn the required knowledge and skills from limited resources in the domain. Demonstrating superior performance on the benchmark datasets provided by the BioNLP shared task, our model benefits from its training across multiple tasks and domains. With subtle techniques including ensemble and factual calibration, our system achieves first place on the RadSum23 leaderboard for the hidden test set. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Medical Report Summarization on MIMIC-CXR (test)](): Medical Report Summarization; MIMIC-CXR (test); ROUGE-L: 47.75. ## Original sources and implementation [Original paper]() [PDF]()