Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays

arXiv:2402.08966v1 Announce Type: cross
Abstract: Difference visual question answering (diff-VQA) is a challenging task that requires answering complex questions based on differences between a pair of images. This task is particularly important in reading chest X-ray images because radiologists often compare multiple images of the same patient taken at different times to track disease progression and changes in its severity in their clinical practice. However, previous works focused on designing specific network architectures for the diff-VQA task, missing opportunities to …

abstract arxiv cs.cl cs.cv diff difference differences images language language model multiple patient pretraining question question answering questions ray reading type vision visual x-ray