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

Yeongjae Cho, Taehee Kim, Heejun Shin, Sungzoon Cho, Dongmyung Shin
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:263-275, 2024.

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 enhance the modelś performance using a pretrained vision-language model (VLM). Here, we introduce a novel VLM called PLURAL, which is pretrained on natural and longitudinal chest X-ray data for the diff-VQA task. The model is developed using a step-by-step approach, starting with being pretrained on natural images and texts, followed by being trained using longitudinal chest X-ray data. The longitudinal data consist of pairs of X-ray images, along with question-answer sets and radiologist’s reports that describe the changes in lung abnormalities and diseases over time. Our experimental results show that the PLURAL model outperforms state-of-the-art methods not only in diff-VQA for longitudinal X-rays but also in conventional VQA for a single X-ray image. Through extensive experiments, we demonstrate the effectiveness of the proposed VLM architecture and pretraining method in improving the model’s performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-cho24a, title = {Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays}, author = {Cho, Yeongjae and Kim, Taehee and Shin, Heejun and Cho, Sungzoon and Shin, Dongmyung}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {263--275}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/cho24a/cho24a.pdf}, url = {https://proceedings.mlr.press/v250/cho24a.html}, 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 enhance the modelś performance using a pretrained vision-language model (VLM). Here, we introduce a novel VLM called PLURAL, which is pretrained on natural and longitudinal chest X-ray data for the diff-VQA task. The model is developed using a step-by-step approach, starting with being pretrained on natural images and texts, followed by being trained using longitudinal chest X-ray data. The longitudinal data consist of pairs of X-ray images, along with question-answer sets and radiologist’s reports that describe the changes in lung abnormalities and diseases over time. Our experimental results show that the PLURAL model outperforms state-of-the-art methods not only in diff-VQA for longitudinal X-rays but also in conventional VQA for a single X-ray image. Through extensive experiments, we demonstrate the effectiveness of the proposed VLM architecture and pretraining method in improving the model’s performance.} }
Endnote
%0 Conference Paper %T Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays %A Yeongjae Cho %A Taehee Kim %A Heejun Shin %A Sungzoon Cho %A Dongmyung Shin %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-cho24a %I PMLR %P 263--275 %U https://proceedings.mlr.press/v250/cho24a.html %V 250 %X 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 enhance the modelś performance using a pretrained vision-language model (VLM). Here, we introduce a novel VLM called PLURAL, which is pretrained on natural and longitudinal chest X-ray data for the diff-VQA task. The model is developed using a step-by-step approach, starting with being pretrained on natural images and texts, followed by being trained using longitudinal chest X-ray data. The longitudinal data consist of pairs of X-ray images, along with question-answer sets and radiologist’s reports that describe the changes in lung abnormalities and diseases over time. Our experimental results show that the PLURAL model outperforms state-of-the-art methods not only in diff-VQA for longitudinal X-rays but also in conventional VQA for a single X-ray image. Through extensive experiments, we demonstrate the effectiveness of the proposed VLM architecture and pretraining method in improving the model’s performance.
APA
Cho, Y., Kim, T., Shin, H., Cho, S. & Shin, D.. (2024). Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:263-275 Available from https://proceedings.mlr.press/v250/cho24a.html.

Related Material