ReXplain: Translating Radiology into Patient-Friendly Video Reports

Luyang Luo, Jenanan Vairavamurthy, Xiaoman Zhang, Abhinav Kumar, Ramon R. Ter-Oganesyan, Stuart T. Schroff, Dan Shilo, Rydhwana Hossain, Mike Moritz, Pranav Rajpurkar
Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 281:109-120, 2025.

Abstract

Radiology reports, designed for efficient communication between medical experts, often remain incomprehensible to patients. This inaccessibility could potentially lead to anxiety, decreased engagement in treatment decisions, and poorer health outcomes, undermining patient-centered care. We present ReXplain (Radiology eXplanation), an innovative AI-driven system that translates radiology findings into patient-friendly video reports. ReXplain uniquely integrates a large language model for medical text simplification and text-anatomy association, an image segmentation model for anatomical region identification, and an avatar generation tool for engaging interface visualization. ReXplain enables producing comprehensive explanations with plain language, highlighted imagery, and 3D organ renderings in the form of video reports. To evaluate the utility of ReXplain-generated explanations, we conducted two rounds of user feedback collection from six board-certified radiologists. The results of this proof-of-concept study indicates that ReXplain could accurately deliver radiological information and effectively simulate one-on-one consultation, shedding light on enhancing patient-centered radiology with potential clinical usage. This work demonstrates a new paradigm in AI-assisted medical communication, potentially improving patient engagement and satisfaction in radiology care, and opens new avenues for research in multimodal medical communication.

Cite this Paper

BibTeX
@InProceedings{pmlr-v281-luo25a, title = {ReXplain: Translating Radiology into Patient-Friendly Video Reports}, author = {Luo, Luyang and Vairavamurthy, Jenanan and Zhang, Xiaoman and Kumar, Abhinav and Ter-Oganesyan, Ramon R. and Schroff, Stuart T. and Shilo, Dan and Hossain, Rydhwana and Moritz, Mike and Rajpurkar, Pranav}, booktitle = {Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare}, pages = {109--120}, year = {2025}, editor = {Wu, Junde and Zhu, Jiayuan and Xu, Min and Jin, Yueming}, volume = {281}, series = {Proceedings of Machine Learning Research}, month = {25 Feb}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v281/main/assets/luo25a/luo25a.pdf}, url = {https://proceedings.mlr.press/v281/luo25a.html}, abstract = {Radiology reports, designed for efficient communication between medical experts, often remain incomprehensible to patients. This inaccessibility could potentially lead to anxiety, decreased engagement in treatment decisions, and poorer health outcomes, undermining patient-centered care. We present ReXplain (Radiology eXplanation), an innovative AI-driven system that translates radiology findings into patient-friendly video reports. ReXplain uniquely integrates a large language model for medical text simplification and text-anatomy association, an image segmentation model for anatomical region identification, and an avatar generation tool for engaging interface visualization. ReXplain enables producing comprehensive explanations with plain language, highlighted imagery, and 3D organ renderings in the form of video reports. To evaluate the utility of ReXplain-generated explanations, we conducted two rounds of user feedback collection from six board-certified radiologists. The results of this proof-of-concept study indicates that ReXplain could accurately deliver radiological information and effectively simulate one-on-one consultation, shedding light on enhancing patient-centered radiology with potential clinical usage. This work demonstrates a new paradigm in AI-assisted medical communication, potentially improving patient engagement and satisfaction in radiology care, and opens new avenues for research in multimodal medical communication.} }
Endnote
%0 Conference Paper %T ReXplain: Translating Radiology into Patient-Friendly Video Reports %A Luyang Luo %A Jenanan Vairavamurthy %A Xiaoman Zhang %A Abhinav Kumar %A Ramon R. Ter-Oganesyan %A Stuart T. Schroff %A Dan Shilo %A Rydhwana Hossain %A Mike Moritz %A Pranav Rajpurkar %B Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare %C Proceedings of Machine Learning Research %D 2025 %E Junde Wu %E Jiayuan Zhu %E Min Xu %E Yueming Jin %F pmlr-v281-luo25a %I PMLR %P 109--120 %U https://proceedings.mlr.press/v281/luo25a.html %V 281 %X Radiology reports, designed for efficient communication between medical experts, often remain incomprehensible to patients. This inaccessibility could potentially lead to anxiety, decreased engagement in treatment decisions, and poorer health outcomes, undermining patient-centered care. We present ReXplain (Radiology eXplanation), an innovative AI-driven system that translates radiology findings into patient-friendly video reports. ReXplain uniquely integrates a large language model for medical text simplification and text-anatomy association, an image segmentation model for anatomical region identification, and an avatar generation tool for engaging interface visualization. ReXplain enables producing comprehensive explanations with plain language, highlighted imagery, and 3D organ renderings in the form of video reports. To evaluate the utility of ReXplain-generated explanations, we conducted two rounds of user feedback collection from six board-certified radiologists. The results of this proof-of-concept study indicates that ReXplain could accurately deliver radiological information and effectively simulate one-on-one consultation, shedding light on enhancing patient-centered radiology with potential clinical usage. This work demonstrates a new paradigm in AI-assisted medical communication, potentially improving patient engagement and satisfaction in radiology care, and opens new avenues for research in multimodal medical communication.
APA
Luo, L., Vairavamurthy, J., Zhang, X., Kumar, A., Ter-Oganesyan, R.R., Schroff, S.T., Shilo, D., Hossain, R., Moritz, M. & Rajpurkar, P.. (2025). ReXplain: Translating Radiology into Patient-Friendly Video Reports. Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 281:109-120 Available from https://proceedings.mlr.press/v281/luo25a.html.

Related Material