@inproceedings{akhter-etal-2026-rad,
title = "Rad-Flamingo: A Multimodal Prompt driven Radiology Report Generation Framework with Patient-Centric Explanations",
author = "Akhter, Md. Tousin and
Lalwani, Devansh and
Jadhav, Kshitij Sharad and
Bhattacharyya, Pushpak",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.10/",
pages = "166--188",
ISBN = "979-8-89176-386-9",
abstract = "In modern healthcare, radiology plays a pivotal role in diagnosing and managing diseases. However, the complexity of medical imaging data and the variability in interpretation can lead to inconsistencies and a lack of patient-centered insight in radiology reports. To address this challenge, a novel multimodal prompt-driven report generation framework Rad-Flamingo was developed, that integrates diverse data modalities{---}such as medical images, and clinical notes{---}to produce comprehensive and context-aware radiology reports. Our framework leverages innovative prompt engineering techniques to guide vision-language models in generating relevant information, ensuring these generated reports are not only accurate but also understandable to individual patients. A key feature of our framework is its ability to provide patient-centric explanations, offering clear and personalized insights into diagnostic findings and their implications. Additionally, we also demonstrate a synthetic data generation pipeline, to append any existing benchmark datasets' findings and impressions with patient-centric explanation. Experimental results demonstrate that this framework{'}s effectiveness in enhancing report quality, improving understandability, and could foster better patient-doctor communication. This approach represents a significant step towards human-centered medical AI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akhter-etal-2026-rad">
<titleInfo>
<title>Rad-Flamingo: A Multimodal Prompt driven Radiology Report Generation Framework with Patient-Centric Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Tousin</namePart>
<namePart type="family">Akhter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devansh</namePart>
<namePart type="family">Lalwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kshitij</namePart>
<namePart type="given">Sharad</namePart>
<namePart type="family">Jadhav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>In modern healthcare, radiology plays a pivotal role in diagnosing and managing diseases. However, the complexity of medical imaging data and the variability in interpretation can lead to inconsistencies and a lack of patient-centered insight in radiology reports. To address this challenge, a novel multimodal prompt-driven report generation framework Rad-Flamingo was developed, that integrates diverse data modalities—such as medical images, and clinical notes—to produce comprehensive and context-aware radiology reports. Our framework leverages innovative prompt engineering techniques to guide vision-language models in generating relevant information, ensuring these generated reports are not only accurate but also understandable to individual patients. A key feature of our framework is its ability to provide patient-centric explanations, offering clear and personalized insights into diagnostic findings and their implications. Additionally, we also demonstrate a synthetic data generation pipeline, to append any existing benchmark datasets’ findings and impressions with patient-centric explanation. Experimental results demonstrate that this framework’s effectiveness in enhancing report quality, improving understandability, and could foster better patient-doctor communication. This approach represents a significant step towards human-centered medical AI systems.</abstract>
<identifier type="citekey">akhter-etal-2026-rad</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.10/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>166</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rad-Flamingo: A Multimodal Prompt driven Radiology Report Generation Framework with Patient-Centric Explanations
%A Akhter, Md. Tousin
%A Lalwani, Devansh
%A Jadhav, Kshitij Sharad
%A Bhattacharyya, Pushpak
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F akhter-etal-2026-rad
%X In modern healthcare, radiology plays a pivotal role in diagnosing and managing diseases. However, the complexity of medical imaging data and the variability in interpretation can lead to inconsistencies and a lack of patient-centered insight in radiology reports. To address this challenge, a novel multimodal prompt-driven report generation framework Rad-Flamingo was developed, that integrates diverse data modalities—such as medical images, and clinical notes—to produce comprehensive and context-aware radiology reports. Our framework leverages innovative prompt engineering techniques to guide vision-language models in generating relevant information, ensuring these generated reports are not only accurate but also understandable to individual patients. A key feature of our framework is its ability to provide patient-centric explanations, offering clear and personalized insights into diagnostic findings and their implications. Additionally, we also demonstrate a synthetic data generation pipeline, to append any existing benchmark datasets’ findings and impressions with patient-centric explanation. Experimental results demonstrate that this framework’s effectiveness in enhancing report quality, improving understandability, and could foster better patient-doctor communication. This approach represents a significant step towards human-centered medical AI systems.
%U https://aclanthology.org/2026.findings-eacl.10/
%P 166-188
Markdown (Informal)
[Rad-Flamingo: A Multimodal Prompt driven Radiology Report Generation Framework with Patient-Centric Explanations](https://aclanthology.org/2026.findings-eacl.10/) (Akhter et al., Findings 2026)
ACL