@inproceedings{kapadnis-etal-2024-serpent,
title = "{SERPENT}-{VLM} : Self-Refining Radiology Report Generation Using Vision Language Models",
author = "Kapadnis, Manav and
Patnaik, Sohan and
Nandy, Abhilash and
Ray, Sourjyadip and
Goyal, Pawan and
Sheet, Debdoot",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.24/",
doi = "10.18653/v1/2024.clinicalnlp-1.24",
pages = "283--291",
abstract = "Radiology Report Generation (R2Gen) demonstrates how Multi-modal Large Language Models (MLLMs) can automate the creation of accurate and coherent radiological reports. Existing methods often hallucinate details in text-based reports that don`t accurately reflect the image content. To mitigate this, we introduce a novel strategy, SERPENT-VLM (SElf Refining Radiology RePort GENeraTion using Vision Language Models), which improves the R2Gen task by integrating a self-refining mechanism into the MLLM framework. We employ a unique self-supervised loss that leverages similarity between pooled image representations and the contextual representations of the generated radiological text, alongside the standard Causal Language Modeling objective, to refine image-text representations. This allows the model to scrutinize and align the generated text through dynamic interaction between a given image and the generated text, therefore reducing hallucination and continuously enhancing nuanced report generation. SERPENT-VLM outperforms existing baselines such as LlaVA-Med, BiomedGPT, etc., achieving SoTA performance on the IU X-ray and Radiology Objects in COntext (ROCO) datasets, and also proves to be robust against noisy images. A qualitative case study emphasizes the significant advancements towards more sophisticated MLLM frameworks for R2Gen, opening paths for further research into self-supervised refinement in the medical imaging domain."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kapadnis-etal-2024-serpent">
<titleInfo>
<title>SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manav</namePart>
<namePart type="family">Kapadnis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sohan</namePart>
<namePart type="family">Patnaik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilash</namePart>
<namePart type="family">Nandy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourjyadip</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debdoot</namePart>
<namePart type="family">Sheet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Radiology Report Generation (R2Gen) demonstrates how Multi-modal Large Language Models (MLLMs) can automate the creation of accurate and coherent radiological reports. Existing methods often hallucinate details in text-based reports that don‘t accurately reflect the image content. To mitigate this, we introduce a novel strategy, SERPENT-VLM (SElf Refining Radiology RePort GENeraTion using Vision Language Models), which improves the R2Gen task by integrating a self-refining mechanism into the MLLM framework. We employ a unique self-supervised loss that leverages similarity between pooled image representations and the contextual representations of the generated radiological text, alongside the standard Causal Language Modeling objective, to refine image-text representations. This allows the model to scrutinize and align the generated text through dynamic interaction between a given image and the generated text, therefore reducing hallucination and continuously enhancing nuanced report generation. SERPENT-VLM outperforms existing baselines such as LlaVA-Med, BiomedGPT, etc., achieving SoTA performance on the IU X-ray and Radiology Objects in COntext (ROCO) datasets, and also proves to be robust against noisy images. A qualitative case study emphasizes the significant advancements towards more sophisticated MLLM frameworks for R2Gen, opening paths for further research into self-supervised refinement in the medical imaging domain.</abstract>
<identifier type="citekey">kapadnis-etal-2024-serpent</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.24</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.24/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>283</start>
<end>291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models
%A Kapadnis, Manav
%A Patnaik, Sohan
%A Nandy, Abhilash
%A Ray, Sourjyadip
%A Goyal, Pawan
%A Sheet, Debdoot
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F kapadnis-etal-2024-serpent
%X Radiology Report Generation (R2Gen) demonstrates how Multi-modal Large Language Models (MLLMs) can automate the creation of accurate and coherent radiological reports. Existing methods often hallucinate details in text-based reports that don‘t accurately reflect the image content. To mitigate this, we introduce a novel strategy, SERPENT-VLM (SElf Refining Radiology RePort GENeraTion using Vision Language Models), which improves the R2Gen task by integrating a self-refining mechanism into the MLLM framework. We employ a unique self-supervised loss that leverages similarity between pooled image representations and the contextual representations of the generated radiological text, alongside the standard Causal Language Modeling objective, to refine image-text representations. This allows the model to scrutinize and align the generated text through dynamic interaction between a given image and the generated text, therefore reducing hallucination and continuously enhancing nuanced report generation. SERPENT-VLM outperforms existing baselines such as LlaVA-Med, BiomedGPT, etc., achieving SoTA performance on the IU X-ray and Radiology Objects in COntext (ROCO) datasets, and also proves to be robust against noisy images. A qualitative case study emphasizes the significant advancements towards more sophisticated MLLM frameworks for R2Gen, opening paths for further research into self-supervised refinement in the medical imaging domain.
%R 10.18653/v1/2024.clinicalnlp-1.24
%U https://aclanthology.org/2024.clinicalnlp-1.24/
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.24
%P 283-291
Markdown (Informal)
[SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models](https://aclanthology.org/2024.clinicalnlp-1.24/) (Kapadnis et al., ClinicalNLP 2024)
ACL