@inproceedings{udomlapsakul-etal-2024-sicar,
title = "{SICAR} at {RRG}2024: {GPU} Poor{'}s Guide to Radiology Report Generation",
author = "Udomlapsakul, Kiartnarin and
Pengpun, Parinthapat and
Saengja, Tossaporn and
Veerakanjana, Kanyakorn and
Tiankanon, Krittamate and
Khlaisamniang, Pitikorn and
Supholkhan, Pasit and
Chinkamol, Amrest and
Aussavavirojekul, Pubordee and
Phimsiri, Hirunkul and
Sripo, Tara and
Boonnag, Chiraphat and
Tongdee, Trongtum and
Siriapisith, Thanongchai and
Saiviroonporn, Pairash and
Kinchagawat, Jiramet and
Ittichaiwong, Piyalitt",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.55",
doi = "10.18653/v1/2024.bionlp-1.55",
pages = "635--644",
abstract = "Radiology report generation (RRG) aims to create free-text radiology reports from clinical imaging. Our solution employs a lightweight multimodal language model (MLLM) enhanced with a two-stage post-processing strategy, utilizing a Large Language Model (LLM) to boost diagnostic accuracy and ensure patient safety. We introduce the {``}First, Do No Harm{''} SafetyNet, which incorporates Xraydar, an advanced X-ray classification model, to cross-verify the model outputs and specifically address false negatives from the MLLM. This comprehensive approach combines the efficiency of lightweight models with the robustness of thorough post-processing techniques, offering a reliable solution for radiology report generation. Our system achieved fourth place on the F1-Radgraph metric for findings generation in the Radiology Report Generation Shared Task (RRG24).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="udomlapsakul-etal-2024-sicar">
<titleInfo>
<title>SICAR at RRG2024: GPU Poor’s Guide to Radiology Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiartnarin</namePart>
<namePart type="family">Udomlapsakul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parinthapat</namePart>
<namePart type="family">Pengpun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tossaporn</namePart>
<namePart type="family">Saengja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanyakorn</namePart>
<namePart type="family">Veerakanjana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krittamate</namePart>
<namePart type="family">Tiankanon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pitikorn</namePart>
<namePart type="family">Khlaisamniang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pasit</namePart>
<namePart type="family">Supholkhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrest</namePart>
<namePart type="family">Chinkamol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pubordee</namePart>
<namePart type="family">Aussavavirojekul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hirunkul</namePart>
<namePart type="family">Phimsiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Sripo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiraphat</namePart>
<namePart type="family">Boonnag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trongtum</namePart>
<namePart type="family">Tongdee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanongchai</namePart>
<namePart type="family">Siriapisith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pairash</namePart>
<namePart type="family">Saiviroonporn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiramet</namePart>
<namePart type="family">Kinchagawat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyalitt</namePart>
<namePart type="family">Ittichaiwong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</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">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Radiology report generation (RRG) aims to create free-text radiology reports from clinical imaging. Our solution employs a lightweight multimodal language model (MLLM) enhanced with a two-stage post-processing strategy, utilizing a Large Language Model (LLM) to boost diagnostic accuracy and ensure patient safety. We introduce the “First, Do No Harm” SafetyNet, which incorporates Xraydar, an advanced X-ray classification model, to cross-verify the model outputs and specifically address false negatives from the MLLM. This comprehensive approach combines the efficiency of lightweight models with the robustness of thorough post-processing techniques, offering a reliable solution for radiology report generation. Our system achieved fourth place on the F1-Radgraph metric for findings generation in the Radiology Report Generation Shared Task (RRG24).</abstract>
<identifier type="citekey">udomlapsakul-etal-2024-sicar</identifier>
<identifier type="doi">10.18653/v1/2024.bionlp-1.55</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.55</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>635</start>
<end>644</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SICAR at RRG2024: GPU Poor’s Guide to Radiology Report Generation
%A Udomlapsakul, Kiartnarin
%A Pengpun, Parinthapat
%A Saengja, Tossaporn
%A Veerakanjana, Kanyakorn
%A Tiankanon, Krittamate
%A Khlaisamniang, Pitikorn
%A Supholkhan, Pasit
%A Chinkamol, Amrest
%A Aussavavirojekul, Pubordee
%A Phimsiri, Hirunkul
%A Sripo, Tara
%A Boonnag, Chiraphat
%A Tongdee, Trongtum
%A Siriapisith, Thanongchai
%A Saiviroonporn, Pairash
%A Kinchagawat, Jiramet
%A Ittichaiwong, Piyalitt
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F udomlapsakul-etal-2024-sicar
%X Radiology report generation (RRG) aims to create free-text radiology reports from clinical imaging. Our solution employs a lightweight multimodal language model (MLLM) enhanced with a two-stage post-processing strategy, utilizing a Large Language Model (LLM) to boost diagnostic accuracy and ensure patient safety. We introduce the “First, Do No Harm” SafetyNet, which incorporates Xraydar, an advanced X-ray classification model, to cross-verify the model outputs and specifically address false negatives from the MLLM. This comprehensive approach combines the efficiency of lightweight models with the robustness of thorough post-processing techniques, offering a reliable solution for radiology report generation. Our system achieved fourth place on the F1-Radgraph metric for findings generation in the Radiology Report Generation Shared Task (RRG24).
%R 10.18653/v1/2024.bionlp-1.55
%U https://aclanthology.org/2024.bionlp-1.55
%U https://doi.org/10.18653/v1/2024.bionlp-1.55
%P 635-644
Markdown (Informal)
[SICAR at RRG2024: GPU Poor’s Guide to Radiology Report Generation](https://aclanthology.org/2024.bionlp-1.55) (Udomlapsakul et al., BioNLP-WS 2024)
ACL
- Kiartnarin Udomlapsakul, Parinthapat Pengpun, Tossaporn Saengja, Kanyakorn Veerakanjana, Krittamate Tiankanon, Pitikorn Khlaisamniang, Pasit Supholkhan, Amrest Chinkamol, Pubordee Aussavavirojekul, Hirunkul Phimsiri, Tara Sripo, Chiraphat Boonnag, Trongtum Tongdee, Thanongchai Siriapisith, Pairash Saiviroonporn, Jiramet Kinchagawat, and Piyalitt Ittichaiwong. 2024. SICAR at RRG2024: GPU Poor’s Guide to Radiology Report Generation. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 635–644, Bangkok, Thailand. Association for Computational Linguistics.