@inproceedings{marimuthu-etal-2026-structured,
title = "Structured Radiology Intelligence: Extracting Structured Data from {MRI} Reports Using {LLM}s",
author = "Marimuthu, Sushvin and
Krishnamurthy, Parameswari and
Sharma, Dipti Misra and
H, Goldwin and
Eapen, Anu and
Simon, Betty and
Chandramohan, Anuradha",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.24/",
doi = "10.63317/4vob5zztrfso",
pages = "268--280",
abstract = "This study presents efforts focused on extracting and structuring doctor notes, specifically Magnetic Resonance Imaging (MRI) reports, into a standardized format using large language models (LLMs). We introduce a novel benchmark dataset comprising of 55 clinically relevant variables given by doctors, making it the first of its kind in the automated processing of unstructured medical texts. The annotations to the dataset were generated using a systematic prompt-tuning approach that was manually validated. It was then evaluated across three experimental stages: baseline, intermediate, and fine-tuned. Each stage assessed the impact of different prompt strategies on the performance of various LLMs (LLaMA, Qwen, and DeepSeek). Among the models tested, LLaMA 3.1 8B Instruct consistently achieved the highest composite Score in both the intermediate and final phases, resulting in an 18.42{\%} improvement in performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marimuthu-etal-2026-structured">
<titleInfo>
<title>Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sushvin</namePart>
<namePart type="family">Marimuthu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goldwin</namePart>
<namePart type="family">H</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anu</namePart>
<namePart type="family">Eapen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Betty</namePart>
<namePart type="family">Simon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuradha</namePart>
<namePart type="family">Chandramohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</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">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study presents efforts focused on extracting and structuring doctor notes, specifically Magnetic Resonance Imaging (MRI) reports, into a standardized format using large language models (LLMs). We introduce a novel benchmark dataset comprising of 55 clinically relevant variables given by doctors, making it the first of its kind in the automated processing of unstructured medical texts. The annotations to the dataset were generated using a systematic prompt-tuning approach that was manually validated. It was then evaluated across three experimental stages: baseline, intermediate, and fine-tuned. Each stage assessed the impact of different prompt strategies on the performance of various LLMs (LLaMA, Qwen, and DeepSeek). Among the models tested, LLaMA 3.1 8B Instruct consistently achieved the highest composite Score in both the intermediate and final phases, resulting in an 18.42% improvement in performance.</abstract>
<identifier type="citekey">marimuthu-etal-2026-structured</identifier>
<identifier type="doi">10.63317/4vob5zztrfso</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.24/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>268</start>
<end>280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs
%A Marimuthu, Sushvin
%A Krishnamurthy, Parameswari
%A Sharma, Dipti Misra
%A H, Goldwin
%A Eapen, Anu
%A Simon, Betty
%A Chandramohan, Anuradha
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F marimuthu-etal-2026-structured
%X This study presents efforts focused on extracting and structuring doctor notes, specifically Magnetic Resonance Imaging (MRI) reports, into a standardized format using large language models (LLMs). We introduce a novel benchmark dataset comprising of 55 clinically relevant variables given by doctors, making it the first of its kind in the automated processing of unstructured medical texts. The annotations to the dataset were generated using a systematic prompt-tuning approach that was manually validated. It was then evaluated across three experimental stages: baseline, intermediate, and fine-tuned. Each stage assessed the impact of different prompt strategies on the performance of various LLMs (LLaMA, Qwen, and DeepSeek). Among the models tested, LLaMA 3.1 8B Instruct consistently achieved the highest composite Score in both the intermediate and final phases, resulting in an 18.42% improvement in performance.
%R 10.63317/4vob5zztrfso
%U https://aclanthology.org/2026.cl4health-1.24/
%U https://doi.org/10.63317/4vob5zztrfso
%P 268-280
Markdown (Informal)
[Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs](https://aclanthology.org/2026.cl4health-1.24/) (Marimuthu et al., CL4Health 2026)
ACL