@inproceedings{schiavone-etal-2026-mosaic,
title = "{MOSAIC}: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings",
author = "Schiavone, Alice and
Fraccaro, Marco and
Pehrson, Lea Marie and
Ingala, Silvia and
Bonnevie, Rasmus and
Nielsen, Michael Bachmann and
Beliveau, Vincent and
Ganz, Melanie and
Elliott, Desmond",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.35/",
doi = "10.63317/3qvne99cm779",
pages = "313--323",
abstract = "Radiology reports contain rich clinical information that can be used to train imaging models without relying on costly manual annotation. However, existing approaches face critical limitations: rule-based methods struggle with linguistic variability, supervised models require large annotated datasets, and recent LLM-based systems depend on closed-source or resource-intensive models that are unsuitable for clinical use. Moreover, current solutions are largely restricted to English and single-modality, single-taxonomy datasets. We introduce MOSAIC, a multilingual, taxonomy-agnostic, and computationally efficient approach for radiological report classification. Built on a compact open-access language model (MedGemma-4B), MOSAIC supports both zero-/few-shot prompting and lightweight fine-tuning, enabling deployment on consumer-grade GPUs. We evaluate MOSAIC across seven datasets in English, Spanish, French, and Danish, spanning multiple imaging modalities and label taxonomies. The model achieves a mean macro F1 score of 88 across five chest X-ray datasets, approaching or exceeding expert-level performance, while requiring only 24 GB of GPU memory. With data augmentation, as few as 80 annotated samples are sufficient to reach a weighted F1 score of 82 on Danish reports, enabling large-scale cohort classification with minimal human effort. Code and models are open-source, offering a practical alternative to large or proprietary LLMs in clinical settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schiavone-etal-2026-mosaic">
<titleInfo>
<title>MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Schiavone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Fraccaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="given">Marie</namePart>
<namePart type="family">Pehrson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Ingala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rasmus</namePart>
<namePart type="family">Bonnevie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Bachmann</namePart>
<namePart type="family">Nielsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Beliveau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Ganz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<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">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Kirk</namePart>
<namePart type="family">Roberts</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>Radiology reports contain rich clinical information that can be used to train imaging models without relying on costly manual annotation. However, existing approaches face critical limitations: rule-based methods struggle with linguistic variability, supervised models require large annotated datasets, and recent LLM-based systems depend on closed-source or resource-intensive models that are unsuitable for clinical use. Moreover, current solutions are largely restricted to English and single-modality, single-taxonomy datasets. We introduce MOSAIC, a multilingual, taxonomy-agnostic, and computationally efficient approach for radiological report classification. Built on a compact open-access language model (MedGemma-4B), MOSAIC supports both zero-/few-shot prompting and lightweight fine-tuning, enabling deployment on consumer-grade GPUs. We evaluate MOSAIC across seven datasets in English, Spanish, French, and Danish, spanning multiple imaging modalities and label taxonomies. The model achieves a mean macro F1 score of 88 across five chest X-ray datasets, approaching or exceeding expert-level performance, while requiring only 24 GB of GPU memory. With data augmentation, as few as 80 annotated samples are sufficient to reach a weighted F1 score of 82 on Danish reports, enabling large-scale cohort classification with minimal human effort. Code and models are open-source, offering a practical alternative to large or proprietary LLMs in clinical settings.</abstract>
<identifier type="citekey">schiavone-etal-2026-mosaic</identifier>
<identifier type="doi">10.63317/3qvne99cm779</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.35/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>313</start>
<end>323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings
%A Schiavone, Alice
%A Fraccaro, Marco
%A Pehrson, Lea Marie
%A Ingala, Silvia
%A Bonnevie, Rasmus
%A Nielsen, Michael Bachmann
%A Beliveau, Vincent
%A Ganz, Melanie
%A Elliott, Desmond
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F schiavone-etal-2026-mosaic
%X Radiology reports contain rich clinical information that can be used to train imaging models without relying on costly manual annotation. However, existing approaches face critical limitations: rule-based methods struggle with linguistic variability, supervised models require large annotated datasets, and recent LLM-based systems depend on closed-source or resource-intensive models that are unsuitable for clinical use. Moreover, current solutions are largely restricted to English and single-modality, single-taxonomy datasets. We introduce MOSAIC, a multilingual, taxonomy-agnostic, and computationally efficient approach for radiological report classification. Built on a compact open-access language model (MedGemma-4B), MOSAIC supports both zero-/few-shot prompting and lightweight fine-tuning, enabling deployment on consumer-grade GPUs. We evaluate MOSAIC across seven datasets in English, Spanish, French, and Danish, spanning multiple imaging modalities and label taxonomies. The model achieves a mean macro F1 score of 88 across five chest X-ray datasets, approaching or exceeding expert-level performance, while requiring only 24 GB of GPU memory. With data augmentation, as few as 80 annotated samples are sufficient to reach a weighted F1 score of 82 on Danish reports, enabling large-scale cohort classification with minimal human effort. Code and models are open-source, offering a practical alternative to large or proprietary LLMs in clinical settings.
%R 10.63317/3qvne99cm779
%U https://aclanthology.org/2026.clinicalnlp-1.35/
%U https://doi.org/10.63317/3qvne99cm779
%P 313-323
Markdown (Informal)
[MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings](https://aclanthology.org/2026.clinicalnlp-1.35/) (Schiavone et al., ClinicalNLP 2026)
ACL
- Alice Schiavone, Marco Fraccaro, Lea Marie Pehrson, Silvia Ingala, Rasmus Bonnevie, Michael Bachmann Nielsen, Vincent Beliveau, Melanie Ganz, and Desmond Elliott. 2026. MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 313–323, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).