---
title: "MOSAIC — paper by Schiavone et al. (2026)"
description: "The authors present MOSAIC, a prompt-driven classifier built by fine-tuning compact open models (MedGemma-4B, plus a… 33 references."
authors: ["Alice Schiavone", "Marco Fraccaro", "Lea Marie Pehrson", "Silvia Ingala", "Rasmus Bonnevie", "Michael Bachmann Nielsen", "Vincent Beliveau", "Melanie Ganz", "Desmond Elliott"]
year: 2026
venue: "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026"
source: "https://aclanthology.org/2026.clinicalnlp-1.35/"
doi: "10.63317/3qvne99cm779"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/schiavone-2026-mosaic-multilingual-taxonomy-agnostic-computationally/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/schiavone-2026-mosaic-multilingual-taxonomy-agnostic-computationally/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/) / MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings

# MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings

**Authors:** Alice Schiavone, Marco Fraccaro, Lea Marie Pehrson, Silvia Ingala, Rasmus Bonnevie, Michael Bachmann Nielsen, Vincent Beliveau, Melanie Ganz and [Desmond Elliott](https://md.research.elamur.ai/free/en/authors/desmond-elliott/) · **Year:** 2026 · **Venue:** [Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/clinicalnlp/) ([Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/clinicalnlp/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.clinicalnlp-1.35/) · [PDF](https://aclanthology.org/2026.clinicalnlp-1.35.pdf) · [DOI 10.63317/3qvne99cm779](https://doi.org/10.63317/3qvne99cm779) · [OpenAlex](https://openalex.org/W7166515382)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Turning free-text radiology reports into finding labels could supply training data for imaging models without radiologists labelling each scan. Existing tools each have drawbacks. Rule systems break on varied phrasing. Supervised classifiers need many expert labels. LLM-based labelers often depend on large or proprietary models that cannot run locally on sensitive patient data. Most tools also assume English and a single fixed label set. The authors present MOSAIC, a prompt-driven classifier built by fine-tuning compact open models (MedGemma-4B, plus a Gemma-12B variant) with 4-bit quantization and LoRA on a single 24 GB GPU. It can also be used zero- or few-shot. It returns JSON labels for whatever finding list and mention scheme a dataset defines. It was evaluated on seven corpora in English, Spanish, French and Danish, covering chest X-ray and brain MRI reports. On five chest X-ray sets it reaches a mean macro F1 of 88, comparable to expert annotators. With augmentation, 80 labelled Danish reports are enough for a weighted F1 of 82. This makes it a practical, privacy-preserving option for hospitals with limited annotation budgets.

## Key points
- **Datasets:** MIMIC-CXR, PadChest-GR, CASIA-CXR, DanskCXR (private), REFLACX I, REFLACX II and DanskMRI (epilepsy-related brain MRI findings). They differ in language, modality, number of findings (3–49) and mention classes (positive, negative, uncertain).
- **Models compared:** Llama 3 (3B, 8B), Gemma 3 (4B, 12B), Mmed-Llama-8B, and larger Gemma-27B, MedGemma-27B and Llama-70B.
- **Training setup:** fine-tuning used an RTX 4090 with Rank-Stabilized LoRA on 4-bit quantized models. Only the largest models needed an H100.
- **Prompts:** all prompts and finding lists are in English, even for non-English reports. Each prompt is tailored to the dataset's label definitions.
- **Results and release:** mean macro F1 of 88 on the chest X-ray sets, and weighted F1 of 82 on Danish data from 80 samples with augmentation. Code and the 4B and 12B models are to be released as open source.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Copenhagen](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/) — University, Copenhagen, Denmark · 116 works · 15,292 citations
- [Universität Innsbruck](https://md.research.elamur.ai/free/en/universities/universitat-innsbruck/) — University, Innsbruck, Austria · 10 works · 876 citations
- [Copenhagen University Hospital](https://md.research.elamur.ai/free/en/hospitals/copenhagen-university-hospital/) — Hospital, Copenhagen, Denmark · 4 works · 1,008 citations

Also on the byline: [Innsbruck Medical University](https://ror.org/03pt86f80).

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 275 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 214 works

🧭 Topics (2): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 287 works

## Cite

Cite as: 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. Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{schiavone2026mosaic,
  title = {{MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification in Low-Resource Settings}},
  author = {Alice Schiavone, Marco Fraccaro, Lea Marie Pehrson, Silvia Ingala, Rasmus Bonnevie, Michael Bachmann Nielsen, Vincent Beliveau, Melanie Ganz and Desmond Elliott},
  booktitle = {Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026},
  year = {2026},
  doi = {10.63317/3qvne99cm779},
  url = {https://doi.org/10.63317/3qvne99cm779}
}
```

- [← previous Morphology-Aware Multi-Granularity Representation Learning for Agglutinative Languages](https://md.research.elamur.ai/free/en/papers/zhang-2026-morphology-aware-multi-granularity-representation/)
- [next → MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning](https://md.research.elamur.ai/free/en/papers/pavlova-2026-mosaic-masked-objective-selective-adaptation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/)

## References

33 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. David Ifeoluwa Adelani, Hannah Liu, Xiaoyu Shen, Nikita Vassilyev, Jesujoba O. Alabi, Yanke Mao, Haonan Gao, and Annie En-Shiun Lee. 2024. [Sib-200: A simple, inclusive, and big evaluation dataset for topic classification in 200+ languages and dialects](https://md.research.elamur.ai/free/en/papers/adelani-2023-sib-200-simple-inclusive-big/).
2. Fares Al Mohamad, Leonhard Donle, Felix Dorfner, Laura Romanescu, Kristin Drechsler, Mike P. Wattjes, Jawed Nawabi, Marcus R. Makowski, Hartmut Häntze, Lisa Adams, Lina Xu, Felix Busch, Aymen Meddeb, and Keno Kyrill Bressem. 2025. Open-source large language models can generate labels from radiology… [find](https://scholar.google.com/scholar?q=Fares+Al+Mohamad%2C+Leonhard+Donle%2C+Felix+Dorfner%2C+Laura+Romanescu%2C+Kristin+Drechsler%2C+Mike+P%2E+Wattjes%2C+Jawed+Nawabi%2C+Marcus+R%2E+Makowski%2C+Hartmut+H%C3%A4ntze%2C+Lisa+Adams%2C+Lina+Xu%2C+Felix+Busch%2C+Aymen+Meddeb%2C+)
3. Anonymous. 2025. Effective machine learning techniques for non-english radiology report classification: A danish case study. AI, 6(2). [find](https://scholar.google.com/scholar?q=Anonymous%2E+2025%2E+Effective+machine+learning+techniques+for+non%2Denglish+radiology+report+classification%3A+A+danish+case+study%2E+AI%2C+6%282%29%2E)
4. Vincent Beliveau, Helene Kaas, Martin Prener, Claes N Ladefoged, Desmond Elliott, Gitte M Knudsen, Lars H Pinborg, and Melanie Ganz. 2024. Classification of radiological text in small and imbalanced datasets in a non-english language. arXiv preprint arXiv:2409.20147. — [arXiv:2409.20147](https://arxiv.org/abs/2409.20147) [find](https://scholar.google.com/scholar?q=Vincent+Beliveau%2C+Helene+Kaas%2C+Martin+Prener%2C+Claes+N+Ladefoged%2C+Desmond+Elliott%2C+Gitte+M+Knudsen%2C+Lars+H+Pinborg%2C+and+Melanie+Ganz%2E+2024%2E+Classification+of+radiological+text+in+small+and+imbalanced+d)
5. Lukas Biewald. 2020. Experiment tracking with weights and biases. Software available from wandb.com. [find](https://scholar.google.com/scholar?q=Lukas+Biewald%2E+2020%2E+Experiment+tracking+with+weights+and+biases%2E+Software+available+from+wandb%2Ecom%2E)
6. Ricardo Bigolin Lanfredi, Mingyuan Zhang, William F Auffermann, Jessica Chan, Phuong-Anh T Duong, Vivek Srikumar, Trafton Drew, Joyce D Schroeder, and Tolga Tasdizen. 2022. Reflacx, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays. Scientific data, 9(1):35… [find](https://scholar.google.com/scholar?q=Ricardo+Bigolin+Lanfredi%2C+Mingyuan+Zhang%2C+William+F+Auffermann%2C+Jessica+Chan%2C+Phuong%2DAnh+T+Duong%2C+Vivek+Srikumar%2C+Trafton+Drew%2C+Joyce+D+Schroeder%2C+and+Tolga+Tasdizen%2E+2022%2E+Reflacx%2C+a+dataset+of+repor)
7. Daniel C Castro, Aurelia Bustos, Shruthi Bannur, Stephanie L Hyland, Kenza Bouzid, Maria Teodora Wetscherek, Maria Dolores Sánchez-Valverde, Lara Jaques-Pérez, Lourdes Pérez-Rodríguez, Kenji Takeda, et al. 2024. Padchest-gr: A bilingual chest x-ray dataset for grounded radiology report generation. a… — [arXiv:2411.05085](https://arxiv.org/abs/2411.05085) [find](https://scholar.google.com/scholar?q=Daniel+C+Castro%2C+Aurelia+Bustos%2C+Shruthi+Bannur%2C+Stephanie+L+Hyland%2C+Kenza+Bouzid%2C+Maria+Teodora+Wetscherek%2C+Maria+Dolores+S%C3%A1nchez%2DValverde%2C+Lara+Jaques%2DP%C3%A9rez%2C+Lourdes+P%C3%A9rez%2DRodr%C3%ADguez%2C+Kenji+Takeda%2C+e)
8. Jaime Collado-Montañez, María-Teresa Martín-Valdivia, and Eugenio Martínez-Cámara. 2025. Data augmentation based on large language models for radiological report classification. Knowledge-Based Systems, 308:112745. [find](https://scholar.google.com/scholar?q=Jaime+Collado%2DMonta%C3%B1ez%2C+Mar%C3%ADa%2DTeresa+Mart%C3%ADn%2DValdivia%2C+and+Eugenio+Mart%C3%ADnez%2DC%C3%A1mara%2E+2025%2E+Data+augmentation+based+on+large+language+models+for+radiological+report+classification%2E+Knowledge%2DBased+System)
9. Felix J Dorfner, Liv Jürgensen, Leonhard Donle, Fares Al Mohamad, Tobias R Bodenmann, Mason C Cleveland, Felix Busch, Lisa C Adams, James Sato, Thomas Schultz, et al. 2024. Is open-source there yet? a comparative study on commercial and open-source llms in their ability to label chest x-ray reports.… — [arXiv:2402.12298](https://arxiv.org/abs/2402.12298) [find](https://scholar.google.com/scholar?q=Felix+J+Dorfner%2C+Liv+J%C3%BCrgensen%2C+Leonhard+Donle%2C+Fares+Al+Mohamad%2C+Tobias+R+Bodenmann%2C+Mason+C+Cleveland%2C+Felix+Busch%2C+Lisa+C+Adams%2C+James+Sato%2C+Thomas+Schultz%2C+et+al%2E+2024%2E+Is+open%2Dsource+there+yet%3F+a)
10. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
11. Jawook Gu, Han-Cheol Cho, Jiho Kim, Kihyun You, Eun Kyoung Hong, and Byungseok Roh. 2024. Chex-gpt: Harnessing large language models for enhanced chest x-ray report labeling. arXiv preprint arXiv:2401.11505. — [arXiv:2401.11505](https://arxiv.org/abs/2401.11505) [find](https://scholar.google.com/scholar?q=Jawook+Gu%2C+Han%2DCheol+Cho%2C+Jiho+Kim%2C+Kihyun+You%2C+Eun+Kyoung+Hong%2C+and+Byungseok+Roh%2E+2024%2E+Chex%2Dgpt%3A+Harnessing+large+language+models+for+enhanced+chest+x%2Dray+report+labeling%2E+arXiv+preprint+arXiv%3A2401)
12. Daniel Han, Michael Han, and Unsloth team. 2023. Unsloth. [http://github.com/unslothai/](http://github.com/unslothai/) unsloth. Software. [↗](http://github.com/unslothai/)
13. Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, et al. 2019. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI conference on art… [find](https://scholar.google.com/scholar?q=Jeremy+Irvin%2C+Pranav+Rajpurkar%2C+Michael+Ko%2C+Yifan+Yu%2C+Silviana+Ciurea%2DIlcus%2C+Chris+Chute%2C+Henrik+Marklund%2C+Behzad+Haghgoo%2C+Robyn+Ball%2C+Katie+Shpanskaya%2C+et+al%2E+2019%2E+Chexpert%3A+A+large+chest+radiograph)
14. Alistair Johnson, Matt Lungren, Yifan Peng, Zhiyong Lu, Roger Mark, Seth Berkowitz, and Steven Horng. 2019. Mimic-cxr-jpg-chest radiographs with structured labels. PhysioNet, 101:215–220. [find](https://scholar.google.com/scholar?q=Alistair+Johnson%2C+Matt+Lungren%2C+Yifan+Peng%2C+Zhiyong+Lu%2C+Roger+Mark%2C+Seth+Berkowitz%2C+and+Steven+Horng%2E+2019%2E+Mimic%2Dcxr%2Djpg%2Dchest+radiographs+with+structured+labels%2E+PhysioNet%2C+101%3A215%E2%80%93220%2E)
15. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
16. Hidetoshi Matsuo, Mizuho Nishio, Takaaki Matsunaga, Koji Fujimoto, and Takamichi Murakami. 2024. Exploring multilingual large language models for enhanced tnm classification of radiology report in lung cancer staging. Cancers, 16(21):3621. [find](https://scholar.google.com/scholar?q=Hidetoshi+Matsuo%2C+Mizuho+Nishio%2C+Takaaki+Matsunaga%2C+Koji+Fujimoto%2C+and+Takamichi+Murakami%2E+2024%2E+Exploring+multilingual+large+language+models+for+enhanced+tnm+classification+of+radiology+report+in+lun)
17. Markus Mergen, Daniel Spitzl, Conrad Ketzer, Maximilian Strenzke, Alexander W. Marka, Marcus R. Makowski, Keno K. Bressem, Lisa C. Adams, and Florian T. Gassert. 2025. Leveraging large language models for accurate ao fracture classification from ct text reports. Journal of Imaging Informatics in Med… [find](https://scholar.google.com/scholar?q=Markus+Mergen%2C+Daniel+Spitzl%2C+Conrad+Ketzer%2C+Maximilian+Strenzke%2C+Alexander+W%2E+Marka%2C+Marcus+R%2E+Makowski%2C+Keno+K%2E+Bressem%2C+Lisa+C%2E+Adams%2C+and+Florian+T%2E+Gassert%2E+2025%2E+Leveraging+large+language+models)
18. Hichem Metmer and Xiaoshan Yang. 2024. An open chest x-ray dataset with benchmarks for automatic radiology report generation in french. Neurocomputing, 609:128478. [find](https://scholar.google.com/scholar?q=Hichem+Metmer+and+Xiaoshan+Yang%2E+2024%2E+An+open+chest+x%2Dray+dataset+with+benchmarks+for+automatic+radiology+report+generation+in+french%2E+Neurocomputing%2C+609%3A128478%2E)
19. Luc Mottin, Jean-Philippe Goldman, Christoph Jäggli, Rita Achermann, Julien Gobeill, Julien Knafou, Julien Ehrsam, Alexandre Wicky, Camille L Gérard, Tanja Schwenk, et al. 2023. Multilingual recist classification of radiology reports using supervised learning. Frontiers in digital health, 5:1195017. [find](https://scholar.google.com/scholar?q=Luc+Mottin%2C+Jean%2DPhilippe+Goldman%2C+Christoph+J%C3%A4ggli%2C+Rita+Achermann%2C+Julien+Gobeill%2C+Julien+Knafou%2C+Julien+Ehrsam%2C+Alexandre+Wicky%2C+Camille+L+G%C3%A9rard%2C+Tanja+Schwenk%2C+et+al%2E+2023%2E+Multilingual+recist+cl)
20. Thao Nguyen, Tam M Vo, Thang V Nguyen, Hieu H Pham, and Ha Q Nguyen. 2022. Learning to diagnose common thorax diseases on chest radiographs from radiology reports in vietnamese. Plos one, 17(10):e0276545. [find](https://scholar.google.com/scholar?q=Thao+Nguyen%2C+Tam+M+Vo%2C+Thang+V+Nguyen%2C+Hieu+H+Pham%2C+and+Ha+Q+Nguyen%2E+2022%2E+Learning+to+diagnose+common+thorax+diseases+on+chest+radiographs+from+radiology+reports+in+vietnamese%2E+Plos+one%2C+17%2810%29%3Ae0276)
21. Matteo Olivato, Luca Putelli, Nicola Arici, Alfonso Emilio Gerevini, Alberto Lavelli, and Ivan Serina. 2024. Language models for hierarchical classification of radiology reports with attention mechanisms, bert, and gpt-4. IEEE Access, 12:69710– 69727. [find](https://scholar.google.com/scholar?q=Matteo+Olivato%2C+Luca+Putelli%2C+Nicola+Arici%2C+Alfonso+Emilio+Gerevini%2C+Alberto+Lavelli%2C+and+Ivan+Serina%2E+2024%2E+Language+models+for+hierarchical+classification+of+radiology+reports+with+attention+mechani)
22. David M Panicek and Hedvig Hricak. 2016. How sure are you, doctor? a standardized lexicon to describe the radiologist’s level of certainty. American Journal of Roentgenology, 207(1):2–3. [find](https://scholar.google.com/scholar?q=David+M+Panicek+and+Hedvig+Hricak%2E+2016%2E+How+sure+are+you%2C+doctor%3F+a+standardized+lexicon+to+describe+the+radiologist%E2%80%99s+level+of+certainty%2E+American+Journal+of+Roentgenology%2C+207%281%29%3A2%E2%80%933%2E)
23. Pengcheng Qiu, Chaoyi Wu, Xiaoman Zhang, Weixiong Lin, Haicheng Wang, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2024. [Towards building multilingual language model for medicine](https://md.research.elamur.ai/free/en/papers/qiu-2024-towards-building-multilingual-language-model/). Nature Communications, 15(1):8384.
24. Daniel Reichenpfader, Henning Müller, and Kerstin Denecke. 2024. A scoping review of large language model based approaches for information extraction from radiology reports. npj Digital Medicine, 7(1). [find](https://scholar.google.com/scholar?q=Daniel+Reichenpfader%2C+Henning+M%C3%BCller%2C+and+Kerstin+Denecke%2E+2024%2E+A+scoping+review+of+large+language+model+based+approaches+for+information+extraction+from+radiology+reports%2E+npj+Digital+Medicine%2C+7%281%29)
25. Eduardo P Reis, Joselisa PQ De Paiva, Maria CB Da Silva, Guilherme AS Ribeiro, Victor F Paiva, Lucas Bulgarelli, Henrique MH Lee, Paulo V Santos, Vanessa M Brito, Lucas TW Amaral, et al. 2022. Brax, brazilian labeled chest x-ray dataset. Scientific Data, 9(1):487. [find](https://scholar.google.com/scholar?q=Eduardo+P+Reis%2C+Joselisa+PQ+De+Paiva%2C+Maria+CB+Da+Silva%2C+Guilherme+AS+Ribeiro%2C+Victor+F+Paiva%2C+Lucas+Bulgarelli%2C+Henrique+MH+Lee%2C+Paulo+V+Santos%2C+Vanessa+M+Brito%2C+Lucas+TW+Amaral%2C+et+al%2E+2022%2E+Brax%2C+b)
26. Konstantinos Sechidis, Grigorios Tsoumakas, and Ioannis Vlahavas. 2011. On the stratification of multi-label data. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2011, Athens, Greece, September 5-9, 2011, Proceedings, Part III 22, pages 145–158. Springer. [find](https://scholar.google.com/scholar?q=Konstantinos+Sechidis%2C+Grigorios+Tsoumakas%2C+and+Ioannis+Vlahavas%2E+2011%2E+On+the+stratification+of+multi%2Dlabel+data%2E+In+Machine+Learning+and+Knowledge+Discovery+in+Databases%3A+European+Conference%2C+ECML+P)
27. Akshay Smit, Saahil Jain, Pranav Rajpurkar, Anuj Pareek, Andrew Y. Ng, and Matthew P. Lungren. 2020. Chexbert: [Combining automatic labelers and expert annotations for accurate radiology report labeling using BERT](https://md.research.elamur.ai/free/en/papers/smit-2020-combining-automatic-labelers-expert-annotations/). CoRR, abs/2004.09167.
28. Kazufumi Suzuki, Hiroki Yamada, Hiroshi Yamazaki, Goro Honda, and Shuji Sakai. 2024. Preliminary assessment of tnm classification performance for pancreatic cancer in japanese radiology reports using gpt-4. Japanese Journal of Radiology, 43(1):51–55. [find](https://scholar.google.com/scholar?q=Kazufumi+Suzuki%2C+Hiroki+Yamada%2C+Hiroshi+Yamazaki%2C+Goro+Honda%2C+and+Shuji+Sakai%2E+2024%2E+Preliminary+assessment+of+tnm+classification+performance+for+pancreatic+cancer+in+japanese+radiology+reports+using+)
29. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, et al. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+et+al%2E+2025%2E+Gemma+3+technical+report%2E+ar)
30. Alessandro Wollek, Sardi Hyska, Thomas Sedlmeyr, Philip Haitzer, Johannes Rueckel, Bastian O. Sabel, Michael Ingrisch, and Tobias Lasser. 2024. German chexpert chest x-ray radiology report labeler. RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren, 196(09):956–965… [find](https://scholar.google.com/scholar?q=Alessandro+Wollek%2C+Sardi+Hyska%2C+Thomas+Sedlmeyr%2C+Philip+Haitzer%2C+Johannes+Rueckel%2C+Bastian+O%2E+Sabel%2C+Michael+Ingrisch%2C+and+Tobias+Lasser%2E+2024%2E+German+chexpert+chest+x%2Dray+radiology+report+labeler%2E+R%C3%B6)
31. Eric Yang, Matthew D Li, Shruti Raghavan, Francis Deng, Min Lang, Marc D Succi, Ambrose J Huang, and Jayashree Kalpathy-Cramer. 2023. Transformer versus traditional natural language processing: how much data is enough for automated radiology report classification? The British Journal of Radiology, 9… [find](https://scholar.google.com/scholar?q=Eric+Yang%2C+Matthew+D+Li%2C+Shruti+Raghavan%2C+Francis+Deng%2C+Min+Lang%2C+Marc+D+Succi%2C+Ambrose+J+Huang%2C+and+Jayashree+Kalpathy%2DCramer%2E+2023%2E+Transformer+versus+traditional+natural+language+processing%3A+how+mu)
32. Shilong Zhang, Peize Sun, Shoufa Chen, Min Xiao, Wenqi Shao, Wenwei Zhang, Yu Liu, Kai Chen, and Ping Luo. 2025. Gpt4roi: Instruction tuning large language model on region-of-interest. In European Conference on Computer Vision, pages 52–70. Springer. [find](https://scholar.google.com/scholar?q=Shilong+Zhang%2C+Peize+Sun%2C+Shoufa+Chen%2C+Min+Xiao%2C+Wenqi+Shao%2C+Wenwei+Zhang%2C+Yu+Liu%2C+Kai+Chen%2C+and+Ping+Luo%2E+2025%2E+Gpt4roi%3A+Instruction+tuning+large+language+model+on+region%2Dof%2Dinterest%2E+In+European+Con)
33. Yirong Zhou, Paul K Amundson, Fangsheng Yu, Matthew M Kessler, Tammie L S Benzinger, and Franz J Wippold. 2014. Automated classification of radiology reports to facilitate retrospective study in radiology. Journal of Digital Imaging, 27(6):730–736. [find](https://scholar.google.com/scholar?q=Yirong+Zhou%2C+Paul+K+Amundson%2C+Fangsheng+Yu%2C+Matthew+M+Kessler%2C+Tammie+L+S+Benzinger%2C+and+Franz+J+Wippold%2E+2014%2E+Automated+classification+of+radiology+reports+to+facilitate+retrospective+study+in+radio)

*Updated 1 November 2026*