PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914581374304256 |
|---|---|
| author | Lin, Ying-Jia Lo, Tzu-Chin Li, Ping-Chien Cheng, Chi-Tung Liao, Chien-Hung Kao, Hung-Yu |
| author_facet | Lin, Ying-Jia Lo, Tzu-Chin Li, Ping-Chien Cheng, Chi-Tung Liao, Chien-Hung Kao, Hung-Yu |
| contents | Automatic report labeling facilitates the identification of clinical findings from unstructured text and enables large-scale annotation for medical imaging research. Existing rule-based labelers struggle with the diverse descriptions in clinical reports, while fine-tuning pre-trained language models (PLMs) requires large amounts of labeled data that are often unavailable in clinical settings. In this paper, we propose PromptRad, a knowledge-enhanced multi-label \textbf{prompt}-tuning approach for \textbf{rad}iology report labeling under low-resource settings. PromptRad reformulates multi-label classification as masked language modeling and incorporates synonyms from the UMLS Metathesaurus into a multi-word verbalizer to enrich category representations. By fine-tuning the PLM without additional classification layers, PromptRad requires substantially less labeled data than conventional fine-tuning. Experiments on liver CT (computed tomography) reports show that PromptRad outperforms dictionary-based and fine-tuning baselines with only 32 labeled training examples, and achieves competitive performance with GPT-4 despite using a much smaller model. Further analysis demonstrates that PromptRad captures complex negation patterns more effectively than existing methods, making it a promising solution for report labeling in data-scarce clinical scenarios. Our code is available at https://github.com/ila-lab/PromptRad. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20052 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling Lin, Ying-Jia Lo, Tzu-Chin Li, Ping-Chien Cheng, Chi-Tung Liao, Chien-Hung Kao, Hung-Yu Computation and Language Artificial Intelligence Automatic report labeling facilitates the identification of clinical findings from unstructured text and enables large-scale annotation for medical imaging research. Existing rule-based labelers struggle with the diverse descriptions in clinical reports, while fine-tuning pre-trained language models (PLMs) requires large amounts of labeled data that are often unavailable in clinical settings. In this paper, we propose PromptRad, a knowledge-enhanced multi-label \textbf{prompt}-tuning approach for \textbf{rad}iology report labeling under low-resource settings. PromptRad reformulates multi-label classification as masked language modeling and incorporates synonyms from the UMLS Metathesaurus into a multi-word verbalizer to enrich category representations. By fine-tuning the PLM without additional classification layers, PromptRad requires substantially less labeled data than conventional fine-tuning. Experiments on liver CT (computed tomography) reports show that PromptRad outperforms dictionary-based and fine-tuning baselines with only 32 labeled training examples, and achieves competitive performance with GPT-4 despite using a much smaller model. Further analysis demonstrates that PromptRad captures complex negation patterns more effectively than existing methods, making it a promising solution for report labeling in data-scarce clinical scenarios. Our code is available at https://github.com/ila-lab/PromptRad. |
| title | PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.20052 |