Martín-Noguerol Teodoro, López-Úbeda Pilar, Luna Antonio, Gómez-Río Manuel, Górriz Juan M
MRI unit, Radiology department, HT medica, Carmelo Torres n°2, 23007, Jaén, Spain.
NLP unit, HT medica, Carmelo Torres n°2, 23007, Jaén, Spain.
Clin Neuroradiol. 2025 Jun 5. doi: 10.1007/s00062-025-01533-4.
Determining the involvement of specific peripheral nerves (PNs) in the upper limb associated with signs of muscle denervation can be challenging. This study aims to develop, compare, and validate various large language models (LLMs) to automatically identify and establish potential relationships between denervated muscles and their corresponding PNs.
We collected 300 retrospective MRI reports in Spanish from upper limb examinations conducted between 2018 and 2024 that showed signs of muscle denervation. An expert radiologist manually annotated these reports based on the affected peripheral nerves (median, ulnar, radial, axillary, and suprascapular). BERT, DistilBERT, mBART, RoBERTa, and Medical-ELECTRA models were fine-tuned and evaluated on the reports. Additionally, an automatic voting system was implemented to consolidate predictions through majority voting.
The voting system achieved the highest F1 scores for the median, ulnar, and radial nerves, with scores of 0.88, 1.00, and 0.90, respectively. Medical-ELECTRA also performed well, achieving F1 scores above 0.82 for the axillary and suprascapular nerves. In contrast, mBART demonstrated lower performance, particularly with an F1 score of 0.38 for the median nerve.
Our voting system generally outperforms the individually tested LLMs in determining the specific PN likely associated with muscle denervation patterns detected in upper limb MRI reports. This system can thereby assist radiologists by suggesting the implicated PN when generating their radiology reports.
确定与肌肉去神经支配迹象相关的上肢特定周围神经（PNs）的受累情况可能具有挑战性。本研究旨在开发、比较和验证各种大语言模型（LLMs），以自动识别并建立去神经支配肌肉与其相应PNs之间的潜在关系。
我们收集了2018年至2024年间上肢检查的300份西班牙语回顾性MRI报告，这些报告显示有肌肉去神经支配的迹象。一位专家放射科医生根据受影响的周围神经（正中神经、尺神经、桡神经、腋神经和肩胛上神经）对这些报告进行了手动标注。对BERT、DistilBERT、mBART、RoBERTa和Medical-ELECTRA模型在这些报告上进行了微调与评估。此外，还实施了一个自动投票系统，通过多数投票来巩固预测结果。
投票系统在正中神经、尺神经和桡神经方面取得了最高的F1分数，分别为0.88、1.00和0.90。Medical-ELECTRA在腋神经和肩胛上神经方面也表现良好，F1分数高于0.82。相比之下，mBART表现较差，尤其是正中神经的F1分数为0.38。
在确定可能与上肢MRI报告中检测到的肌肉去神经支配模式相关的特定PN方面，我们的投票系统总体上优于单独测试的LLMs。因此，该系统在放射科医生生成放射学报告时，通过提示相关的PN，可为他们提供帮助。
