López-Úbeda Pilar, Martín-Noguerol Teodoro, Escartín Jorge, Cabrera-Zubizarreta Alberto, Luna Antonio
NLP Department. HT Medica, Carmelo Torres nº2, 23007, Jaén, Spain.
MRI Unit, Radiology Department, HT Medica. Carmelo Torres nº2, 23007, Jaén, Spain.
Jpn J Radiol. 2025 May;43(5):770-778. doi: 10.1007/s11604-024-01721-1. Epub 2024 Dec 28.
Structured reports in radiology have demonstrated substantial advantages over unstructured ones. However, the transition from unstructured to structured reporting can face challenges, as experienced radiologists worry about the potential loss of valuable information. In this study, we fine-tuned the Llama 2 model capable of generating structured pituitary MRI reports from unstructured reports.
We used a training set comprising 104 pituitary MRI reports to fine-tune Llama 2 and 26 reports as a test set to evaluate the system. The dataset was annotated manually by three expert radiologists. For this annotation, the radiologists used the unstructured report and structured it into eight anatomical landmarks: adenohypophysis, pituitary stalk, optic chiasm, suprasellar cistern, neurohypophysis, cavernous sinuses, sphenoid sinuses and other findings.
Llama2 achieves a value greater than 0.79 on the ROUGE-L metric in four anatomical landmarks from free-text pituitary MRI reports. The other anatomical landmarks exceed 0.61 of ROUGE-L except for the other findings section.
Our study suggests good performance in structuring anatomical landmarks on pituitary MRI reports using the fine-tune Llama 2 model.
放射学中的结构化报告已显示出比非结构化报告具有显著优势。然而，从非结构化报告向结构化报告的转变可能面临挑战，因为经验丰富的放射科医生担心会丢失有价值的信息。在本研究中，我们对能够从非结构化报告生成垂体MRI结构化报告的Llama 2模型进行了微调。
我们使用了一个包含104份垂体MRI报告的训练集来微调Llama 2，并使用26份报告作为测试集来评估该系统。数据集由三位放射学专家手动标注。对于此标注，放射科医生使用非结构化报告并将其结构化为八个解剖标志：腺垂体、垂体柄、视交叉、鞍上池、神经垂体、海绵窦、蝶窦和其他发现。
Llama2在来自自由文本垂体MRI报告的四个解剖标志上，ROUGE-L指标的值大于0.79。除其他发现部分外，其他解剖标志的ROUGE-L超过0.61。
我们的研究表明，使用微调后的Llama 2模型在构建垂体MRI报告的解剖标志方面具有良好性能。
