Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model

Computer Science > Artificial Intelligence [Submitted on 5 Jun 2026] Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model Kaouther Mouheb, Amos Pomp, Antoine Manenti, Romy de Haan, Farog Faghir, Joy Martens, Harro Seelaar, Francesco Mattace-Raso, Meike W. Vernooij, Frank J. Wolters, Stefan Klein, Esther E. Bron Objectives: Automatic data extraction from free-text radiology reports enables large-scale research, but few studies assessed the performance of large language models (LLMs) on Dutch neuroradiology reports. Methods: We analyzed 947 brain MRI reports from a tertiary memory clinic (2016-2021), authored by consultant neuroradiologists. Trained medical students annotated thirty variables; 100 reports were double-annotated to assess inter-rater reliability. We evaluated the performance of the open-weight LLM LLaMA 3.1 using different languages (Dutch vs. English translation) and few-shot prompting with different example selection strategies. Performance was evaluated using balanced accuracy for categorical variables, accuracy and mean absolute error for counts, and text similarity for free-text. Metrics were computed across 10 random splits of the 947 reports. Results: LLaMA 3.1 demonstrated high zero-shot performance for visual rating scores (mean [95%-CI]): Medial Temporal Atrophy: 90% [77-100%] on the left and 96% [94-99%] on the right, Global Cortical Atrophy: 87% [83-91%], and Fazekas: 94% [93-96%]. Microbleed mentions were detected with 93% accuracy [92-95%] and infarct mentions with 82% [80-84%]. Text similarity for lesion location reached 0.95 [0.95-0.96]. Performance was lower for numerical variables: 80% [78-82%] for the number of microbleeds and 66% [63-68%] for infarcts. English translation yielded comparable results. Few-shot prompting improved performance for numerical variables, achieving 92% [90-93%] for microbleeds and 81% [77-85%] for infarcts using structural similarity-based selection. Conclusion: LLaMA 3.1 shows strong potential for extracting data from Dutch neuroradiology reports. Few-shot prompting enhances performance for numerical variables, whereas challenges remain for location-specific variables. Comments: Submitted to European Radiology Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.07721 [cs.AI]   (or arXiv:2606.07721v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.07721 Focus to learn more Submission history From: Kaouther Mouheb [view email] [v1] Fri, 5 Jun 2026 15:57:35 UTC (6,056 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)