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

arXiv: https://arxiv.org/abs/2606.07721 · HTML: https://mlsanity.com/paper/2606.07721/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation](https://mlsanity.com/paper/2305.16938/) (2023)
- [RobBERT: a Dutch RoBERTa-based Language Model](https://mlsanity.com/paper/2001.06286/) (2020)
- [LLMs Are Few-Shot In-Context Low-Resource Language Learners](https://mlsanity.com/paper/2403.16512/) (2024)
- [Democratizing Neural Machine Translation with OPUS-MT](https://mlsanity.com/paper/2212.01936/) (2022)
- [AutoPDL: Automatic Prompt Optimization for LLM Agents](https://mlsanity.com/paper/2504.04365/) (2025)
- [Leveraging Open-Source Large Language Models for Clinical Information Extraction in Resource-Constrained Settings](https://mlsanity.com/paper/2507.20859/) (2025)
- [ChocoLlama: Lessons Learned From Teaching Llamas Dutch](https://mlsanity.com/paper/2412.07633/) (2024)
- [The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints](https://mlsanity.com/paper/2407.19299/) (2024)

## Abstract (arXiv)

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.