--- title: "Structured Radiology Intelligence: Extracting Structured Data" description: "The paper tackles the conversion of free-text doctor notes on MRI reports into a standardized JSON record, so the data can feed… 1 reference." authors: ["Sushvin Marimuthu", "Parameswari Krishnamurthy", "Dipti Misra Sharma", "Goldwin H", "Anu Eapen", "Betty Simon", "Anuradha Chandramohan"] year: 2026 venue: "Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026" source: "https://aclanthology.org/2026.cl4health-1.24/" doi: "10.63317/4vob5zztrfso" licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)" licence_url: "https://creativecommons.org/licenses/by-nc/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/marimuthu-2026-structured-radiology-intelligence-extracting-structured/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/marimuthu-2026-structured-radiology-intelligence-extracting-structured/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/) / Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs # Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs **Authors:** Sushvin Marimuthu, [Parameswari Krishnamurthy](https://md.research.elamur.ai/free/en/authors/parameswari-krishnamurthy/), [Dipti Misra Sharma](https://md.research.elamur.ai/free/en/authors/dipti-misra-sharma/), Goldwin H, Anu Eapen, Betty Simon and Anuradha Chandramohan · **Year:** 2026 · **Venue:** [Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/cl4health/) ([Workshop on Patient-Oriented Language Processing @ LREC 2026](https://md.research.elamur.ai/free/en/venues/cl4health/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.cl4health-1.24/) · [PDF](https://aclanthology.org/2026.cl4health-1.24.pdf) · [DOI 10.63317/4vob5zztrfso](https://doi.org/10.63317/4vob5zztrfso) · [OpenAlex](https://openalex.org/W7166506084) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary The paper tackles the conversion of free-text doctor notes on MRI reports into a standardized JSON record, so the data can feed hospital information systems, clinical decision support and large-scale analysis. The authors, from IIIT Hyderabad and CMC Vellore, gathered 630 de-identified notes from an academic health center. Clinicians defined 55 variables, and the examples suggest a rectal cancer focus: tumour measurements, CRM/MRF involvement, EMVI, TNM stage and MR TRG. Annotations were built step by step. LLM drafts were checked by the authors and then by doctors in a custom web tool, and prompts were revised whenever clinicians disagreed with the output. Experiments ran in three stages: baseline, intermediate and fine-tuned. They compared zero-, one- and few-shot settings with one-question, multi-question and all-question prompts across LLaMA, Qwen and DeepSeek models. LLaMA 3.1 8B Instruct ranked best in the later stages, and after fine-tuning it reached a composite score of 87.36%. The work matters because labeled resources pairing unstructured radiology notes with structured outputs are scarce. However, the dataset is not released for privacy reasons; only the model is shared. ## Key points - The data comes from 630 MRI doctor notes and is organized into dataset versions V1–V5: - 60 doctor-validated reports serve as the gold test set. - 65 reports supply prompt examples. - 300 validated reports are used for fine-tuning. - With the basic one-question prompt, LLaMA 3.1 8B Instruct scored 61.16% against the validated data. Typical errors included: - spurious "not mentioned" labels; - repeated numbers; - inconsistent yes/no answers; - hallucinations. - Under that baseline prompt, the seven models scored as follows: - Qwen3 4B Instruct-2507: 64.49% (best) - Qwen2.5 7B Instruct: 63.84% - DeepSeek R1 Distill Llama 8B: 63.01% - DeepSeek R1 Distill Qwen 7B: 53.94% - Llama 3.2 3B Instruct: 35.56% - MMed Llama 3 8B: 34.86% - Enhanced prompts define how to extract each variable, including implicitly stated information. They use labels such as "Not Mentioned" and "Not Relevant" and group related variables together. - Fine-tuned LLaMA 3.1 8B Instruct achieved the top composite score of 87.36%. The abstract reports an 18.42% improvement but does not state which stage it is measured against. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [International Institute of Information Technology, Hyderabad](https://md.research.elamur.ai/free/en/universities/international-institute-of-information-technology-hyderabad/) — University, Hyderabad, India · 38 works · 1,821 citations Also on the byline: [Christian Medical College, Vellore](https://ror.org/00c7kvd80). 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 234 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 231 works ## Cite Cite as: Sushvin Marimuthu, Parameswari Krishnamurthy, Dipti Misra Sharma, Goldwin H, Anu Eapen, Betty Simon and Anuradha Chandramohan. 2026. Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs. Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{marimuthu2026structured, title = {{Structured Radiology Intelligence: Extracting Structured Data from MRI Reports Using LLMs}}, author = {Sushvin Marimuthu, Parameswari Krishnamurthy, Dipti Misra Sharma, Goldwin H, Anu Eapen, Betty Simon and Anuradha Chandramohan}, booktitle = {Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026}, year = {2026}, doi = {10.63317/4vob5zztrfso}, url = {https://doi.org/10.63317/4vob5zztrfso} } ``` - [← previous Structured Prompting for Arabic Essay Proficiency: A Trait-Centric Evaluation Approach](https://md.research.elamur.ai/free/en/papers/mandhari-2026-structured-prompting-arabic-essay-proficiency/) - [next → STRUDEL: Unrolling a Benchmark for Evaluating Vision-Language Models on Structured Diagram Understanding across Domains](https://md.research.elamur.ai/free/en/papers/steinigen-2026-strudel-unrolling-benchmark-evaluating-vision/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/) ## References 1 references, 1 of them with a card of ours. ↗ leads to the work. 1. DeepSeek-AI. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). \#\# Conclusion *Updated 1 November 2026*