BTReport: A Framework for Brain Tumor Radiology Report Generation with Clinically Relevant Features

Juampablo E Heras Rivera, Dickson T Chen, Tianyi Ren, Daniel Low, Asma Ben Abacha, Alberto Santamaria-Pang, Mehmet Kurt

Keywords: Brain MRI, Radiology report generation, VASARI, Midline shift, Open dataset, Multimodal learning, Neurooncology

TL;DR: We generate Findings sections for brain tumor imaging using a two-stage approach: first quantitative features are extracted, then LLMs are used for report writing.

Abstract: Recent advances in radiology report generation (RRG) have been driven by large paired image-text datasets; however, progress in neuro-oncology RRG has been limited due to a lack of open paired image-report datasets. Here, we introduce BTReport, an open-source framework for brain tumor RRG that constructs natural language radiology reports using reliably extracted quantitative imaging features. Unlike existing approaches that rely on large general-purpose or fine-tuned vision-language models for both image interpretation and report composition, BTReport first performs deterministic feature extraction of clinically-relevant features, then uses large language models only for syntactic structuring and narrative formatting. By separating RRG into a deterministic feature extraction step and a report generation step, the generated reports are completely interpretable and less prone to hallucinations. We show that the features used for report generation are predictive of key clinical outcomes, including survival time, and reports generated by BTReport are more closely aligned with reference clinical reports than existing baselines for RRG. Finally, to further research in neuro-oncology RRG, we introduce BTReport-BraTS, a companion dataset that augments BraTS imaging with synthetically generated radiology reports produced with BTReport. Code for this project can be found at: \url{https://github.com/KurtLabUW/BTReport}.

Primary Subject Area: Integration of Imaging and Clinical Data

Secondary Subject Area: Generative Models

Registration Requirement: Yes

Reproducibility: https://github.com/KurtLabUW/BTReport

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Replace NNN with your OpenReview submission ID., Includes \documentclass{midl}, \jmlryear{2026}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package., Did not use the times package., Use the correct spelling and format, avoid Unicode characters, and use LaTeX equivalents instead., Any math in the title and abstract must be enclosed within $...$., Did not override the bibliography style defined in midl.cls and did not use \begin{thebibliography} directly to insert references., Avoid using \scalebox; use \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., No separate supplementary PDF uploads., Acknowledgements, references, and appendix must start after the main content.

Submission Number: 115