Vietnamese brain MRI dataset enables better automated radiology reports
ViBMR: A Large-Scale Multi-Sequence Brain MRI Dataset and Comprehensive Evaluation for Vietnamese Radiology Report Generation
Computer Vision and Pattern Recognition
Summary
Radiology reports from brain MRI scans help doctors diagnose patients but writing them takes a lot of time, especially for less common languages like Vietnamese. The authors created a large collection of brain MRI scans paired with Vietnamese clinical reports to help build automated report-writing computer models. They tested various machine learning methods on this dataset to understand how to combine images from different MRI types effectively. Their work shows that having datasets in native low-resource languages is important for reliable automated reporting.
What this means in practice
- •For radiology ai developers: Train and evaluate automated report generation systems on Vietnamese brain MRI scans with paired clinical text to improve diagnostic support.
- •For medical language technology teams: Use the ViBMR dataset to build or enhance Vietnamese clinical natural language processing tools for radiology workflows.
Authors
Dai Lam Le, Minh Khoi Nguyen, Son Dinh Nguyen, Amir Reza Jafari, Viet Ha, Nguyen Son, Reza Farahbakhsh, Noel Crespi, Phi Le Nguyen
Abstract
Automated radiology report generation for multi-sequence brain MRI holds strong promise for alleviating radiologists' workload, yet it remains a demanding problem: brain MRI studies are inherently volumetric, each pulse sequence carries complementary diagnostic information, and annotated data are critically scarce for low-resource clinical languages. Existing brain MRI-report resources are still dominated by English reports, translated clinical text, or datasets adapted from task-specific imaging benchmarks, leaving routine low-resource clinical reporting and heterogeneous multi-sequence MRI protocols insufficiently represented. To bridge this gap, we introduce ViBMR, to the best of our knowledge, the first large-scale multi-sequence brain MRI dataset paired with routine Vietnamese clinical reports, comprising 3,649 patients and 11,875 MRI series across T1, T2, FLAIR, and contrast-enhanced T1 sequences. Building on ViBMR, we establish a comprehensive evaluation setup for brain MRI report generation, covering representative medical vision-language models, multi-sequence inputs, and feature aggregation strategies. The results provide key insights into dataset characteristics and model behavior, while demonstrating the necessity of native low-resource clinical datasets for reliable Vietnamese-origin brain MRI report generation. Our dataset and baseline models will be released for non-commercial research.