Dai Lam Le, Minh Khoi Nguyen, Son Dinh Nguyen, Amir Reza Jafari, Viet Ha, Nguyen Son, Reza Farahbakhsh, Noël Crespi, Phi Le Nguyen · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.29905 · cited by 0 works (OpenAlex) · open-access PDF
La generación de informes de comportamiento de radiología automática para la MRI del cerebro multi-sequencia tiene una fuerte promesa de aliviar la carga de trabajo de los radiólogos, pero sigue siendo un problema exigente: los estudios de MRI del cerebro son inherentemente volumétricos, cada secuencia de pulso lleva información diagnóstica complementaria, y los datos anotados son críticamente escasos para los idiomas clínicos de bajos recursos. Los recursos de informes de MRI del cerebro existentes todavía están dominados por informes en inglés, texto clínico traducido o conjuntos de datos adaptados a partir de referencias de imagen específicas de tareas, dejando a la rutina informes clínicos de bajos recursos y los protocolos MRI heterogéneos de varias secuencias insuficientemente representados. Para hacer frente a esta brecha,
Machine translation (Meta M2M100); the English original follows.
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.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Medicine, Vietnamese, Neuroimaging, Medical physics, Computer science, Feature (linguistics)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29905, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange