VinDr-CXR-VQA: A Visual Question Answering Dataset for Explainable Chest X-Ray Analysis with Multi-Task Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915605872902144 |
|---|---|
| author | Nguyen, Dang H. Pham, Hieu H. Nguyen, Hao T. Pham, Hieu H. |
| author_facet | Nguyen, Dang H. Pham, Hieu H. Nguyen, Hao T. Pham, Hieu H. |
| contents | We present VinDr-CXR-VQA, a large-scale chest X-ray dataset for explainable Medical Visual Question Answering (Med-VQA) with spatial grounding. The dataset contains 17,597 question-answer pairs across 4,394 images, each annotated with radiologist-verified bounding boxes and clinical reasoning explanations. Our question taxonomy spans six diagnostic types-Where, What, Is there, How many, Which, and Yes/No-capturing diverse clinical intents. To improve reliability, we construct a balanced distribution of 41.7% positive and 58.3% negative samples, mitigating hallucinations in normal cases. Benchmarking with MedGemma-4B-it demonstrates improved performance (F1 = 0.624, +11.8% over baseline) while enabling lesion localization. VinDr-CXR-VQA aims to advance reproducible and clinically grounded Med-VQA research. The dataset and evaluation tools are publicly available at huggingface.co/datasets/Dangindev/VinDR-CXR-VQA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00504 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VinDr-CXR-VQA: A Visual Question Answering Dataset for Explainable Chest X-Ray Analysis with Multi-Task Learning Nguyen, Dang H. Pham, Hieu H. Nguyen, Hao T. Pham, Hieu H. Computer Vision and Pattern Recognition We present VinDr-CXR-VQA, a large-scale chest X-ray dataset for explainable Medical Visual Question Answering (Med-VQA) with spatial grounding. The dataset contains 17,597 question-answer pairs across 4,394 images, each annotated with radiologist-verified bounding boxes and clinical reasoning explanations. Our question taxonomy spans six diagnostic types-Where, What, Is there, How many, Which, and Yes/No-capturing diverse clinical intents. To improve reliability, we construct a balanced distribution of 41.7% positive and 58.3% negative samples, mitigating hallucinations in normal cases. Benchmarking with MedGemma-4B-it demonstrates improved performance (F1 = 0.624, +11.8% over baseline) while enabling lesion localization. VinDr-CXR-VQA aims to advance reproducible and clinically grounded Med-VQA research. The dataset and evaluation tools are publicly available at huggingface.co/datasets/Dangindev/VinDR-CXR-VQA. |
| title | VinDr-CXR-VQA: A Visual Question Answering Dataset for Explainable Chest X-Ray Analysis with Multi-Task Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.00504 |