Elamur Research⌕
☰
home / papers / 2026 / ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models

ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models

Summary

Most vision-language models (VLMs) are trained on chest X-ray data from Western populations and rarely see Vietnamese clinical text. As a result, they often misdescribe Vietnamese patients. Earlier Vietnamese radiology resources such as VinDr-CXR mostly support classification or segmentation and do not include free-text reports. ViX-Ray addresses this gap with 5,400 chest radiographs from Military Hospital 175. Each image comes with radiologist-written findings and impressions, plus anonymized age and gender. The authors parse the reports with Stanza to profile the anatomical terms and diagnoses physicians use. They then benchmark five open-source VLMs, before and after supervised fine-tuning, in three settings:

  • findings generation
  • impressions generation
  • a multi-turn dialogue combining both

The models are also compared with GPT-4V and Gemini. Fine-tuned Qwen2.5-VL-7B performs best overall and outperforms the proprietary systems. Still, all models show weak precision and frequent hallucinations, especially when writing impressions. The dataset is therefore a demanding, publicly released benchmark for Vietnamese medical multimodal AI.

Key points

  • Dataset contents: ViX-Ray has 5,400 chest X-rays from Vietnam Military Hospital 175, each paired with expert findings and impressions. Protected health information was removed, and the hospital's review board approved the study on ethical grounds.
  • Linguistic analysis: Stanza parse trees were used to extract noun phrases. Heart (tim) and lungs (phổi) are the most frequently mentioned structures, followed by ribs, diaphragm dome and pulmonary hilum. Reports often specify exact lesion locations.
  • Models tested: Vintern-1B-v3.5, Lavy, InternVL2.5, Qwen2.5-VL and MiniCPM-V-2.6, each evaluated with and without SFT.
  • Main comparison: Qwen2.5-VL-7B leads across all three evaluation stages. In the examples shown, GPT-4V sometimes declines to diagnose, and Gemini produces incorrect or invented details.
  • Availability: The dataset is released on Hugging Face as MilitaryHospital175/VNMedical_bv175. It is the only dataset in the paper's comparison table that combines Vietnamese images with both findings and impressions text.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/3do8tpzockx8

@inproceedings{nguyen2026vix,
  title = {{ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models}},
  author = {Nguyen, Duy Vu Minh and Truong, Chinh Thanh and Phúc, Trần Hoàng and Le, Hung Tuan and Dat, Nguyen Van-Thanh and Pham, Trung Hieu and Nguyen, Kiet Van},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/3do8tpzockx8},
  url = {https://doi.org/10.63317/3do8tpzockx8}
}

References

62 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774. find our card
  2. SM Nabil Ashraf, Md Adyelullahil Mamun, Hasnat Md Abdullah, and Md Golam Rabiul Alam. 2023. Synthensemble: a fusion of cnn, vision transformer, and hybrid models for multi-label chest x-ray classification. In 2023 26th International Conference on Computer and Information Technology (ICCIT), pages 1–… find
  3. Vietnamese National Assembly. 2023. Law on medical examination and treatment (revised). Published in the Official Gazette, Nos. 489–490, on February 19, 2023. find
  4. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. find our card
  5. Diane E Bild, Robert Detrano, DO Peterson, Alan Guerci, Kiang Liu, Eyal Shahar, Pamela Ouyang, Sharon Jackson, and Mohammed F Saad. 2005. Ethnic differences in coronary calcification: the multi-ethnic study of atherosclerosis (mesa). Circulation, 111(10):1313–1320. find
  6. Aurelia Bustos, Antonio Pertusa, Jose-Maria Salinas, and Maria De La Iglesia-Vaya. 2020. Padchest: A large chest x-ray image dataset with multi-label annotated reports. Medical image analysis, 66:101797. find
  7. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, et al. 2024a. Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271. find our card
  8. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, et al. 2024b. How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. Science China Information Sciences, 67(12):220101. find our card
  9. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024c. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern… find our card
  10. Khang T Doan, Bao G Huynh, Dung T Hoang, Thuc D Pham, Nhat H Pham, Quan Nguyen, Bang Q Vo, and Suong N Hoang. 2024. Vintern-1b: An efficient multimodal large language model for vietnamese. arXiv preprint arXiv:2408.12480. — [arXiv:2408.12480](https://arxiv.org/abs/2408.12480) find
  11. PM Donnelly, TS Yang, JK Peat, and AJ Woolcock. 1991. What factors explain racial differences in lung volumes? European respiratory journal, 4(7):829–838. find
  12. Sedigheh Eslami, Christoph Meinel, and Gerard de Melo. 2023. PubMedCLIP: How much does CLIP benefit visual question answering in the medical domain? In Findings of the Association for Computational Linguistics: EACL 2023, pages 1181–1193, Dubrovnik, Croatia. Association for Computational Linguistics… find
  13. Eli Gibson, Wenqi Li, Carole Sudre, Lucas Fidon, Dzhoshkun I Shakir, Guotai Wang, Zach Eaton-Rosen, Robert Gray, Tom Doel, Yipeng Hu, et al. 2018. Niftynet: a deep-learning platform for medical imaging. Computer methods and programs in biomedicine, 158:113–122. find
  14. Ben Glocker, Charles Jones, Mélanie Roschewitz, and Stefan Winzeck. 2023. Risk of bias in chest radiography deep learning foundation models. Radiology: Artificial Intelligence, 5(6):e230060. find
  15. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. find
  16. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276. find our card
  17. Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, et al. 2019. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI conference on art… find
  18. Sasank Isola and Yasir Al Khalili. 2023. Protected health information. In StatPearls [Internet]. Stat-Pearls Publishing. find
  19. Stefan Jaeger, Sema Candemir, Sameer Antani, Yì-Xiáng J Wáng, Pu-Xuan Lu, and George Thoma. 2014. Two public chest x-ray datasets for computer-aided screening of pulmonary diseases. Quantitative imaging in medicine and surgery, 4(6):475. find
  20. Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. 2019. Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data, 6(1):317. find
  21. Olga Kovaleva, Chaitanya Shivade, Satyananda Kashyap, Karina Kanjaria, Joy Wu, Deddeh Ballah, Adam Coy, Alexandros Karargyris, Yufan Guo, David Beymer Beymer, Anna Rumshisky, and Vandana Mukherjee Mukherjee. 2020. Towards visual dialog for radiology. In Proceedings of the 19th SIGBioMed Workshop on… find
  22. Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems, 36:28541–28564. find our card
  23. Haonan Li, Xudong Han, Hao Wang, Yuxia Wang, Minghan Wang, Rui Xing, Yilin Geng, Zenan Zhai, Preslav Nakov, and Timothy Baldwin. 2025. Loki: An open-source tool for fact verification. In Proceedings of the 31st International Conference on Computational Linguistics: System Demonstrations, pages 28–36… find
  24. Bo Liu, Li-Ming Zhan, Li Xu, Lin Ma, Yan Yang, and Xiao-Ming Wu. 2021. Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In 2021 IEEE 18th international symposium on biomedical imaging (ISBI), pages 1650–1654. IEEE. find
  25. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024. Improved baselines with visual instruction tuning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 26296–26306. find our card
  26. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, 36:34892–34916. find our card
  27. Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Hao Yang, et al. 2024. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525. find our card
  28. Omid Nejati Manzari, Hamid Ahmadabadi, Hossein Kashiani, Shahriar B Shokouhi, and Ahmad Ayatollahi. 2023. Medvit: a robust vision transformer for generalized medical image classification. Computers in biology and medicine, 157:106791. find
  29. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. Factscore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural L… find our card
  30. Binh D Nguyen, Thanh-Toan Do, Binh X Nguyen, Tuong Do, Erman Tjiputra, and Quang D Tran. 2019. Overcoming data limitation in medical visual question answering. In Medical Image Computing and Computer Assisted Intervention– MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2… find
  31. Chien Van Nguyen, Thuat Nguyen, Quan Nguyen, Huy Nguyen, Björn Plüster, Nam Pham, Huu Nguyen, Patrick Schramowski, and Thien Nguyen. 2023a. Vistral-7b-chat - towards a state-of-the-art large language model for vietnamese. find
  32. Ha Q Nguyen, Khanh Lam, Linh T Le, Hieu H Pham, Dat Q Tran, Dung B Nguyen, Dung D Le, Chi M Pham, Hang TT Tong, Diep H Dinh, et al. 2022a. Vindr-cxr: An open dataset of chest x-rays with radiologist’s annotations. Scientific Data, 9(1):429. find
  33. Hieu T Nguyen, Ha Q Nguyen, Hieu H Pham, Khanh Lam, Linh T Le, Minh Dao, and Van Vu. 2023b. Vindr-mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography. Scientific Data, 10(1):277. find
  34. Hoang Canh Nguyen, Tung Thanh Le, Hieu Pham, and Ha Quy Nguyen. 2021. Vindr-ribcxr: A benchmark dataset for automatic segmentation and labeling of individual ribs on chest x-rays. In Medical Imaging with Deep Learning. find
  35. Nghia Hieu Nguyen, Duong TD Vo, and Kiet Van Nguyen. 2022b. Uit-hwdb: Using transferring method to construct a novel benchmark for evaluating unconstrained handwriting image recognition in vietnamese. In 2022 RIVF International Conference on Computing and Communication Technologies (RIVF), pages 659… find
  36. Nghia Hieu Nguyen, Duong TD Vo, Kiet Van Nguyen, and Ngan Luu-Thuy Nguyen. 2023c. Openvivqa: Task, dataset, and multimodal fusion models for visual question answering in vietnamese. Information Fusion, 100:101868. find
  37. K Nickol and AJ Wade. 1982. Radiographic heart size and cardiothoracic ratio in three ethnic groups: a basis for a simple screening test for cardiac enlargement in men. The British journal of radiology, 55(654):399–403. find
  38. Luke Oakden-Rayner. 2020. Exploring large-scale public medical image datasets. Academic radiology, 27(1):106–112. find
  39. Hieu H Pham, Ngoc H Nguyen, Thanh T Tran, Tuan NM Nguyen, and Ha Q Nguyen. 2023. Pedicxr: an open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children. Scientific Data, 10(1):240. find
  40. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D Manning. 2020. Stanza: A python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Association for Computat… find our card
  41. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. Pm… find our card
  42. Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie Shpanskaya, et al. 2017. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225. — [arXiv:1711.05225](https://arxiv.org/abs/1711.05225) find
  43. Ekagra Ranjan, Soumava Paul, Siddharth Kapoor, Aupendu Kar, Ramanathan Sethuraman, and Debdoot Sheet. 2018. Jointly learning convolutional representations to compress radiological images and classify thoracic diseases in the compressed domain. In Proceedings of the 11th Indian Conference on computer… find
  44. Amber L Simpson, Michela Antonelli, Spyridon Bakas, Michel Bilello, Keyvan Farahani, Bram Van Ginneken, Annette Kopp-Schneider, Bennett A Landman, Geert Litjens, Bjoern Menze, et al. 2019. A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv pr… — [arXiv:1902.09063](https://arxiv.org/abs/1902.09063) find
  45. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805. find our card
  46. Chi Tran and Huong Le Thanh. 2024. Lavy: Vietnamese multimodal large language model. arXiv preprint arXiv:2404.07922. — [arXiv:2404.07922](https://arxiv.org/abs/2404.07922) find
  47. Minh-Nam Tran, Phu-Vinh Nguyen, Long Nguyen, and Dinh Dien. 2024a. Vimedaqa: A vietnamese medical abstractive question-answering dataset and findings of large language model. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Worksh… find
  48. Oanh Ngoc Tran, Hop Van Bui, Hoang Huy Ha, and Phuc Van Phan. 2024b. Vista. find
  49. Kiet Van Nguyen, Tin Van Huynh, Duc-Vu Nguyen, Anh Gia-Tuan Nguyen, and Ngan Luu-Thuy Nguyen. 2022. New vietnamese corpus for machine reading comprehension of health news articles. Transactions on Asian and Low-Resource Language Information Processing, 21(5):1–28. find
  50. Thanh Vu, Dat Quoc Nguyen, Dai Quoc Nguyen, Mark Dras, and Mark Johnson. 2018. Vn-CoreNLP: A Vietnamese natural language processing toolkit. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 56–60, New Orleans,… find
  51. Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, Mohammadhadi Bagheri, and Ronald M Summers. 2017. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the IEEE conference on computer vision and… find
  52. Yuxia Wang, Minghan Wang, Hasan Iqbal, Georgi N Georgiev, Jiahui Geng, Iryna Gurevych, and Preslav Nakov. 2025. Openfactcheck: Building, benchmarking customized fact-checking systems and evaluating the factuality of claims and llms. In Proceedings of the 31st International Conference on Computationa… find
  53. Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, and Jimeng Sun. 2022. Medclip: Contrastive learning from unpaired medical images and text. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, volume 2022, page… find
  54. Per Welander, Simon Karlsson, and Anders Eklund. 2018. Generative adversarial networks for image-to-image translation on multi-contrast mr images-a comparison of cyclegan and unit. arXiv preprint arXiv:1806.07777. — [arXiv:1806.07777](https://arxiv.org/abs/1806.07777) find
  55. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Juny… find
  56. Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421, 9(1):1. find our card
  57. Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, et al. 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800. find our card
  58. Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, et al. 2024a. Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback. In Proceedings of the IEEE/CVF Conference on Computer Vision an… find
  59. Tianyu Yu, Haoye Zhang, Yuan Yao, Yunkai Dang, Da Chen, Xiaoman Lu, Ganqu Cui, Taiwen He, Zhiyuan Liu, Tat-Seng Chua, et al. 2024b. Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness. arXiv preprint arXiv:2405.17220. — [arXiv:2405.17220](https://arxiv.org/abs/2405.17220) find
  60. Sheng Zhang, Yanbo Xu, Naoto Usuyama, Hanwen Xu, Jaspreet Bagga, Robert Tinn, Sam Preston, Rajesh Rao, Mu Wei, Naveen Valluri, et al. 2023. Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915. — [arXiv:2303.00915](https://arxiv.org/abs/2303.00915) find
  61. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. Minigpt-4: Enhancing vision-language understanding with advanced large language models. In 12th International Conference on Learning Representations, ICLR 2024. find our card
  62. Mohammad Zunaed, Md Aynal Haque, and Taufiq Hasan. 2024. Learning to generalize towards unseen domains via a content-aware style invariant model for disease detection from chest x-rays. IEEE Journal of Biomedical and Health Informatics. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/nguyen-2026-vix-ray-vietnamese-chest-x/