# Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation

arXiv: https://arxiv.org/abs/2509.24739 · HTML: https://mlsanity.com/paper/2509.24739/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 37 of its 67 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [HuatuoGPT, towards Taming Language Model to Be a Doctor](https://mlsanity.com/paper/2305.15075/) (2023)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models](https://mlsanity.com/paper/2404.00578/) (2024)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training](https://mlsanity.com/paper/2105.11333/) (2021)
- [CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging](https://mlsanity.com/paper/2403.06801/) (2024)
- [RoentGen: Vision-Language Foundation Model for Chest X-ray Generation](https://mlsanity.com/paper/2211.12737/) (2022)
- [Knowledge Matters: Radiology Report Generation with General and Specific Knowledge](https://mlsanity.com/paper/2112.15009/) (2021)
- [GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes](https://mlsanity.com/paper/2305.16037/) (2023)
- [Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare](https://mlsanity.com/paper/2310.17956/) (2023)
- [XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models](https://mlsanity.com/paper/2306.07971/) (2023)
- [ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset](https://mlsanity.com/paper/2405.10004/) (2024)
- [ELIXR: Towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders](https://mlsanity.com/paper/2308.01317/) (2023)

## Built on by (most cited first, 7 of 7)

- [PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting](https://mlsanity.com/paper/2510.27680/) (2025)
- [Unveiling and Bridging the Functional Perception Gap in MLLMs: Atomic Visual Alignment and Hierarchical Evaluation via PET-Bench](https://mlsanity.com/paper/2601.02737/) (2026)
- [Vision-Language Models for Automated 3D PET/CT Report Generation](https://mlsanity.com/paper/2511.20145/) (2025)
- [PADM: A Physics-aware Diffusion Model for Attenuation Correction](https://mlsanity.com/paper/2511.06948/) (2025)
- [An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation](https://mlsanity.com/paper/2605.21835/) (2026)
- [Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework](https://mlsanity.com/paper/2604.18145/) (2026)
- [MUST-PET: MUltimodal Self-supervised learning across Tracers for whole-body PET/CT-based lesion segmentation](https://mlsanity.com/paper/2608.19666/) (2026)

## Abstract (arXiv)

Vision-Language Foundation Models (VLMs), trained on large-scale multimodal datasets, have driven significant advances in Artificial Intelligence (AI) by enabling rich cross-modal reasoning. Despite their success in general domains, applying these models to medical imaging remains challenging due to the limited availability of diverse imaging modalities and multilingual clinical data. Most existing medical VLMs are trained on a subset of imaging modalities and focus primarily on high-resource languages, thus limiting their generalizability and clinical utility. To address these limitations, we introduce a novel Vietnamese-language multimodal medical dataset consisting of 2,757 whole-body PET/CT volumes from independent patients and their corresponding full-length clinical reports. This dataset is designed to fill two pressing gaps in medical AI development: (1) the lack of PET/CT imaging data in existing VLMs training corpora, which hinders the development of models capable of handling functional imaging tasks; and (2) the underrepresentation of low-resource languages, particularly the Vietnamese language, in medical vision-language research. To the best of our knowledge, this is the first dataset to provide comprehensive PET/CT-report pairs in Vietnamese. We further introduce a training framework to enhance VLMs' learning, including data augmentation and expert-validated test sets. We conduct comprehensive experiments benchmarking state-of-the-art VLMs on downstream tasks. The experimental results show that incorporating our dataset significantly improves the performance of existing VLMs. We believe this dataset and benchmark will serve as a pivotal step in advancing the development of more robust VLMs for medical imaging, especially for low-resource languages and clinical use in Vietnamese healthcare. The source code is available at https://github.com/AIoT-Lab-BKAI/ViPET-ReportGen.