This repository curates foundational models for vision and language tasks within medical imaging, serving researchers and practitioners in the field. It provides a comprehensive overview and a categorized list of relevant papers, enabling users to explore state-of-the-art approaches for medical AI applications.

How It Works

The project acts as a living bibliography, categorizing foundation models based on their training strategies and application domains. It covers textual prompted models, contrastive learning approaches, generative models, and adaptations of generalist models like SAM for medical use cases. This structured approach facilitates understanding the landscape of foundation models in medical imaging.

Quick Start & Requirements

This is a curated list of research papers and does not involve direct code execution. Users can access the survey paper and individual research papers via provided arXiv and publication links.

Highlighted Details

• Features a comprehensive survey paper on "Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision."
• Categorizes models by modality (vision, language, multimodal) and task type (textual prompted, contrastive, generative, visual prompted).
• Includes links to papers, GitHub repositories, and official publications for each listed model.
• Highlights adaptations of generalist models like Segment Anything Model (SAM) for medical imaging tasks.

Maintenance & Community

The project is maintained by xmindflow and encourages contributions via pull requests for relevant new papers. A citation is provided for the survey paper.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific license. Individual papers and code repositories linked within will have their own licenses.

Limitations & Caveats

This repository is a curated list of research and does not provide executable code or pre-trained models directly. Users must refer to individual paper links for implementation details and access to models.