README.md

metadata

license: apache-2.0
library_name: pytorch
tags:
  - Medical Imaging Foundation Model

MerMED-FM Model Card

A self-supervised multi-specialty imaging foundation model that supports 7 medical imaging modalities.

Model Details

• Model Type: Image classification / feature backbone
• Architecture: ViT-Base-Patch16 image encoder
• Model Stats:
  • Params (M): 85.8
  • GMACs: 16.9
  • Activations (M): 16.5
  • Image size: 224 x 224
• Paper Papers: Multi-Modal, Multi-Disease Medical Imaging Foundation Model
• Code: https://github.com/yangzhou12/MerMED

Intended Use

• Primary Use Cases:
  • Medical Image Classification
  • Medical Image Embedding Extraction

Pre-Training Data

• Dataset:
  • Data source(s): MerMED-Data-3.5M
  • Types of medical images: Computed Tomography (CT), Chest X-Ray (CXR), Colour Fundus Photography (CFP), Optical Coherence Tomography (OCT), Histopathology, Ultrasound, and Dermatology images

Citations

@article{zhou2025mermedfm,
  title        = {Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM)},
  author       = {Yang Zhou and Chrystie Wan Ning Quek and Jun Zhou and Yan Wang and Yang Bai and Yuhe Ke and Jie Yao and Laura Gutierrez and Zhen Ling Teo and Darren Shu Jeng Ting and Brian T. Soetikno and Christopher S. Nielsen and Tobias Elze and Zengxiang Li and Linh Le Dinh and Lionel Tim-Ee Cheng and Tran Nguyen Tuan Anh and Chee Leong Cheng and Tien Yin Wong and Nan Liu and Iain Beehuat Tan and Tony Kiat Hon Lim and Rick Siow Mong Goh and Yong Liu and Daniel Shu Wei Ting},
  journal      = {arXiv preprint arXiv:2507.00185},
  year         = {2025},
  doi          = {10.48550/arXiv.2507.00185},
  url          = {https://arxiv.org/abs/2507.00185},
  archivePrefix= {arXiv},
  eprint       = {2507.00185},
  primaryClass = {eess.IV}
}