jusiro2/CXR_Unimodal_CM

A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?

• Code: DLILP
• Paper: IPMI 2025 - ArXiv
• Docs: Documentation
• Tutorial: Notebook

About "CXR_Unimodal_CM" weights:

• A vision encoder for CXR pre-trained using only a vision encoder, via labels extracted trough NER extraction methods.
• Pre-trained on CheXpert and MIMIC data.

If you find this repository useful, please consider citing this paper:

@inproceedings{dlilp,
    title={A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?},
    author={Julio Silva-Rodríguez and Jose Dolz and Ismail {Ben Ayed}},
    booktitle={Information Processing in Medical Imaging (IPMI)},
    year={2025}
}