RoentGen: Vision-Language Foundation Model for Chest X-ray Generation

doi:doi:10.57702/4gsh3dkb

RoentGen: Vision-Language Foundation Model for Chest X-ray Generation

Multimodal models trained on large natural image-text pair datasets have exhibited astounding abilities in gener-ating high-quality images. Medical imaging data is fundamentally different to natural images, and the language used to succinctly capture relevant details in medical data uses a different, narrow but semantically rich, domain-speciﬁc vocabulary.

BibTex:

@dataset{Pierre_Chambon_and_Christian_Bluethgen_and_Jean-Benoit_Delbrouck_and_Rogier_Van_der_Sluijs_and_Małgorzata_Połacin_and_Juan_Manuel_Zambrano_Chaves_and_Tanishq_Mathew_Abraham_and_Shivanshu_Purohit_and_Curtis_P_Langlotz_and_Akshay_Chaudhari_2024,
    abstract = {Multimodal models trained on large natural image-text pair datasets have exhibited astounding abilities in gener-ating high-quality images. Medical imaging data is fundamentally different to natural images, and the language used to succinctly capture relevant details in medical data uses a different, narrow but semantically rich, domain-speciﬁc vocabulary.},
    author = {Pierre Chambon and Christian Bluethgen and Jean-Benoit Delbrouck and Rogier Van der Sluijs and Małgorzata Połacin and Juan Manuel Zambrano Chaves and Tanishq Mathew Abraham and Shivanshu Purohit and Curtis P. Langlotz and Akshay Chaudhari},
    doi = {10.57702/4gsh3dkb},
    institution = {No Organization},
    keyword = {'chest x-ray', 'image generation', 'medical imaging', 'natural language processing'},
    month = {dec},
    publisher = {TIB},
    title = {RoentGen: Vision-Language Foundation Model for Chest X-ray Generation},
    url = {https://service.tib.eu/ldmservice/dataset/roentgen--vision-language-foundation-model-for-chest-x-ray-generation},
    year = {2024}
}