BibTeX @article{ilse2025data, title={Data Scaling Laws for Radiology Foundation Models}, author={Ilse, Maximilian and Sharma, Harshita and Schwaighofer, Anton and Bond-Taylor, Sam and P{\'e}rez-Garc{\'i}a, Fernando and Melnichenko, Olesya and Sykes, Anne-Marie G. and Horst, Kelly K. and Khandelwal, Ashish and Reynolds, Maxwell and Wetscherek, Maria T. and Codella, Noel C. F. and Alvarez-Valle, Javier and Panagiotis, Korfiatis and Salvatelli, Valentina}, journal={arXiv preprint arXiv:2509.12818}, year={2025}, doi={10.48550/arXiv.2509.12818}, url={https://arxiv.org/abs/2509.12818} }
BibTeX @article{perezgarcia2025exploring, title={Exploring scalable medical image encoders beyond text supervision}, author={P{\'e}rez-Garc{\'i}a, Fernando and Sharma, Harshita and Bond-Taylor, Sam and Bouzid, Kenza and Salvatelli, Valentina and Ilse, Maximilian and Bannur, Shruthi and Castro, Daniel C. and Schwaighofer, Anton and Lungren, Matthew P. and Wetscherek, Maria Teodora and Codella, Noel and Hyland, Stephanie L. and Alvarez-Valle, Javier and Oktay, Ozan}, journal={Nature Machine Intelligence}, volume={7}, number={1}, pages={119--130}, year={2025}, doi={10.1038/s42256-024-00965-w}, url={https://www.nature.com/articles/s42256-024-00965-w} }
Image representations are commonly learned from class labels, which are a simplistic approximation of human image understanding. In this paper we demonstrate that transferable representations of images can be learned without manual annotations by …