A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling
It is demonstrated that even with multi-billion parameter models and extensive training, current Vision Language Models fall short in the seemingly simple task of tool detection in neurosurgery, and experiments suggest that current models could still face significant obstacles in surgical use cases.
K. Skobelev, Eric Fithian, Yegor Baranovski et al.
· 0 citations