Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper investigates the performance of large Vision Language Models (VLMs) on surgical tool detection, a key task for surgical AI. Through a case study using neurosurgery data and models available in 2026, the authors find that even multi-billion parameter VLMs struggle with this task, despite extensive training. Scaling experiments reveal diminishing returns with increased model size and training time, suggesting that factors beyond data and compute limit performance.
Even with billions of parameters and extensive training, today's VLMs still stumble on seemingly simple surgical tasks like tool detection, suggesting that scaling alone won't solve the challenges of surgical AI.
Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but have lagged behind on surgical image-analysis benchmarks. Since surgery requires integrating disparate tasks --- including multimodal data integration, human interaction, and physical effects --- generally-capable AI models could be particularly attractive as a collaborative tool if performance could be improved. On the one hand, the canonical approach of scaling architecture size and training data is attractive, especially since there are millions of hours of surgical video data generated per year. On the other hand, preparing surgical data for AI training requires significantly higher levels of professional expertise, and training on that data requires expensive computational resources. These trade-offs paint an uncertain picture of whether and to-what-extent modern AI could aid surgical practice. In this paper, we explore this question through a case study of surgical tool detection using state-of-the-art AI methods available in 2026. We demonstrate 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. Additionally, we show scaling experiments indicating that increasing model size and training time only leads to diminishing improvements in relevant performance metrics. Thus, our experiments suggest that current models could still face significant obstacles in surgical use cases. Moreover, some obstacles cannot be simply ``scaled away'' with additional compute and persist across diverse model architectures, raising the question of whether data and label availability are the only limiting factors. We discuss the main contributors to these constraints and advance potential solutions.