# A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling

arXiv: https://arxiv.org/abs/2603.27341 · HTML: https://mlsanity.com/paper/2603.27341/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 66 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM](https://mlsanity.com/paper/2402.09181/) (2024)
- [PyTorch Distributed: Experiences on Accelerating Data Parallel Training](https://mlsanity.com/paper/2006.15704/) (2020)
- [Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer](https://mlsanity.com/paper/2206.11053/) (2022)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [A Rosetta Stone for AI Benchmarks](https://mlsanity.com/paper/2512.00193/) (2025)
- [MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning](https://mlsanity.com/paper/2505.16964/) (2025)
- [PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery](https://mlsanity.com/paper/2405.13949/) (2024)
- [LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings](https://mlsanity.com/paper/2503.19740/) (2025)
- [GP-VLS: A general-purpose vision language model for surgery](https://mlsanity.com/paper/2407.19305/) (2024)
- [Surgical Visual Understanding (SurgVU) Dataset](https://mlsanity.com/paper/2501.09209/) (2025)
- [SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning](https://mlsanity.com/paper/2603.06570/) (2026)

## Abstract (arXiv)

Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are often missing from prominent medical benchmark suites. Since surgery requires integrating disparate tasks, 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.