arXiv cs.AI· Alejandra Perez, Anita Rau, Busisiwe Mlambo, Lee White, Aina Brunet, Juan Verde, Juan Caicedo, Jo\"el L. Lavanchy, Adam Schmidt, Chinedu Nwoye, Omid Mohareri, Muhammad Abdullah Jamal·· 15 小时前AI 评分38
SUREON：面向手术推理的基准与视觉语言模型
SUREON: A Benchmark and Vision-Language Model for Surgical Reasoning
AI 导读
研究团队推出 SUREON 视频问答数据集与基准，用于评估真正依赖视觉证据的手术推理，包含 76K 训练问答对、覆盖 168 种手术和 10 个专科，另有 340 道经外科专家审核的测试题。测试显示现有领先商业与开源模型均未超过 53% 准确率，专家外科医生也仅达 64.9%。基于该数据训练的 SUREON-VLM 在 SUREON 上优于现有开源模型，并在多个标准手术基准上追平更大的专科模型。
正文 · 原文
Authors:Alejandra Perez, Anita Rau, Busisiwe Mlambo, Lee White, Aina Brunet, Juan Verde, Juan Caicedo, Joël L. Lavanchy, Adam Schmidt, Chinedu Nwoye, Omid Mohareri, Muhammad Abdullah Jamal
Abstract:A capable surgical AI model should reason from visual evidence; yet, many existing surgical benchmarks can be partially solved without visual input, as models may exploit procedural priors or common anatomy-instrument interactions to infer answers from language alone. To address this, we introduce SUREON, a video question-answering (QA) dataset and benchmark designed to evaluate visually grounded surgical reasoning. Our pipeline generates QA pairs from narrated surgical academic videos, refines incorrect options using multiple models to reduce linguistic biases, and uses trained adversarial guessers to filter out questions answerable without visual evidence. The resulting dataset contains 76K training pairs covering 168 procedures and 10 specialties, alongside a benchmark of 340 questions across 10 categories verified by expert surgeons. Benchmarking leading commercial and open-source models shows that surgical visual reasoning remains largely unsolved--no model exceeds 53% accuracy and even expert surgeons reach only 64.9%. We also introduce SUREON-VLM, a baseline trained on our curated data that avoids language shortcuts, outperforms existing open-source models on SUREON, and matches larger specialist models on multiple standard surgical benchmarks. Our training ablations show that distractor refinement and blind curation strengthen visual grounding, increasing the multimodal gain from 8.7 to 29.1 percentage points while reducing the training set from 176.6K to 76K filtered samples. SUREON thus offers both a verified testbed for surgical visual reasoning and training data that strengthens visual grounding.
| Comments: | WACV 2027 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.06570 [cs.CV] |
| (or arXiv:2603.06570v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2603.06570 arXiv-issued DOI via DataCite |
Submission history
From: Anita Rau [view email]
[v1]
Fri, 6 Mar 2026 18:58:36 UTC (644 KB)
[v2]
Fri, 30 Oct 2026 17:58:13 UTC (9,712 KB)
来源：arXiv cs.AI · arxiv.org