# GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation

arXiv: https://arxiv.org/abs/2603.01108 · HTML: https://mlsanity.com/paper/2603.01108/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [Surgical Data Science: Enabling Next-Generation Surgery](https://mlsanity.com/paper/1701.06482/) (2017)
- [CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80](https://mlsanity.com/paper/2012.12453/) (2020)
- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)
- [VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.12081/) (2025)
- [Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation](https://mlsanity.com/paper/2601.10880/) (2026)
- [Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models](https://mlsanity.com/paper/2501.05767/) (2025)
- [Robust Medical Instrument Segmentation Challenge 2019](https://mlsanity.com/paper/2003.10299/) (2020)
- [BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities](https://mlsanity.com/paper/2412.07769/) (2024)
- [CaDIS: Cataract Dataset for Image Segmentation](https://mlsanity.com/paper/1906.11586/) (2019)
- [CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery](https://mlsanity.com/paper/2406.16039/) (2024)
- [MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images](https://mlsanity.com/paper/2602.06965/) (2026)
- [Phase-Informed Tool Segmentation for Manual Small-Incision Cataract Surgery](https://mlsanity.com/paper/2411.16794/) (2024)

## Abstract (arXiv)

Clinically reliable perception of surgical scenes is essential for advancing intelligent, context-aware intraoperative assistance such as instrument handoff guidance, collision avoidance, and workflow-aware robotic support. Existing surgical tool benchmarks primarily evaluate category-level segmentation, requiring models to detect all instances of predefined instrument classes. However, real-world clinical decisions often require resolving references to a specific instrument instance based on its functional role, spatial relation, or anatomical interaction capabilities not captured by current evaluation paradigms. We introduce GroundedSurg, the first language-conditioned, instance-level surgical grounding benchmark. Each instance pairs a surgical image with a natural-language description targeting a single instrument, accompanied by structured spatial grounding annotations including bounding boxes and point-level anchors. The dataset spans ophthalmic, laparoscopic, robotic, and open procedures, encompassing diverse instrument types, imaging conditions, and operative complexities. By jointly evaluating linguistic reference resolution and pixel-level localization, GroundedSurg enables a systematic and realistic evaluation of vision-language models in clinically realistic multi-instrument scenes. Extensive experiments demonstrate substantial performance gaps across modern segmentation and VLMs, highlighting the urgent need for clinically grounded vision-language reasoning in surgical AI systems. Code and data are publicly available at https://github.com/gaash-lab/GroundedSurg