# Toward Mask Annotation-Free Surgical Instrument Segmentation from Endoscopic Images Using Text-Prompted Segment Anything Model 3 (SAM3)

arXiv: https://arxiv.org/abs/2608.08844 · HTML: https://mlsanity.com/paper/2608.08844/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 28 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation](https://mlsanity.com/paper/2308.08746/) (2023)
- [Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding](https://mlsanity.com/paper/2510.08668/) (2025)
- [Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning](https://mlsanity.com/paper/1803.01207/) (2018)
- [ISINet: An Instance-Based Approach for Surgical Instrument Segmentation](https://mlsanity.com/paper/2007.05533/) (2020)
- [Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video](https://mlsanity.com/paper/1907.07899/) (2019)
- [Pixel-Wise Recognition for Holistic Surgical Scene Understanding](https://mlsanity.com/paper/2401.11174/) (2024)
- [TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery](https://mlsanity.com/paper/2202.08453/) (2022)
- [MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation](https://mlsanity.com/paper/2303.09514/) (2023)
- [From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments](https://mlsanity.com/paper/2211.16200/) (2022)
- [SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation](https://mlsanity.com/paper/2308.07156/) (2023)
- [Text Promptable Surgical Instrument Segmentation with Vision-Language Models](https://mlsanity.com/paper/2306.09244/) (2023)
- [U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical Instrument](https://mlsanity.com/paper/1902.08994/) (2019)
- [SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement](https://mlsanity.com/paper/2502.06756/) (2025)
- [Real-time Instance Segmentation of Surgical Instruments using Attention and Multi-scale Feature Fusion](https://mlsanity.com/paper/2111.04911/) (2021)
- [Deep Learning for Surgical Instrument Recognition and Segmentation in Robotic-Assisted Surgeries: A Systematic Review](https://mlsanity.com/paper/2410.07269/) (2024)
- [Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2](https://mlsanity.com/paper/2408.01648/) (2024)
- [Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery](https://mlsanity.com/paper/2404.14040/) (2024)
- [Evaluating Large Vision-language Models for Surgical Tool Detection](https://mlsanity.com/paper/2601.16895/) (2026)

## Abstract (arXiv)

Surgical instrument segmentation is a fundamental task for computer-assisted interventions, yet most existing methods rely on pixel-level annotations or manual spatial prompts, which limit scalability and automation. The recently introduced Segment Anything Model 3 (SAM3) offers a pathway to annotation-free, automatic segmentation via text-based prompting; however, the instrument name as a text prompt could not be directly used due to a large domain gap. To overcome these limitations, we propose a two-stage framework that achieves instance-level segmentation without requiring ground truth masks or manual interaction. In the first stage, we leverage a natural-language-aligned generic prompt - "tool" - to produce binary masks using SAM3's zero-shot capability. In the second stage, these masks are extended to instance-level by integrating a vision-language model (Qwen) that is fine-tuned on SAM3-generated masked regions for instrument classification. We evaluate our approach on the EndoVis 2017 and 2018 datasets. Results show that, while our two-stage approach does not reach the performance of current fully supervised methods, it significantly outperforms the direct use of SAM3 for instance-level instrument segmentation with text prompts. Overall, our findings highlight both the limitations and potential of SAM3, suggesting a promising direction toward annotation-free surgical instrument segmentation.