# From Generalization to Precision: Exploring SAM for Tool Segmentation in Surgical Environments

arXiv: https://arxiv.org/abs/2402.17972 · HTML: https://mlsanity.com/paper/2402.17972/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [SAM Meets Robotic Surgery: An Empirical Study in Robustness Perspective](https://mlsanity.com/paper/2304.14674/) (2023)
- [CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Data](https://mlsanity.com/paper/2203.09475/) (2022)

## Built on by (most cited first, 3 of 3)

- [OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding](https://mlsanity.com/paper/2503.01646/) (2025)
- [Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review](https://mlsanity.com/paper/2502.14886/) (2025)
- [A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness](https://mlsanity.com/paper/2503.02797/) (2025)

## Abstract (arXiv)

Purpose: Accurate tool segmentation is essential in computer-aided procedures. However, this task conveys challenges due to artifacts' presence and the limited training data in medical scenarios. Methods that generalize to unseen data represent an interesting venue, where zero-shot segmentation presents an option to account for data limitation. Initial exploratory works with the Segment Anything Model (SAM) show that bounding-box-based prompting presents notable zero-short generalization. However, point-based prompting leads to a degraded performance that further deteriorates under image corruption. We argue that SAM drastically over-segment images with high corruption levels, resulting in degraded performance when only a single segmentation mask is considered, while the combination of the masks overlapping the object of interest generates an accurate prediction. Method: We use SAM to generate the over-segmented prediction of endoscopic frames. Then, we employ the ground-truth tool mask to analyze the results of SAM when the best single mask is selected as prediction and when all the individual masks overlapping the object of interest are combined to obtain the final predicted mask. We analyze the Endovis18 and Endovis17 instrument segmentation datasets using synthetic corruptions of various strengths and an In-House dataset featuring counterfactually created real-world corruptions. Results: Combining the over-segmented masks contributes to improvements in the IoU. Furthermore, selecting the best single segmentation presents a competitive IoU score for clean images. Conclusions: Combined SAM predictions present improved results and robustness up to a certain corruption level. However, appropriate prompting strategies are fundamental for implementing these models in the medical domain.