# SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation

arXiv: https://arxiv.org/abs/2308.07156 · HTML: https://mlsanity.com/paper/2308.07156/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 14 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [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)
- [Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging](https://mlsanity.com/paper/2304.04155/) (2023)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [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)
- [When SAM Meets Medical Images: An Investigation of Segment Anything Model (SAM) on Multi-phase Liver Tumor Segmentation](https://mlsanity.com/paper/2304.08506/) (2023)
- [SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery](https://mlsanity.com/paper/2304.09974/) (2023)
- [TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery](https://mlsanity.com/paper/2202.08453/) (2022)
- [From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments](https://mlsanity.com/paper/2211.16200/) (2022)
- [Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding](https://mlsanity.com/paper/2201.11957/) (2022)
- [Real-Time Instrument Segmentation in Robotic Surgery using Auxiliary Supervised Deep Adversarial Learning](https://mlsanity.com/paper/2007.11319/) (2020)
- [ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery](https://mlsanity.com/paper/2112.08189/) (2021)
- [AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery](https://mlsanity.com/paper/2003.04769/) (2020)
- [Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need](https://mlsanity.com/paper/2206.11804/) (2022)

## Built on by (most cited first, 30 of 30)

- [SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation](https://mlsanity.com/paper/2308.08746/) (2023)
- [MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation](https://mlsanity.com/paper/2309.08842/) (2023)
- [Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model](https://mlsanity.com/paper/2401.17868/) (2024)
- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery](https://mlsanity.com/paper/2401.06013/) (2024)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [Foundation Models for Biomedical Image Segmentation: A Survey](https://mlsanity.com/paper/2401.07654/) (2024)
- [APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.08372/) (2024)
- [FRoundation: Are Foundation Models Ready for Face Recognition?](https://mlsanity.com/paper/2410.23831/) (2024)
- [SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation](https://mlsanity.com/paper/2408.04593/) (2024)
- [FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection](https://mlsanity.com/paper/2501.02892/) (2025)
- [MADation: Face Morphing Attack Detection with Foundation Models](https://mlsanity.com/paper/2501.03800/) (2025)
- [SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation](https://mlsanity.com/paper/2312.14481/) (2023)
- [Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery](https://mlsanity.com/paper/2404.14040/) (2024)
- [Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review](https://mlsanity.com/paper/2502.14886/) (2025)
- [Recent Advances in Medical Imaging Segmentation: A Survey](https://mlsanity.com/paper/2505.09274/) (2025)
- [SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification](https://mlsanity.com/paper/2407.17689/) (2024)
- [Few-Shot Adaptation of Training-Free Foundation Model for 3D Medical Image Segmentation](https://mlsanity.com/paper/2501.09138/) (2025)
- [SASVi -- Segment Any Surgical Video](https://mlsanity.com/paper/2502.09653/) (2025)
- [Robust SAM: On the Adversarial Robustness of Vision Foundation Models](https://mlsanity.com/paper/2504.08906/) (2025)
- [EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3](https://mlsanity.com/paper/2511.15833/) (2025)
- [Continual Learning for Segment Anything Model Adaptation](https://mlsanity.com/paper/2412.06418/) (2024)
- [StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models](https://mlsanity.com/paper/2603.07307/) (2026)
- [EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery](https://mlsanity.com/paper/2506.06830/) (2025)
- [More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery](https://mlsanity.com/paper/2512.07596/) (2025)
- [LapFM: A Laparoscopic Segmentation Foundation Model via Hierarchical Concept Evolving Pre-training](https://mlsanity.com/paper/2512.08439/) (2025)
- [When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuning](https://mlsanity.com/paper/2608.21300/) (2026)
- [RobustSurg: Tackling domain generalisation for out-of-distribution surgical scene segmentation](https://mlsanity.com/paper/2512.02188/) (2025)
- [Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos](https://mlsanity.com/paper/2606.31007/) (2026)
- [Toward Mask Annotation-Free Surgical Instrument Segmentation from Endoscopic Images Using Text-Prompted Segment Anything Model 3 (SAM3)](https://mlsanity.com/paper/2608.08844/) (2026)

## Abstract (arXiv)

The Segment Anything Model (SAM) serves as a fundamental model for semantic segmentation and demonstrates remarkable generalization capabilities across a wide range of downstream scenarios. In this empirical study, we examine SAM's robustness and zero-shot generalizability in the field of robotic surgery. We comprehensively explore different scenarios, including prompted and unprompted situations, bounding box and points-based prompt approaches, as well as the ability to generalize under corruptions and perturbations at five severity levels. Additionally, we compare the performance of SAM with state-of-the-art supervised models. We conduct all the experiments with two well-known robotic instrument segmentation datasets from MICCAI EndoVis 2017 and 2018 challenges. Our extensive evaluation results reveal that although SAM shows remarkable zero-shot generalization ability with bounding box prompts, it struggles to segment the whole instrument with point-based prompts and unprompted settings. Furthermore, our qualitative figures demonstrate that the model either failed to predict certain parts of the instrument mask (e.g., jaws, wrist) or predicted parts of the instrument as wrong classes in the scenario of overlapping instruments within the same bounding box or with the point-based prompt. In fact, SAM struggles to identify instruments in complex surgical scenarios characterized by the presence of blood, reflection, blur, and shade. Additionally, SAM is insufficiently robust to maintain high performance when subjected to various forms of data corruption. We also attempt to fine-tune SAM using Low-rank Adaptation (LoRA) and propose SurgicalSAM, which shows the capability in class-wise mask prediction without prompt. Therefore, we can argue that, without further domain-specific fine-tuning, SAM is not ready for downstream surgical tasks.